{ "data": [ { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part9/Y7fmOlUlwoNg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y7fmOlUlwoNg.npy", "labels": "/m/09x0r,/m/0llzx,/t/dd00127", "caption": "Constant rattling noise and sharp vibrations" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part7/Y6BJ455B1aAs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y6BJ455B1aAs.npy", "labels": "/m/014zdl,/m/07qsvvw", "caption": "A rocket flies by followed by a loud explosion and fire crackling as a truck engine runs idle" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part15/YGOD8Bt5LfDE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YGOD8Bt5LfDE.npy", "labels": "/m/07jdr,/m/09x0r,/m/0ytgt", "caption": "Humming and vibrating with a man and children speaking and laughing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YYQSuFyFm3Lc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YYQSuFyFm3Lc.npy", "labels": "/m/01g50p,/m/0284vy3,/m/06d_3,/m/07jdr", "caption": "A train running on a railroad track followed by a vehicle door closing and a man talking in the distance while a train horn honks and railroad crossing warning signals ring" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part24/YVjSEIRnLAh8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YVjSEIRnLAh8.npy", "labels": "/m/09x0r,/m/0dxrf", "caption": "Food is frying, and a woman talks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YDlWd7Wmdi1E.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YDlWd7Wmdi1E.npy", "labels": "/m/015p6,/m/07rc7d9,/m/09x0r,/m/0jbk", "caption": "A man speaks as birds chirp and dogs bark" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YYNDKuNINDOY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YYNDKuNINDOY.npy", "labels": "/m/012ndj,/m/03j1ly,/m/03kmc9", "caption": "A large truck driving by as an emergency siren wails and truck horn honks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/YfsBR7e_X_0Y.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YfsBR7e_X_0Y.npy", "labels": "/m/09x0r,/m/0ytgt,/t/dd00125", "caption": "A child yelling as a young boy talks during several slaps on a hard surface" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YtjCNwdOUiGc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YtjCNwdOUiGc.npy", "labels": "/m/07qv_d5,/m/07yv9,/m/0912c9", "caption": "An engine rumbles loudly, then an air horn honk three times" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/YyL3gKa6YLoM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YyL3gKa6YLoM.npy", "labels": "/m/01d3sd,/m/09x0r", "caption": "A person snoring with another man speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YLbken4JCr94.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YLbken4JCr94.npy", "labels": "/m/06mb1,/m/0jb2l,/m/0ngt1", "caption": "Thunder and a gentle rain" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part27/Y_xylo5_IiaM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y_xylo5_IiaM.npy", "labels": "/m/09x0r,/m/0ytgt,/t/dd00125", "caption": "A woman talks and a baby whispers" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YsVYTOURVsQ0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YsVYTOURVsQ0.npy", "labels": "/m/07pqc89,/m/09x0r", "caption": "A man talking as a stream of water trickles in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YSmdj6JFB9MQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YSmdj6JFB9MQ.npy", "labels": "/m/01jt3m,/m/09x0r", "caption": "A person briefly talks followed quickly by toilet flushing and another voice from another person" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part38/Yu84FiZ_omhA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yu84FiZ_omhA.npy", "labels": "/m/015p6,/m/07pggtn,/m/0jbk", "caption": "A woman singing then choking followed by birds chirping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/Ykx6Rj4MDIAw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ykx6Rj4MDIAw.npy", "labels": "/m/07rjwbb", "caption": "Machinery banging and hissing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YPLHXGDnig4M.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YPLHXGDnig4M.npy", "labels": "/m/01yrx,/m/07qrkrw", "caption": "A person talking which later imitates a couple of meow sounds" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YZ0IrCa4MvOA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YZ0IrCa4MvOA.npy", "labels": "/m/0130jx,/m/02jz0l,/m/07pqc89,/m/0838f", "caption": "Rain is falling continuously" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y14ekd4nkpwc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y14ekd4nkpwc.npy", "labels": "/t/dd00002", "caption": "An infant crying followed by a man laughing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/YyfYNPWs7mWY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YyfYNPWs7mWY.npy", "labels": "/m/02dgv,/m/05zppz,/m/09x0r", "caption": "A man talking as a door slams shut followed by a door creaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part38/YuhSDBwVrEdo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YuhSDBwVrEdo.npy", "labels": "/m/01w250", "caption": "Whistling with wind blowing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YYQGW5AwDOIo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YYQGW5AwDOIo.npy", "labels": "/m/07yv9,/m/0k4j,/m/0ltv", "caption": "Vehicles passing by slowly together with distant murmuring" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part19/YMe4npKmtchA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YMe4npKmtchA.npy", "labels": "/m/07pqc89,/m/0838f,/m/09x0r", "caption": "Water is trickling, and a man talks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/YgbtcDoh0q3c.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YgbtcDoh0q3c.npy", "labels": "/m/01j3sz,/m/07s04w4,/m/09x0r", "caption": "Scraping and speech followed by people laughing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9HVgYs8OOLc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9HVgYs8OOLc.npy", "labels": "/m/015p6,/m/09x0r,/m/0h0rv,/t/dd00125", "caption": "Birds cackling and young peoples voices" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YOpiWMltpj44.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YOpiWMltpj44.npy", "labels": "/m/015p6,/m/09ddx,/m/0dbvp", "caption": "Birds are squawking, and ducks are quacking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9ZZHvwaH-CU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9ZZHvwaH-CU.npy", "labels": "/m/032s66", "caption": "Repeated gunfire and screaming in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YK_Vre_-4KqU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YK_Vre_-4KqU.npy", "labels": "/m/07yv9,/m/0k5j,/t/dd00129", "caption": "An aircraft engine is taking off" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YqeSl7YZAfs4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YqeSl7YZAfs4.npy", "labels": "/m/0130jx,/m/02jz0l,/m/0838f", "caption": "Water running with a main is speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4IeDBwyQ9ZQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4IeDBwyQ9ZQ.npy", "labels": "/m/04brg2", "caption": "A female speaking with some rustling followed by another female speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YArHiac57pVk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YArHiac57pVk.npy", "labels": "/m/07qjznl,/m/09x0r", "caption": "Males speaking and then a clock ticks twice" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YqZEIs6tS5vk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YqZEIs6tS5vk.npy", "labels": "/m/07r04,/m/07rknqz,/m/07yv9", "caption": "An engine revving and then tires squealing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/Ypaf0nyjg1Js.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ypaf0nyjg1Js.npy", "labels": "/m/0dxrf", "caption": "A woman speaking followed by a porcelain plate clanking as food and oil sizzles" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YBZCEDkx37rI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBZCEDkx37rI.npy", "labels": "/m/02mk9,/m/07pb8fc,/t/dd00066,/t/dd00130", "caption": "An engine hums as it idles" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YFR7BDRhMATo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YFR7BDRhMATo.npy", "labels": "/m/06hck5,/m/06wzb,/m/07rjwbb", "caption": "Blowing of a horn as a train passes" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YXJba7pTbpD0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YXJba7pTbpD0.npy", "labels": "/m/07qlf79", "caption": "Short spray followed by louder longer spray" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YCeRoaEcqUgM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YCeRoaEcqUgM.npy", "labels": "/m/019jd,/m/02rlv9,/m/07yv9", "caption": "A motor is revving and changing gears" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/Yzq00Oe1ecpE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yzq00Oe1ecpE.npy", "labels": "/m/012f08,/m/01bjv,/m/07yv9", "caption": "Humming from an engine slowing down then speeding up" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/YztSjcZNUY7A.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YztSjcZNUY7A.npy", "labels": "/m/09x0r,/t/dd00002", "caption": "A baby cries as a woman speaks with other speech background noise" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/YglAeihz0NAM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YglAeihz0NAM.npy", "labels": "/m/09x0r,/m/0ytgt,/t/dd00129", "caption": "Ocean waves crashing in the distance as young girl talks followed by a young man talking while a group of children laughs in the background and wind blows into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YCM49C3RkzV8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YCM49C3RkzV8.npy", "labels": "/m/02qldy,/m/02zsn,/m/09x0r", "caption": "An adult female speaks, and muted speech occurs briefly in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part15/YH-vTZh81qAU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YH-vTZh81qAU.npy", "labels": "/m/01jwx6", "caption": "A metal clank followed by motor vibrating and rumbling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part38/Yup2PpjTzyyc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yup2PpjTzyyc.npy", "labels": "/m/01yrx,/m/07qrkrw,/m/09x0r,/m/0jbk", "caption": "Music and a man speaking followed by bleeps and someone singing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/YdlsiellSFf0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YdlsiellSFf0.npy", "labels": "/m/019jd,/m/02rlv9,/m/07yv9", "caption": "Motorboat engine screams as it accelerates" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y0jGH7A_hpBM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y0jGH7A_hpBM.npy", "labels": "/m/02qldy,/m/05zppz,/m/09x0r", "caption": "A man speaking followed by another man speaking with some rustling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YCefFMA3klxk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YCefFMA3klxk.npy", "labels": "/m/012f08,/m/07r04,/m/07yv9,/m/0912c9", "caption": "A vehicle horn honking followed by a large truck engine accelerating while wind blows lightly into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YKnXNy5Q6YS4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YKnXNy5Q6YS4.npy", "labels": "/m/01h3n,/m/03vt0,/m/09x0r", "caption": "Many insects are buzzing and rustling is occurring, while an adult male speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/YcPiSd5nJLrI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YcPiSd5nJLrI.npy", "labels": "/m/014zdl,/m/07pxg6y,/m/07qsvvw", "caption": "People speaking with loud bangs followed by a slow motion rumble" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YrJVXE6Axtrg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YrJVXE6Axtrg.npy", "labels": "/m/09x0r,/m/0llzx", "caption": "A couple of men speaking as metal clanks and a power tool operates" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YFA11v4SmdBc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YFA11v4SmdBc.npy", "labels": "/m/01w250,/m/09x0r", "caption": "A man speaks and then whistles" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3iLGu2Omgrw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3iLGu2Omgrw.npy", "labels": "/m/02qldy,/m/05zppz,/m/09x0r", "caption": "An adult male is speaking in a quiet environment" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YQvATUKXYFBs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YQvATUKXYFBs.npy", "labels": "/m/01g50p,/m/0284vy3,/m/06d_3,/m/07jdr,/m/07rwm0c", "caption": "Bells ring followed by humming and vibrations as a train passes while blowing a horn" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part27/Y_ezm-TpKj1w.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y_ezm-TpKj1w.npy", "labels": "/m/07q2z82,/m/09x0r,/m/0k4j", "caption": "A vehicle engine revving as a crowd of people talk" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/Yq46VXJ6JN9M.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yq46VXJ6JN9M.npy", "labels": "/m/07qlf79", "caption": "Some rustling followed by a quick powerful hiss" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YYEYeQ0lIkBQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YYEYeQ0lIkBQ.npy", "labels": "/m/015p6,/m/09ddx,/m/09x0r", "caption": "Several ducks quack and chirp as men speak and wind blows" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part27/Y_xylo5_IiaM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y_xylo5_IiaM.npy", "labels": "/m/09x0r,/m/0ytgt,/t/dd00125", "caption": "A woman talking as a baby talks followed by plastic thumping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part4/Y31WGUPOYS5g.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y31WGUPOYS5g.npy", "labels": "/m/012ndj,/m/03j1ly,/m/03kmc9", "caption": "A large engine passes as people speak followed by a siren" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YKtTLsveexOg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YKtTLsveexOg.npy", "labels": "/m/0llzx", "caption": "A sewing machine operating as a machine motor hisses loudly in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part7/Y5QZ0NtdoKJ8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y5QZ0NtdoKJ8.npy", "labels": "/m/02fs_r,/m/07pp_mv,/m/09x0r", "caption": "Digital beeps repeating then a person speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part27/Y_AcJVyToQUQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y_AcJVyToQUQ.npy", "labels": "/m/01j3sz,/m/09x0r", "caption": "A man and woman laughing followed by a man shouting then a woman laughing as a child laughs" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YkEP-BwMarf8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YkEP-BwMarf8.npy", "labels": "/m/09x0r,/t/dd00112", "caption": "Crumpling paper noise with female speech" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y7D7xgd4WJ50.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y7D7xgd4WJ50.npy", "labels": "/m/0395lw", "caption": "A bell is ringing loudly and quickly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/YyVVLq4ao1Ck.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YyVVLq4ao1Ck.npy", "labels": "/m/015p6,/m/020bb7,/m/07pggtn", "caption": "Several birds chirp with some hissing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YS0YE96w0YRk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YS0YE96w0YRk.npy", "labels": "/m/028ght", "caption": "A man speaking as a crowd of people laugh and applaud" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/Ylh801oHGtD4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ylh801oHGtD4.npy", "labels": "/m/01d380,/m/09x0r", "caption": "A small motor buzzing followed by a man speaking as a metal door closes" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YPb6MqpdX5Jw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YPb6MqpdX5Jw.npy", "labels": "/m/0ngt1", "caption": "Clip-clops gallop as the wind blows and thunder cracks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9U8COLzEegs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9U8COLzEegs.npy", "labels": "/m/02fs_r,/m/09x0r", "caption": "Electronic beeping as a man talks and water pouring in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/Ypaf0nyjg1Js.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ypaf0nyjg1Js.npy", "labels": "/m/0dxrf", "caption": "Food and oil sizzling as a woman is talking followed by dinner plates clanking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/Ydxow2DcTrwk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ydxow2DcTrwk.npy", "labels": "/m/0ngt1", "caption": "Wind blowing followed by people speaking then a loud burst of thunder" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part27/Ya0yXS7PmVR0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ya0yXS7PmVR0.npy", "labels": "/m/07qlf79", "caption": "A heavy rain dies down and begins again" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part1/Y0a9wVat2PWk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y0a9wVat2PWk.npy", "labels": "/m/0284vy3,/m/07jdr,/m/07yv9", "caption": "A train sounds horn while traveling on train track" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/Ybgbnu5YKTDg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ybgbnu5YKTDg.npy", "labels": "/m/032s66", "caption": "A man speaking over an intercom as a helicopter engine runs followed by several gunshots firing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YCO6-i8NLbeo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YCO6-i8NLbeo.npy", "labels": "/m/03fwl,/m/09x0r,/m/0jbk", "caption": "A man talking followed by a goat baaing then a metal gate sliding while ducks quack and wind blows into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/YpI_kPedctoo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YpI_kPedctoo.npy", "labels": "/m/04_sv,/m/07yv9,/m/09x0r", "caption": "Motorcycle engine running" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YEYTz1LPDHsc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YEYTz1LPDHsc.npy", "labels": "/m/02dgv", "caption": "A vehicle door opening as a crow caws and birds chirp while vehicles drive by in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YD9tinq3RMpU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YD9tinq3RMpU.npy", "labels": "/m/019jd,/m/02rlv9,/m/07yv9,/m/09x0r", "caption": "An engine running and wind with various speech in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YEzWEO2WD_MM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YEzWEO2WD_MM.npy", "labels": "/m/01d380", "caption": "A drone whirring followed by a crashing sound" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YtfOIhQpYYe8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YtfOIhQpYYe8.npy", "labels": "/m/09ct_,/m/09x0r,/t/dd00129", "caption": "A man talking as a helicopter flies by" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part27/Y_w2pA1VeB40.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y_w2pA1VeB40.npy", "labels": "/m/01j3sz", "caption": "A group of people laughing followed by farting" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YJnSwRonB9wI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YJnSwRonB9wI.npy", "labels": "/m/019jd,/m/02rlv9,/m/034srq,/m/05kq4", "caption": "Screaming, wind and an engine running, and laughing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YRNBoH2LHQEM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YRNBoH2LHQEM.npy", "labels": "/m/028ght", "caption": "A crowd applauds with a man speaking briefly in the middle" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/YpaetCbEqp2w.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YpaetCbEqp2w.npy", "labels": "/m/0463cq4", "caption": "A series of computer mouse clicks followed by a kid crying" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YLs1zyPjs3k8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YLs1zyPjs3k8.npy", "labels": "/m/02fs_r", "caption": "A series of electronic beeps followed by static" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YK03ydb1uaoQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YK03ydb1uaoQ.npy", "labels": "/m/01d3sd,/t/dd00125", "caption": "Loud snoring repeating" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/Yific_gRalg0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yific_gRalg0.npy", "labels": "/m/07swgks", "caption": "Water pouring down a drain with a series of metal clangs followed by a metal chain rattling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YBlbGXalLNVU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBlbGXalLNVU.npy", "labels": "/m/07pqc89", "caption": "A man talking as water splashes" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y1nUOGZgSzZo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1nUOGZgSzZo.npy", "labels": "/m/07swgks,/m/09x0r,/m/0j6m2", "caption": "Wind blowing and water splashing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/Yc0V_HAul7rI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yc0V_HAul7rI.npy", "labels": "/m/01j3sz,/m/07rgt08,/m/09x0r", "caption": "A group of people laughing followed by a man talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YPtW0cZVprJQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YPtW0cZVprJQ.npy", "labels": "/m/01d3sd,/m/09x0r", "caption": "A person snoring followed by a man talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YAbplcXwXnvE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YAbplcXwXnvE.npy", "labels": "/m/09x0r,/t/dd00112", "caption": "Girl speaks and crunches plastic wrapping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/Yd1tL-9BILy8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yd1tL-9BILy8.npy", "labels": "/m/015p6,/m/020bb7,/m/07r_25d,/m/0h0rv", "caption": "Pigeons cooing as air lightly hisses in the background followed by a camera muffling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/YonBZOH88OYs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YonBZOH88OYs.npy", "labels": "/m/07qlf79", "caption": "A series of compressed air spraying as a motor hums in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3wV3ST-c4PE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3wV3ST-c4PE.npy", "labels": "/m/07qjznl", "caption": "Low ticktock sounds followed by objects moving" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/Yy93cZqNCtks.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yy93cZqNCtks.npy", "labels": "/m/032s66,/m/04zjc", "caption": "Gunshots fire, an adult male speaks, footfalls and clicking occur as other adult males speak, gunshots fire again, an adult male speaks, and a dog growls" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YL2dyilgQ8iM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YL2dyilgQ8iM.npy", "labels": "/m/09t49,/t/dd00092", "caption": "Footsteps shuffling on snow alongside a camera muffling while wind blows into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YWWkhzcmx3VE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YWWkhzcmx3VE.npy", "labels": "/m/09ddx", "caption": "Duck quacking repeatedly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part38/Yu9px4Lwv9XI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yu9px4Lwv9XI.npy", "labels": "/m/07st88b,/m/09ld4", "caption": "Tribal drums playing as footsteps shuffle on wet dirt as frogs and crickets chirp in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/Yhrv6fwnmBkY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yhrv6fwnmBkY.npy", "labels": "/m/068hy,/m/07rc7d9,/m/09b5t,/m/09x0r,/m/0bt9lr,/m/0jbk,/t/dd00136", "caption": "A rooster clucking followed by a dog whimpering then a man talking and a dog barking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/YzEaGx6an4es.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YzEaGx6an4es.npy", "labels": "/m/01d380,/m/07k1x", "caption": "A power tool drill operating continuously" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YE6FH_xp3I54.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YE6FH_xp3I54.npy", "labels": "/m/07pggtn,/m/09x0r,/m/0jbk,/t/dd00129", "caption": "A man speaking as birds are chirping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YDt53UZgyznE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YDt53UZgyznE.npy", "labels": "/m/09x0r,/t/dd00002", "caption": "Pretend to scream and crying is occurring, and an adult male begins to speak" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YOMGHnJV0l2U.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YOMGHnJV0l2U.npy", "labels": "/m/02p01q,/m/07pdjhy,/m/083vt", "caption": "Metal scrapping against a wooden surface followed by sand scrapping then more metal scrapping against wood" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part0/Y-NsC63dA01g.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y-NsC63dA01g.npy", "labels": "/m/01yrx,/m/068hy,/m/07qrkrw,/m/09x0r,/m/0jbk", "caption": "A cat meows and a woman speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/YfGGYeXR_LS8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YfGGYeXR_LS8.npy", "labels": "/m/01w250,/m/09x0r", "caption": "Whistling as a man speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part27/Y_ezm-TpKj1w.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y_ezm-TpKj1w.npy", "labels": "/m/07q2z82,/m/09x0r,/m/0k4j", "caption": "A mid-size motor vehicle engine is revving repeatedly, while people talk in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/YhJtOGmN_KVw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YhJtOGmN_KVw.npy", "labels": "/m/09x0r,/t/dd00112,/t/dd00125", "caption": "A man is speaking as paper is crumpling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part24/YUmNrhFKpWIY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YUmNrhFKpWIY.npy", "labels": "/m/07q2z82,/m/07yv9,/m/0k4j", "caption": "A vehicle engine revving then powering down" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/YxBZnvfniA1c.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YxBZnvfniA1c.npy", "labels": "/m/09x0r,/m/0ytgt,/t/dd00125", "caption": "A man is speaking followed by a child speaking and then laughter" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YEQVWhHmT_cE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YEQVWhHmT_cE.npy", "labels": "/m/02qldy,/m/05zppz,/m/09x0r", "caption": "Some claps followed by a man speaking then glass breaking and people laughing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YUCy1BEx8jBE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YUCy1BEx8jBE.npy", "labels": "/m/0j6m2", "caption": "A man speaking as a stream of water splashes and flows while music faintly plays in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YF7QtqKtllK0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YF7QtqKtllK0.npy", "labels": "/m/01d3sd", "caption": "Continuous snoring of a person" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YalaxBd_EEUc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YalaxBd_EEUc.npy", "labels": "/m/03q5_w,/m/09x0r", "caption": "A man talking followed by a series of belches" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part15/YGSHcgY6ATkQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YGSHcgY6ATkQ.npy", "labels": "/m/0316dw", "caption": "A man speaks while typing occurs" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/YxYwpABpZed4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YxYwpABpZed4.npy", "labels": "/m/07ptfmf,/m/0dxrf", "caption": "A woman speaks as she fries food" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YlfO471Rn61k.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YlfO471Rn61k.npy", "labels": "/m/06wzb,/m/07rjwbb", "caption": "Spray and a high pitch tone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YHZ9O6sc7cLA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YHZ9O6sc7cLA.npy", "labels": "/m/05tny_,/m/07rc7d9,/m/0bt9lr", "caption": "A woman speaks and continues to do so as a dog starts barking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y41D0yXSBqfI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y41D0yXSBqfI.npy", "labels": "/m/015p6,/m/0h0rv,/t/dd00125", "caption": "A bird is cooing and flapping its wings" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YJ0yeFeKvIt8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YJ0yeFeKvIt8.npy", "labels": "/m/09t49", "caption": "Continuous white noise, rustling and wind" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YKvrcRMfFzOE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YKvrcRMfFzOE.npy", "labels": "/m/07yv9,/m/09ct_,/m/0k5j", "caption": "An engine running and helicopter propellers spinning" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part9/Y7cHRSfbp7tc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y7cHRSfbp7tc.npy", "labels": "/m/02dgv,/m/07r4wb8,/m/09x0r", "caption": "People are talking along with knock sounds" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YNeWW30WZjPc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YNeWW30WZjPc.npy", "labels": "/m/01z5f,/m/05tny_,/m/068hy,/m/07rc7d9,/m/0bt9lr,/m/0jbk,/t/dd00125", "caption": "A dog barking and growling while plastic rattles and clanks against a hard surface" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YtjCNwdOUiGc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YtjCNwdOUiGc.npy", "labels": "/m/07qv_d5,/m/07yv9,/m/0912c9", "caption": "Humming of an engine followed by some honks of a horn" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YOpiWMltpj44.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YOpiWMltpj44.npy", "labels": "/m/015p6,/m/09ddx,/m/0dbvp", "caption": "Ducks quacking as roosters crow and chickens cluck while water trickles" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/YdYvL6uEMl6E.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YdYvL6uEMl6E.npy", "labels": "/m/019jd,/m/02rlv9,/m/034srq,/m/03m9d0z,/m/05kq4,/t/dd00092", "caption": "A helicopter flying followed by wind heavily blowing into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/YgbtcDoh0q3c.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YgbtcDoh0q3c.npy", "labels": "/m/01j3sz,/m/07s04w4,/m/09x0r", "caption": "A scratching of surface sound followed by men talking and snickering" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/YjjHIINDfE1c.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YjjHIINDfE1c.npy", "labels": "/m/07yv9,/m/0912c9,/t/dd00129", "caption": "Humming from an engine followed by loud honks of a horn" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YsqsI2UyrcBQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YsqsI2UyrcBQ.npy", "labels": "/m/07q2z82,/m/07yv9,/m/0k4j", "caption": "A car engine revs producing a room and a whine" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/YjOYvIISk--4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YjOYvIISk--4.npy", "labels": "/m/0130jx,/m/02jz0l,/m/0838f", "caption": "A man speaks as water flows from a faucet in quick bursts" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3MoF8myFs8Y.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3MoF8myFs8Y.npy", "labels": "/m/034srq,/m/03m9d0z,/m/05kq4,/t/dd00092", "caption": "Ocean waves crashing as a man talks in the distance and wind heavily blows into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YPMMkPq5jJXY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YPMMkPq5jJXY.npy", "labels": "/m/03q5_w,/m/09x0r", "caption": "Burping and then laughing with continuous burping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YtfOIhQpYYe8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YtfOIhQpYYe8.npy", "labels": "/m/09ct_,/m/09x0r,/t/dd00129", "caption": "An aircraft motor is running and whirring is present, helicopter rotors slap rhythmically, and an adult male speaks in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YAtkD-3GjXMw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YAtkD-3GjXMw.npy", "labels": "/m/032s66,/m/04zjc", "caption": "Music is playing with machine gun sounds" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part7/Y6Nvu6EcpdE8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y6Nvu6EcpdE8.npy", "labels": "/m/07pb8fc,/m/07yv9,/m/09x0r,/t/dd00130", "caption": "The wind is blowing, an adult male speaks via an electronic device, and a click occurs" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/YzoxFl3pddMg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YzoxFl3pddMg.npy", "labels": "/m/09ld4", "caption": "Nature sounds with a frog croaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part24/YVQnmlf2OsUg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YVQnmlf2OsUg.npy", "labels": "/m/09ct_", "caption": "Helicopter blades spinning" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/YjjHIINDfE1c.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YjjHIINDfE1c.npy", "labels": "/m/07yv9,/m/0912c9,/t/dd00129", "caption": "A tractor engine driving by followed by a car horn honking and wind blowing on a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YB4SZwi9Ce3o.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YB4SZwi9Ce3o.npy", "labels": "/m/07q2z82,/m/07yv9,/m/09x0r,/m/0k4j", "caption": "A man talks over a clicking sound and a car engine switches gears and speeds up" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9ucb5HYO8ps.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9ucb5HYO8ps.npy", "labels": "/m/03q5_w,/m/09x0r", "caption": "A girl burping then laughing followed by a group of girls laughing and talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YWWkhzcmx3VE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YWWkhzcmx3VE.npy", "labels": "/m/09ddx", "caption": "A duck quacking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part19/YNJEPbGVBJIQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YNJEPbGVBJIQ.npy", "labels": "/m/012f08,/m/04_sv,/m/07yv9,/m/09x0r,/m/0btp2,/t/dd00128", "caption": "Traffic hums and beeps with revving engines and a man speaking nearby" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YZYWCwfCkBp4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YZYWCwfCkBp4.npy", "labels": "/m/01b82r,/m/07pdjhy,/m/083vt", "caption": "A person is sawing wood and music is playing in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9XqkKuTqEOM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9XqkKuTqEOM.npy", "labels": "/m/02dgv", "caption": "Some scratching and rustling with small clicks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3IguMJkqpl4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3IguMJkqpl4.npy", "labels": "/m/07qdb04,/m/09ddx,/m/09x0r", "caption": "A man speaking then a baby crying, duck quacking in background and finally a woman speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part24/YUhCzD6EBJBU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YUhCzD6EBJBU.npy", "labels": "/m/01d380,/m/07k1x,/m/0_ksk", "caption": "A power tool vibrating quick followed by a man speaking and some bangs" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YTQr9v-PQOc4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YTQr9v-PQOc4.npy", "labels": "/m/01hsr_", "caption": "Some clicking followed by a sneeze and a man laughing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/YxBZnvfniA1c.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YxBZnvfniA1c.npy", "labels": "/m/09x0r,/m/0ytgt,/t/dd00125", "caption": "A man speaks with others speaking in the distance followed by a girl speaking and others laughing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part1/Y0NGSrwioYjA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y0NGSrwioYjA.npy", "labels": "/m/03fwl,/m/068hy,/m/09ld4,/m/09x0r,/m/0jbk", "caption": "There is a mature male talking to some animals" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part7/Y6Pywt0f_NFY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y6Pywt0f_NFY.npy", "labels": "/m/02jz0l,/m/03dnzn,/m/0838f", "caption": "Water running continuously" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/Yh5_1pnkl_SY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yh5_1pnkl_SY.npy", "labels": "/m/02jz0l,/m/0838f", "caption": "Water trickles, splashes and gurgles, slow at first and then faster, and an adult male is speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/Yfx4r_KuW6No.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yfx4r_KuW6No.npy", "labels": "/m/09x0r,/m/0ytgt,/t/dd00126", "caption": "A woman talking back and forth with a child who is crying" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9F3sutgYTvo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9F3sutgYTvo.npy", "labels": "/m/09x0r,/t/dd00002", "caption": "A man yelling followed by an infant crying then a woman shouting as a crowd of people talk and laugh" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/YjOYvIISk--4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YjOYvIISk--4.npy", "labels": "/m/0130jx,/m/02jz0l,/m/0838f", "caption": "A man speaking as a faucet pours water several times while water drains down a pipe" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y7P6lcyeDKNI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y7P6lcyeDKNI.npy", "labels": "/m/0199g,/m/04_sv,/m/07yv9,/m/09x0r", "caption": "Dirt shuffling followed by gears cranking and a branch snapping then a man talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YQHfyKaOHSz4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YQHfyKaOHSz4.npy", "labels": "/m/07st88b,/m/09ld4", "caption": "Fly buzzing followed by frog swallowing it and then a croak" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YSE_3nszEw7o.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YSE_3nszEw7o.npy", "labels": "/m/06wzb,/m/07rjwbb", "caption": "Hissing together with an engine chugging" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part27/Y_iUX8CibElk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y_iUX8CibElk.npy", "labels": "/m/0ngt1", "caption": "Sustained industrial engine noise" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YPLHXGDnig4M.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YPLHXGDnig4M.npy", "labels": "/m/01yrx,/m/07qrkrw", "caption": "A person speaks and makes meow sounds" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/YyVVLq4ao1Ck.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YyVVLq4ao1Ck.npy", "labels": "/m/015p6,/m/020bb7,/m/07pggtn", "caption": "Several birds tweeting loudly followed by insects chirping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y2JutOgAnqWA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y2JutOgAnqWA.npy", "labels": "/m/01d380,/m/07k1x,/m/0_ksk", "caption": "Humming and vibrating of a power tool with some high frequency squealing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YbX2vDaHL26U.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YbX2vDaHL26U.npy", "labels": "/m/07rknqz,/m/07yv9,/m/0k4j,/m/0ltv", "caption": "Loud wind noise followed by a car accelerating fast" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YXf5LjaE_JQ0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YXf5LjaE_JQ0.npy", "labels": "/m/07qlf79,/m/09x0r", "caption": "A man speaks with distant traffic passing and some nearby rattling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part1/Y0NGSrwioYjA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y0NGSrwioYjA.npy", "labels": "/m/03fwl,/m/068hy,/m/09ld4,/m/09x0r,/m/0jbk", "caption": "A man talking followed by a goat baaing as wind lightly blows into a microphone followed by a crow cawing in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YCh0LMmhBUg4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YCh0LMmhBUg4.npy", "labels": "/m/03m9d0z,/m/06q74,/m/07yv9,/m/09x0r,/t/dd00129", "caption": "A man talking as a kid yells followed by an aircraft flying in the distance as wind blows into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/Yl5KdHAWwJCw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yl5KdHAWwJCw.npy", "labels": "/m/07qjznl", "caption": "A clock ticks with breathing in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part24/YVE6Ku0-ucUM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YVE6Ku0-ucUM.npy", "labels": "/m/07qsvvw,/m/09x0r", "caption": "A man speaks followed by popping noise and laughter" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YYIqpIjjee00.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YYIqpIjjee00.npy", "labels": "/m/01jt3m", "caption": "Water running from a flushed toilet" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YItS07xtdi4s.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YItS07xtdi4s.npy", "labels": "/m/07qsvvw,/m/09x0r", "caption": "Fire igniting followed by an electronic beep then footsteps running on concrete as vehicle engines run idle and horns honk in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YHeEa1GZpUGI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YHeEa1GZpUGI.npy", "labels": "/m/032s66", "caption": "Several gunshots with a click and glass breaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/YjjfUaMQaG1A.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YjjfUaMQaG1A.npy", "labels": "/m/01d380,/m/09x0r", "caption": "A man speaks followed by vibrations of a power tool" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y79XDcI6xZm0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y79XDcI6xZm0.npy", "labels": "/m/02qldy,/m/05zppz,/m/09x0r", "caption": "A man is giving a speech while the crowd is chanting and clapping in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y52IxrdTxGs4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y52IxrdTxGs4.npy", "labels": "/m/07qsvvw,/m/09x0r", "caption": "A large explosion and a heartbeat, a person speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YlJayhiVzl_E.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YlJayhiVzl_E.npy", "labels": "/m/019jd,/m/02rlv9,/m/03m9d0z,/t/dd00092", "caption": "A motorboat engine running as wind blows into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/YgQMTOKsCIyk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YgQMTOKsCIyk.npy", "labels": "/m/015p6,/m/07qwf61,/m/09ddx,/m/09x0r", "caption": "Ducks quacking and chirping followed by a man talking while water trickles" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YLs2vrr9TamU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YLs2vrr9TamU.npy", "labels": "/m/083vt", "caption": "Humming from a motor with loud dry cracking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part4/Y31WGUPOYS5g.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y31WGUPOYS5g.npy", "labels": "/m/012ndj,/m/03j1ly,/m/03kmc9", "caption": "Child speaks and an emergency siren sounds" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4SZ7JXDCNps.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4SZ7JXDCNps.npy", "labels": "/m/07yv9,/m/0k4j,/m/0ltv", "caption": "An engine booms and hums with constant rattling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/YzIgGMlZENTs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YzIgGMlZENTs.npy", "labels": "/m/07qdb04,/m/09ddx,/m/09x0r", "caption": "A duck quacks followed by a man talking while birds chirp in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y1GgEpRZDWN0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1GgEpRZDWN0.npy", "labels": "/m/01h8n0,/m/02zsn,/m/09x0r", "caption": "A woman and a man talking as another man talks softly and papers shuffle in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YqF72bT878gw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YqF72bT878gw.npy", "labels": "/m/019jd,/m/02rlv9,/m/07yv9", "caption": "A speedboat running as wind blows into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YrgrmLLhxoCQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YrgrmLLhxoCQ.npy", "labels": "/t/dd00112", "caption": "Rubbing and scraping a rough surface" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part24/YVeCSHwtkBZU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YVeCSHwtkBZU.npy", "labels": "/m/012n7d,/m/03j1ly,/m/03kmc9", "caption": "An emergency vehicle has the siren on" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YZ1Cyj4N05lk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YZ1Cyj4N05lk.npy", "labels": "/m/01w250", "caption": "A person whistling then a man speaking with plastic tapping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YXplKBvZaHXA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YXplKBvZaHXA.npy", "labels": "/m/04_sv,/m/07yv9,/m/09x0r,/t/dd00129", "caption": "A man talking as a motorbike engine runs and accelerates" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/Yhzn_wGlzGpU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yhzn_wGlzGpU.npy", "labels": "/m/07yv9,/m/0k4j,/m/0ltv", "caption": "A vehicle engine running smoothly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y0yxEvdnimGg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y0yxEvdnimGg.npy", "labels": "/m/068hy,/m/07rc7d9,/m/09x0r,/m/0bt9lr,/m/0jbk", "caption": "A dog barking as a man is talking while birds chirp and wind blows into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YLKhokVsJhN0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YLKhokVsJhN0.npy", "labels": "/m/07bgp,/m/0ch8v,/m/0jbk", "caption": "A herd of sheep baaing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YRp4Ct_TQvAM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YRp4Ct_TQvAM.npy", "labels": "/m/06mb1,/m/09x0r", "caption": "Rain falling as a motor engine runs idle and a man talks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YYqYCDis3EUA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YYqYCDis3EUA.npy", "labels": "/m/01h3n,/m/03vt0,/m/0h2mp", "caption": "Birds chirping and bees buzzing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YXL8JV9qXGLE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YXL8JV9qXGLE.npy", "labels": "/m/0463cq4,/m/09x0r,/m/0ytgt,/t/dd00002,/t/dd00125", "caption": "Distant murmuring followed by a child cooing and laughter" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9BGLAUSF0sk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9BGLAUSF0sk.npy", "labels": "/m/01jwx6,/m/0chx_", "caption": "An engine running" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part27/Y_duNX6Vyd6g.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y_duNX6Vyd6g.npy", "labels": "/m/019jd,/m/02rlv9,/m/07yv9", "caption": "A speedboat is racing across water with loud wind noise" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YFA11v4SmdBc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YFA11v4SmdBc.npy", "labels": "/m/01w250,/m/09x0r", "caption": "Male speech and then whistling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y7QN3lwOzfdg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y7QN3lwOzfdg.npy", "labels": "/m/07cx4,/m/09x0r", "caption": "A man speaking through a telephone speaker as another man is talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YOUUckswAaNI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YOUUckswAaNI.npy", "labels": "/m/02dgv", "caption": "A short hammering sound followed by two men speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YAgaiowyYt88.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YAgaiowyYt88.npy", "labels": "/m/02dgv", "caption": "A loud and forceful bang" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YTdl9SmBbRnA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YTdl9SmBbRnA.npy", "labels": "/m/012f08,/m/01bjv,/m/07yv9,/m/09x0r", "caption": "Speaking and an engine running" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part7/Y6OlHuvJR_Dk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y6OlHuvJR_Dk.npy", "labels": "/m/07yv9,/m/09ct_", "caption": "A helicopter engine working" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YbygBWUkpaC8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YbygBWUkpaC8.npy", "labels": "/m/020bb7,/m/07pggtn,/m/09x0r,/m/0jbk,/t/dd00129", "caption": "A male speech and wind and then birds chirping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YFfUqv0Vv3ME.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YFfUqv0Vv3ME.npy", "labels": "/m/03k3r,/m/09x0r,/m/0jbk", "caption": "A man speaking followed by a woman talking then plastic clacking as footsteps walk on grass and a rooster crows in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YWWkhzcmx3VE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YWWkhzcmx3VE.npy", "labels": "/m/09ddx", "caption": "A duck quacking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YqZEIs6tS5vk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YqZEIs6tS5vk.npy", "labels": "/m/07r04,/m/07rknqz,/m/07yv9", "caption": "A crowd of people talking followed by a vehicle engine revving then tires skidding" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/Ypgq2KPX5_SA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ypgq2KPX5_SA.npy", "labels": "/t/dd00112", "caption": "A paper is being crumpled" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part15/YH7rd9bZtbgc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YH7rd9bZtbgc.npy", "labels": "/m/0395lw", "caption": "Church bells ringing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YO90Qy2xG6oA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YO90Qy2xG6oA.npy", "labels": "/m/068hy,/m/0jbk,/t/dd00002", "caption": "A domestic pet is making noises and a baby cries" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part15/YGuizRlAQ8qQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YGuizRlAQ8qQ.npy", "labels": "/m/01d380", "caption": "Humming and vibrating from a power tool" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/YoOMtaqvQ3_M.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YoOMtaqvQ3_M.npy", "labels": "/m/07yv9,/m/09ct_,/m/0k5j", "caption": "A helicopter flying as wind blows into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part4/Y2ymiXjImwGs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y2ymiXjImwGs.npy", "labels": "/m/012ndj,/m/01bjv,/m/09x0r", "caption": "A crowd murmurs as a siren blares and then stops at a distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part9/Y7fmOlUlwoNg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y7fmOlUlwoNg.npy", "labels": "/m/09x0r,/m/0llzx,/t/dd00127", "caption": "Vibrations and rattling with people speaking in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YWmDe2xbnSY4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YWmDe2xbnSY4.npy", "labels": "/m/07qsvvw", "caption": "Several bursts and explosions with grunting and growling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part0/Y-DmjkgWa-rw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y-DmjkgWa-rw.npy", "labels": "/m/0395lw", "caption": "A bell is ringing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YKtinboYbmHQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YKtinboYbmHQ.npy", "labels": "/m/07rknqz,/m/07yv9,/m/0h9mv,/m/0k4j", "caption": "A vehicle driving by while revving as tires skid and squeal" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YrUq4w4EUSWA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YrUq4w4EUSWA.npy", "labels": "/m/01jt3m,/m/0838f", "caption": "Loud buzzing followed by rustling and a toilet flushing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YHUwXtfYRFwk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YHUwXtfYRFwk.npy", "labels": "/m/012f08,/m/01bjv,/m/07yv9,/m/0k4j", "caption": "A bus engine running as several vehicles pass by and car horns honk in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y0rSETXszQM0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y0rSETXszQM0.npy", "labels": "/m/028v0c,/m/04_sv,/m/07yv9,/t/dd00128", "caption": "Motorcycle starting then driving away" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/YfwhkCnOeyC0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YfwhkCnOeyC0.npy", "labels": "/m/028ght,/m/09x0r", "caption": "Applause and speech followed by a loud high pitched bell and more applause and speech" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YEbpOXac13yo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YEbpOXac13yo.npy", "labels": "/m/01bjv,/m/07yv9,/m/09x0r", "caption": "Vehicles driving by as a muffled engine runs while a man speaks then another man speaking in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part27/Y_YS5uKWoB6g.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y_YS5uKWoB6g.npy", "labels": "/m/09x0r,/t/dd00002", "caption": "A kid crying as a man and a woman talk followed by a car door opening then closing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/YyhDw7PZje3g.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YyhDw7PZje3g.npy", "labels": "/m/01h3n,/m/09x0r,/t/dd00129", "caption": "Two men speaking with loud insects buzzing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/Ydxow2DcTrwk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ydxow2DcTrwk.npy", "labels": "/m/0ngt1", "caption": "Rain falls and a man speaks with distant thunder" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/Yjlwe9jtu5Gw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yjlwe9jtu5Gw.npy", "labels": "/m/01w250", "caption": "A person whistling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4KObP7cREWw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4KObP7cREWw.npy", "labels": "/m/02mk9,/m/07yv9,/m/0k4j", "caption": "A car engine clicks and whines as it tries to start" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part4/Y35b9BSmN5JM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y35b9BSmN5JM.npy", "labels": "/m/07q2z82,/m/07yv9,/m/0k4j", "caption": "Loud vibrating followed by revving" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YSGaIvgwwWSE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YSGaIvgwwWSE.npy", "labels": "/m/06mb1,/m/0jb2l,/m/0ngt1", "caption": "Rain falling and thunder roaring in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part4/Y2j8pxiFvElM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y2j8pxiFvElM.npy", "labels": "/m/01yrx,/m/068hy,/m/07qrkrw,/m/0jbk", "caption": "A cat meowing twice" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y11SEBDuoqSk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y11SEBDuoqSk.npy", "labels": "/m/07yv9,/m/0cmf2,/m/0k5j", "caption": "An aircraft engine flying before becoming louder while several rapid gunshots fire" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/Yjid4t-FzUn0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yjid4t-FzUn0.npy", "labels": "/m/03fwl,/m/07s04w4,/m/09x0r", "caption": "A man speaking and laughing followed by a goat bleat" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4Ujigme2IxY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4Ujigme2IxY.npy", "labels": "/m/01jwx6", "caption": "A motor vehicle is running and vibrating, and a high-pitched squeal occurs" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/Ybpv_LneHmfU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ybpv_LneHmfU.npy", "labels": "/m/014yck,/m/07yv9,/m/0cmf2,/m/0k5j,/t/dd00129", "caption": "Humming of a nearby jet engine" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part1/Y0Rpjl1AO-P0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y0Rpjl1AO-P0.npy", "labels": "/m/07yv9,/m/0k4j,/t/dd00134", "caption": "A car engine is revving while driving" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YFKaJsvcyHTk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YFKaJsvcyHTk.npy", "labels": "/t/dd00002", "caption": "An infant crying" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YJon_DEFqsfM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YJon_DEFqsfM.npy", "labels": "/m/020bb7,/m/06_y0by,/m/09ddx", "caption": "Ducks quacking as birds chirp followed by a flock of ducks quacking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/YxUWSHYoslPQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YxUWSHYoslPQ.npy", "labels": "/m/04brg2,/m/09x0r", "caption": "A man speaks with a high frequency hum with some banging and clanking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/Yg5l3Bz6lWnc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yg5l3Bz6lWnc.npy", "labels": "/m/01h3n,/m/03vt0", "caption": "Wood lightly shuffling as insects buzz while birds chirp in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YqWYncqPSy9A.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YqWYncqPSy9A.npy", "labels": "/m/03vt0,/m/09f96,/m/0h2mp", "caption": "A man speaking as an insect buzzes followed by a woman laughing then another man talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YXIooZl1QdM4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YXIooZl1QdM4.npy", "labels": "/m/03q5_w", "caption": "Several loud burps" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/YxYwpABpZed4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YxYwpABpZed4.npy", "labels": "/m/07ptfmf,/m/0dxrf", "caption": "Metal clacking in a pan as a woman talks while food and oil sizzle" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part38/Yu8bQf0SnCVI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yu8bQf0SnCVI.npy", "labels": "/m/0130jx,/m/02jz0l,/t/dd00125", "caption": "Tapping followed by water spraying and more tapping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YQARuiRtfy-k.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YQARuiRtfy-k.npy", "labels": "/m/01d380", "caption": "A power tool drilling as music plays followed by someone blows air then plastic clanking and a man speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YbUTOsLXYyxg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YbUTOsLXYyxg.npy", "labels": "/m/01j3sz,/m/09x0r", "caption": "A man talking followed by another man speaking then a group of people laughing and a man speaking a bit in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y6eX6bJOFftA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y6eX6bJOFftA.npy", "labels": "/m/02rlv9,/m/07yv9,/m/09x0r", "caption": "A crowd of people talking as ducks quack and a motorboat speeds by in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y2ErfX6ZT5pM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y2ErfX6ZT5pM.npy", "labels": "/m/01jt3m", "caption": "Some child speaking in the distant and a toilet flushing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YFDwK7T1JO_0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YFDwK7T1JO_0.npy", "labels": "/m/01d380,/m/07k1x,/m/09x0r,/t/dd00125", "caption": "Two men speaking followed by plastic clacking then a power tool drilling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y40cuHrYfaqA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y40cuHrYfaqA.npy", "labels": "/m/068hy,/m/07rc7d9,/m/09x0r,/m/0bt9lr,/m/0jbk,/t/dd00136", "caption": "Dogs barking and growling followed by a man talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YXrJcmftCY04.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YXrJcmftCY04.npy", "labels": "/m/028ght", "caption": "A crowd of people applauding and cheering" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/Ya_Rjlu50TfA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ya_Rjlu50TfA.npy", "labels": "/m/01d3sd,/m/07q0yl5,/m/09x0r", "caption": "A person snoring during a series of thumps followed by a man talking in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y1DKLyH3FixM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1DKLyH3FixM.npy", "labels": "/m/015p6,/m/020bb7,/m/07pggtn", "caption": "Chirping birds near and far" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part7/Y6NBPiArs2-w.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y6NBPiArs2-w.npy", "labels": "/m/032s66", "caption": "A series of rapid gunshots firing alongside footsteps running on concrete as a man groans while a muffled heart beats in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part38/YuJzAf4PaExI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YuJzAf4PaExI.npy", "labels": "/m/07yv9,/m/09x0r,/m/0k5j", "caption": "A muffled aircraft engine operating as a group of people talk in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y41D0yXSBqfI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y41D0yXSBqfI.npy", "labels": "/m/015p6,/m/0h0rv,/t/dd00125", "caption": "A group of pigeons cooing as bird wings flap in the background followed by plastic tapping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YJQz40TkjymY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YJQz40TkjymY.npy", "labels": "/m/01m2v,/m/0316dw", "caption": "Typing on a computer keyboard" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/YyVVLq4ao1Ck.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YyVVLq4ao1Ck.npy", "labels": "/m/015p6,/m/020bb7,/m/07pggtn", "caption": "Insects trill in the background, while birds chirp and flies buzz" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/Ykdflh3akyH8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ykdflh3akyH8.npy", "labels": "/m/0ghcn6,/m/0jbk,/t/dd00136", "caption": "Small dogs yip and whimper" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YlmPMhs-9IYE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YlmPMhs-9IYE.npy", "labels": "/m/07yv9,/m/09x0r,/m/0k4j,/m/0ltv", "caption": "A vehicle engine revving several times as a man speaks over an intercom along with a crowd of people talking and whistling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/YhGWarNR6xmg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YhGWarNR6xmg.npy", "labels": "/m/06wzb,/m/07rjwbb", "caption": "Hisses continuously with some static" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part27/YZsf2YvJfCKw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YZsf2YvJfCKw.npy", "labels": "/m/01jt3m", "caption": "A toilet is flushed with a loud hum and gurgling water" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/Ynq0BF9zGkzg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ynq0BF9zGkzg.npy", "labels": "/m/09x0r,/t/dd00018", "caption": "A low slow groan followed by a crash and men speaking with distant birds" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part38/Yvigslb0kClE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yvigslb0kClE.npy", "labels": "/m/03fwl,/m/09x0r,/m/0jbk", "caption": "People talking while herding goats near a fast running stream" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part4/Y2t82STv2GR8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y2t82STv2GR8.npy", "labels": "/m/0395lw", "caption": "A large bell rings out multiple times" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/YzoctgurhvHE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YzoctgurhvHE.npy", "labels": "/m/012f08,/m/02dgv,/m/04gxbd,/m/07yv9", "caption": "A man speaking as plastic is clanking followed by a door hatch opening and plastic tumbling with a vehicle engine revving in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YRdC8cviN6Bs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YRdC8cviN6Bs.npy", "labels": "/m/06mb1,/t/dd00038", "caption": "Rain is splashing on a surface while rustling occurs and a car door shuts, and traffic is discernible in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YB8rdur4aams.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YB8rdur4aams.npy", "labels": "/m/07yv9,/m/0912c9,/t/dd00128", "caption": "A vehicle engine gurgling followed by a horn tooting as wind blows into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/YgQMTOKsCIyk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YgQMTOKsCIyk.npy", "labels": "/m/015p6,/m/07qwf61,/m/09ddx,/m/09x0r", "caption": "Chirps from several ducks as a man speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3wrdPAeqjVI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3wrdPAeqjVI.npy", "labels": "/m/083vt,/m/09x0r", "caption": "A man speaks with some high pitched ringing and some rustling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y6cS0FsUM-cQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y6cS0FsUM-cQ.npy", "labels": "/m/01yrx,/m/068hy,/m/07qrkrw,/m/07r81j2,/m/09x0r,/m/0jbk", "caption": "A cat meowing followed by people speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YFfUqv0Vv3ME.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YFfUqv0Vv3ME.npy", "labels": "/m/03k3r,/m/09x0r,/m/0jbk", "caption": "A male speaking and rustling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YOmmPaIAXN0s.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YOmmPaIAXN0s.npy", "labels": "/m/03k3r,/m/07rv9rh,/m/09x0r,/m/0jbk", "caption": "A man speaking followed by a horse trotting" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YbmEF-c-M174.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YbmEF-c-M174.npy", "labels": "/m/015p6,/m/09ddx,/m/09x0r", "caption": "A duck quacks repeatedly and soft thumping occurs, a bird chirps twice, and an adult male speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part15/YGOD8Bt5LfDE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YGOD8Bt5LfDE.npy", "labels": "/m/07jdr,/m/09x0r,/m/0ytgt", "caption": "A quiet machine running and a child speaking and then an adult speaks and the child laughs" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y59VP93Tzjmg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y59VP93Tzjmg.npy", "labels": "/m/01g50p,/m/0284vy3,/m/06d_3,/m/07jdr", "caption": "Train blowing horn then approaching track sounds" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3VHpLxtd498.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3VHpLxtd498.npy", "labels": "/m/015p6,/m/09x0r,/m/0h0rv", "caption": "Graveling shuffling followed by a young kid talking as pigeons are cooing and a motor hums in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YOTLtzk0W4zg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YOTLtzk0W4zg.npy", "labels": "/m/07yv9,/m/09x0r,/m/0k4j,/t/dd00128,/t/dd00130", "caption": "A vehicle running and a man talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YRtenf2XSXRc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YRtenf2XSXRc.npy", "labels": "/m/07q2z82,/m/07yv9,/m/0k4j", "caption": "A mid-size motor vehicle engine idles smoothly and is then revved several times, followed by a car door shutting" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YD9GHUPGWsV0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YD9GHUPGWsV0.npy", "labels": "/m/07bgp,/m/07q0h5t,/m/09x0r", "caption": "A woman and man speak as click-clops occur and a sheep fleets" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YJnSwRonB9wI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YJnSwRonB9wI.npy", "labels": "/m/019jd,/m/02rlv9,/m/034srq,/m/05kq4", "caption": "People scream with a distant hum and splashing waves" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YT32kii824pA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YT32kii824pA.npy", "labels": "/m/083vt", "caption": "Plastic cranking followed by metal rattling then a series of metal falling in the background as a man is talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YJBWJQCS4SvA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YJBWJQCS4SvA.npy", "labels": "/m/034srq,/m/03m9d0z,/m/05kq4,/t/dd00092", "caption": "Bird chirping while waves come in with high wind" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/Yjf4iyQPJSvk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yjf4iyQPJSvk.npy", "labels": "/m/07pqc89,/m/0838f,/m/0j2kx,/t/dd00129", "caption": "Water is falling, splashing and gurgling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/Yjs4dr5JusdM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yjs4dr5JusdM.npy", "labels": "/m/07cx4,/m/09x0r", "caption": "A woman speaks quietly, and man answers much louder, then she speaks again" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YalaxBd_EEUc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YalaxBd_EEUc.npy", "labels": "/m/03q5_w,/m/09x0r", "caption": "A man speaks followed by eructation" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part7/Y5eSRL3PRHzo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y5eSRL3PRHzo.npy", "labels": "/m/028ght,/m/03qtwd", "caption": "A crowd applauds for a while" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part0/Y-EQByFLFqig.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y-EQByFLFqig.npy", "labels": "/m/06mb1,/m/0ngt1,/t/dd00038", "caption": "A man speaking as rain lightly falls followed by thunder" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YHVz-FJBf_iM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YHVz-FJBf_iM.npy", "labels": "/m/01jt3m,/m/0838f", "caption": "Toilet flushes and water gurgles as it drains" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YBXxlqaDvdaA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBXxlqaDvdaA.npy", "labels": "/m/05kq4,/m/07yv9,/m/09x0r,/m/0hsrw,/m/0j6m2", "caption": "A man talking as ocean waves trickle and splash while wind blows into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y1PvMtRIlZNI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1PvMtRIlZNI.npy", "labels": "/m/07swgks", "caption": "A stream of water trickling as plastic clanks against a metal surface followed by water pouring down a drain alongside a camera muffling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YPMMdAKZxI_I.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YPMMdAKZxI_I.npy", "labels": "/m/03q5_w,/m/09x0r", "caption": "Loud burping speech followed by women laughing, alongside a man and woman talking in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/Yj0KvrVE_Oww.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yj0KvrVE_Oww.npy", "labels": "/m/0912c9,/m/09x0r,/t/dd00125", "caption": "Two adult males speak, a small horn blow, and clattering occurs" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/YhuMLK0oA3L8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YhuMLK0oA3L8.npy", "labels": "/m/01w250", "caption": "A man speaks then whistles with a playing guitar" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/YilspW7JRjAg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YilspW7JRjAg.npy", "labels": "/m/012f08,/m/02mk9,/m/07yv9,/m/0k4j", "caption": "A vehicle engine revving a few times" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YEvZ3jOMYWxk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YEvZ3jOMYWxk.npy", "labels": "/m/02qldy,/m/02zsn,/m/09x0r", "caption": "A woman speaks while delivering a speech" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YL_CNz9Vrtkw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YL_CNz9Vrtkw.npy", "labels": "/m/028ght,/m/09x0r", "caption": "Brief speech followed by loud applause and cheering" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YBL8ksJ0sTXk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBL8ksJ0sTXk.npy", "labels": "/m/01jwx6,/m/07pb8fc,/m/07yv9,/m/09x0r,/m/0k4j", "caption": "Vibrations of an idling engine with a man speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/YilspW7JRjAg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YilspW7JRjAg.npy", "labels": "/m/012f08,/m/02mk9,/m/07yv9,/m/0k4j", "caption": "A vehicle engine revving numerous times then running idle" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4xrL4TSgHwU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4xrL4TSgHwU.npy", "labels": "/m/02mk9,/m/07pb8fc,/m/07q2z82,/m/07yv9,/t/dd00066,/t/dd00130", "caption": "A vehicle engine starting up then running idle" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YZ1Cyj4N05lk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YZ1Cyj4N05lk.npy", "labels": "/m/01w250", "caption": "A man whistles and then speaks loudly while some rustling and banging in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part19/YMe4npKmtchA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YMe4npKmtchA.npy", "labels": "/m/07pqc89,/m/0838f,/m/09x0r", "caption": "Splashing water and quiet murmuring" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YITlqMkR5alY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YITlqMkR5alY.npy", "labels": "/m/03fwl,/m/09x0r,/m/0ch8v,/m/0jbk", "caption": "Wind blowing followed by a scream with people speaking faintly in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YIvg_q4t-3w0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YIvg_q4t-3w0.npy", "labels": "/m/02dgv,/m/09x0r", "caption": "A person speaks and then a loud click occurs" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/YwNiYSYJXssA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YwNiYSYJXssA.npy", "labels": "/m/03k3r,/m/09x0r,/m/0jbk", "caption": "A kid speaking as camera plastic clicking followed by a crowd of people gasping and talking followed by a person whistling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/YhuMLK0oA3L8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YhuMLK0oA3L8.npy", "labels": "/m/01w250", "caption": "A man speaks then whistles with a playing guitar" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/YzBXoaQ1GVlc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YzBXoaQ1GVlc.npy", "labels": "/m/09x0r,/m/0ytgt,/t/dd00013,/t/dd00126", "caption": "A woman talking while a group of children shout and talk in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/Yf2fSxfvmkZQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yf2fSxfvmkZQ.npy", "labels": "/m/01d380,/m/09x0r", "caption": "A man speaks, a power tool starts and increases in frequency, a clunking noise" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YU90e2P9jy30.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YU90e2P9jy30.npy", "labels": "/m/07pqc89,/m/09x0r", "caption": "Squeaking and bouncing followed by a man speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/YzEM94PH29VQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YzEM94PH29VQ.npy", "labels": "/m/09x0r,/t/dd00002", "caption": "An infant crying as a group of kids and adults talk in the background while a woman talks in the foreground" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YXJba7pTbpD0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YXJba7pTbpD0.npy", "labels": "/m/07qlf79", "caption": "Spray and then a loud pop and hiss" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YtjCNwdOUiGc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YtjCNwdOUiGc.npy", "labels": "/m/07qv_d5,/m/07yv9,/m/0912c9", "caption": "A bus engine running followed by a bus horn honking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part19/YMPLZUg89y5U.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YMPLZUg89y5U.npy", "labels": "/m/07r04,/m/07yv9,/m/09x0r", "caption": "A large truck engine running idle as a man is talking and wind blows into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/YelztUCeNQvQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YelztUCeNQvQ.npy", "labels": "/m/0195fx,/m/01g50p,/m/0284vy3,/m/06d_3,/m/07jdr", "caption": "A train honks horn and passes by" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4Ujigme2IxY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4Ujigme2IxY.npy", "labels": "/m/01jwx6", "caption": "Vehicle engine running then a high whistle" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YAizmnCDlXos.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YAizmnCDlXos.npy", "labels": "/m/07qjznl,/m/07qjznt", "caption": "A steady ringing with the tick took of a clock" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YZBtgrP4vU_w.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YZBtgrP4vU_w.npy", "labels": "/m/07p9k1k", "caption": "Sizzling and crackling are occurring" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3qrVku794u0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3qrVku794u0.npy", "labels": "/m/02fs_r,/m/09x0r,/m/0fx9l", "caption": "A man talking before and after a young kid talks as plastic rattles followed by an electronic beep" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part19/YMPLZUg89y5U.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YMPLZUg89y5U.npy", "labels": "/m/07r04,/m/07yv9,/m/09x0r", "caption": "Male speaking with rustling in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part4/Y2t82STv2GR8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y2t82STv2GR8.npy", "labels": "/m/0395lw", "caption": "Bells are ringing with echo repeatedly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/Yzq00Oe1ecpE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yzq00Oe1ecpE.npy", "labels": "/m/012f08,/m/01bjv,/m/07yv9", "caption": "A bus engine driving then slowing down before accelerating" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/Yktc_tJxw8sc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yktc_tJxw8sc.npy", "labels": "/m/0463cq4", "caption": "An infant crying" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/YpI_kPedctoo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YpI_kPedctoo.npy", "labels": "/m/04_sv,/m/07yv9,/m/09x0r", "caption": "Motorcycle engines running and revving as a man talks in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/Yy93cZqNCtks.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yy93cZqNCtks.npy", "labels": "/m/032s66,/m/04zjc", "caption": "A series of gunshots followed by a man speaking and footsteps running proceeded by more gunshots firing and a dog growling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/YdP5DbAzTl5M.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YdP5DbAzTl5M.npy", "labels": "/m/019jd,/m/02rlv9,/m/07yv9,/m/09x0r", "caption": "A motorboat engine running as a man talks followed by wind blowing into a microphone and plastic clacking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YLWng-4PDzPM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YLWng-4PDzPM.npy", "labels": "/m/01w250", "caption": "Instrumental music playing followed by heavy fabric being rustled then a man whistling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YIvfaKPDWC00.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YIvfaKPDWC00.npy", "labels": "/m/012f08,/m/012ndj,/m/03j1ly,/m/03kmc9,/m/07yv9", "caption": "Emergency sirens wailing as a vehicle accelerates in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/Ycr0GiZr0TNY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ycr0GiZr0TNY.npy", "labels": "/m/01j3sz,/t/dd00001", "caption": "Babies are laughing followed by a fizzling sound" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part1/Y-nQHwrRLfc0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y-nQHwrRLfc0.npy", "labels": "/m/02mk9,/m/07pb8fc,/t/dd00066", "caption": "Chainsaw being run" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y1e98HeU9Vrg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1e98HeU9Vrg.npy", "labels": "/m/034srq,/m/03m9d0z,/m/05kq4", "caption": "Waves and wind rake a shore" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y1slvoNgzBLE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1slvoNgzBLE.npy", "labels": "/m/01g50p,/m/06d_3,/m/07jdr,/m/07yv9,/m/0912c9", "caption": "A subway train signal plays followed by a bell chiming followed by a horn honking as a crowd of people talk in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/YfrOqlk0Wm5Y.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YfrOqlk0Wm5Y.npy", "labels": "/m/07pdjhy", "caption": "A man talking as metal clacks followed by metal scrapping against a metal surface" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YJZloTOdIY_c.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YJZloTOdIY_c.npy", "labels": "/m/03k3r,/m/07q5rw0,/m/07rv9rh,/m/0jbk", "caption": "Horses growl and clop hooves" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YIJ6pm5Kns8A.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YIJ6pm5Kns8A.npy", "labels": "/m/03q5_w,/m/09x0r", "caption": "A woman speaks, then a phone chimes, then there is a burp followed by laughter" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/Yh0M4RS8p_mo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yh0M4RS8p_mo.npy", "labels": "/m/01j3sz,/m/0463cq4", "caption": "Audio static followed by a man laughing before an electronic device motor slides then an infant cries" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/Yz4MeV9IGVo0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yz4MeV9IGVo0.npy", "labels": "/m/01bjv,/m/07yv9,/m/09x0r", "caption": "A man speaking through a radio as a truck engine runs idle and a vehicle accelerates in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part7/Y63KW_EQ72yU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y63KW_EQ72yU.npy", "labels": "/m/014zdl,/m/07qsvvw", "caption": "Several very loud explosions occur" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YJfaj4P3us9M.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YJfaj4P3us9M.npy", "labels": "/m/02c8p,/m/07cx4", "caption": "A telephone dialing tone followed by a plastic switch flipping on and off" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part0/Y-NrFeH-kBSM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y-NrFeH-kBSM.npy", "labels": "/m/032s66", "caption": "A gun cocking then firing as metal clanks on a hard surface followed by a man talking during an electronic laser effect as gunshots and explosions go off in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YnlC4UI4hZ60.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YnlC4UI4hZ60.npy", "labels": "/m/012f08,/m/02mk9,/m/07yv9,/m/0k4j", "caption": "Rapid clicking occurs, a motor vehicle engine attempts to start and grinds, then the engine fully engages and begins to run and vibrate" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YE3D_z0aoUEg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YE3D_z0aoUEg.npy", "labels": "/m/07st88b,/m/09ld4", "caption": "Frogs croaking and a humming with insects vocalizing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YE3Q1jfTeuWs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YE3Q1jfTeuWs.npy", "labels": "/t/dd00002", "caption": "A baby crying and breathing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/YwoadpeAGHUQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YwoadpeAGHUQ.npy", "labels": "/m/012ndj,/m/03j1ly,/m/03kmc9", "caption": "An emergency vehicles' siren with a brief male yell" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/YxIztYnMIWUA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YxIztYnMIWUA.npy", "labels": "/m/01hnzm,/m/07cx4,/m/07pp8cl", "caption": "A telephone ringing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YAbplcXwXnvE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YAbplcXwXnvE.npy", "labels": "/m/09x0r,/t/dd00112", "caption": "Plastic crinkling as a young girl is talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3ghVB-KaU_E.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3ghVB-KaU_E.npy", "labels": "/m/07rjwbb", "caption": "A man talking followed by a brush scrapping then liquid spraying in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/Yktc_tJxw8sc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yktc_tJxw8sc.npy", "labels": "/m/0463cq4", "caption": "A crying and moaning in a low voice" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y2ItTq2JShdU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y2ItTq2JShdU.npy", "labels": "/m/07rqsjt", "caption": "Train engine as it travels" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YawxrHOpt-sE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YawxrHOpt-sE.npy", "labels": "/m/03fwl,/m/09x0r,/m/0ch8v,/m/0jbk", "caption": "A goat yelling while a group of people laugh and talk alongside bells jingling and a motorbike driving by in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/Yy3-M1sonh3M.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yy3-M1sonh3M.npy", "labels": "/m/01jt3m", "caption": "A footstep shuffling on a hard surface followed by plastic clacking then a toilet flushing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/Yir1XTdyt4IY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yir1XTdyt4IY.npy", "labels": "/m/014zdl,/m/07qsvvw,/m/09x0r", "caption": "A loud burst and a metallic ring followed by men speaking and laughing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YWU3qB7gf6ao.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YWU3qB7gf6ao.npy", "labels": "/m/02fs_r", "caption": "Digital beeps with some clicking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3ghVB-KaU_E.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3ghVB-KaU_E.npy", "labels": "/m/07rjwbb", "caption": "Man speaking continuously with hissing in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YYEYeQ0lIkBQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YYEYeQ0lIkBQ.npy", "labels": "/m/015p6,/m/09ddx,/m/09x0r", "caption": "A crowd of people talking as a man hollers and laughs while a group of ducks quack" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part4/Y2j8pxiFvElM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y2j8pxiFvElM.npy", "labels": "/m/01yrx,/m/068hy,/m/07qrkrw,/m/0jbk", "caption": "A cat meows repeatedly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part4/Y35b9BSmN5JM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y35b9BSmN5JM.npy", "labels": "/m/07q2z82,/m/07yv9,/m/0k4j", "caption": "Truck in idle mode, door closing, engine revving and accelerating" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YD1Sy7kRoaR8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YD1Sy7kRoaR8.npy", "labels": "/m/03k3r,/m/07rv9rh,/m/09x0r,/m/0jbk", "caption": "A woman talking while children talk in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YWq4OD3olO2w.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YWq4OD3olO2w.npy", "labels": "/m/07r660_,/m/09x0r,/m/0ytgt,/t/dd00125", "caption": "A man talking followed by screaming children, followed by more high pitched conversation" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part38/Yup2PpjTzyyc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yup2PpjTzyyc.npy", "labels": "/m/01yrx,/m/07qrkrw,/m/09x0r,/m/0jbk", "caption": "Music playing as a man is speaking followed by a series of electronic beeping and meowing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YARFFw0e_jig.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YARFFw0e_jig.npy", "labels": "/m/03q5_w", "caption": "Loud burping and screaming" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3RultJjvTWI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3RultJjvTWI.npy", "labels": "/m/019jd,/m/034srq,/m/03m9d0z,/t/dd00092", "caption": "Vibrations and splashing followed by people speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/YfK4QBQZ6i7w.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YfK4QBQZ6i7w.npy", "labels": "/m/01j3sz,/m/07rgt08,/m/07s04w4", "caption": "People are laughing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YAtkD-3GjXMw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YAtkD-3GjXMw.npy", "labels": "/m/032s66,/m/04zjc", "caption": "A rap and hip-hop song starts with a person rapping loudly with random computer generated sounds" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/YA61Mry8zBwE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YA61Mry8zBwE.npy", "labels": "/m/07rv9rh,/m/09x0r,/m/0jbk", "caption": "A crowd is clapping at an animal of some kind" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y7-HCqJFwHoI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y7-HCqJFwHoI.npy", "labels": "/m/01m2v,/m/0316dw", "caption": "Keys typing repeatedly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YlJayhiVzl_E.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YlJayhiVzl_E.npy", "labels": "/m/019jd,/m/02rlv9,/m/03m9d0z,/t/dd00092", "caption": "The wind is blowing while a boat motor runs and water splashes, and the boat motor advances and gets louder but then fades somewhat" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/Yd6gu2w19YQo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yd6gu2w19YQo.npy", "labels": "/m/01j3sz", "caption": "A baby laughing loudly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YAagLJkfrFMk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YAagLJkfrFMk.npy", "labels": "/m/01jt3m", "caption": "A toilet is flushing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/YA2mcp0N__7U.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YA2mcp0N__7U.npy", "labels": "/m/07qlf79,/m/09x0r", "caption": "Coughing and speech" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YKvrcRMfFzOE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YKvrcRMfFzOE.npy", "labels": "/m/07yv9,/m/09ct_,/m/0k5j", "caption": "A helicopter flying and wind" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y7-HCqJFwHoI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y7-HCqJFwHoI.npy", "labels": "/m/01m2v,/m/0316dw", "caption": "A person is typing in a computer keyboard" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YrjUrB1WUpcI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YrjUrB1WUpcI.npy", "labels": "/m/07swgks", "caption": "A sink faucet turning on then off as water pours then drains down a pipe" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9BukzlPNqC8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9BukzlPNqC8.npy", "labels": "/m/01d380,/m/09x0r", "caption": "A power tool motor humming as compressed air hisses alongside a group of people talking in the background followed by hammering on a metal surface" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part9/Y8OTd45_6cvY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y8OTd45_6cvY.npy", "labels": "/m/07qlf79", "caption": "A constant pounding noise followed by vibrating sounds" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YPg2cWEnEEvc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YPg2cWEnEEvc.npy", "labels": "/m/03q5_w", "caption": "A series of burping and farting" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YbIiiIo20PsY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YbIiiIo20PsY.npy", "labels": "/m/01h3n,/m/09x0r", "caption": "A main is speaking over a group of bees are buzzing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YbmEF-c-M174.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YbmEF-c-M174.npy", "labels": "/m/015p6,/m/09ddx,/m/09x0r", "caption": "A duck quacks then a man speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part19/YNDaVSIJaXVs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YNDaVSIJaXVs.npy", "labels": "/m/014yck,/m/07yv9,/m/0cmf2,/m/0k5j,/t/dd00128", "caption": "Wind blowing with a distant jet engine humming" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YKnXNy5Q6YS4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YKnXNy5Q6YS4.npy", "labels": "/m/01h3n,/m/03vt0,/m/09x0r", "caption": "Muffled speech and insect buzzing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/Ygr5Zss89yLQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ygr5Zss89yLQ.npy", "labels": "/m/01bjv,/m/07yv9,/m/09x0r", "caption": "A large motor vehicle engine is idling, an adult female speaks, vehicle traffic is present, and people talk in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y6ZFU4PqXmoI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y6ZFU4PqXmoI.npy", "labels": "/m/019jd,/m/02rlv9,/m/07yv9,/m/09x0r", "caption": "Roaring is present, cracking occurs, a metal clink, and an adult male speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YArHiac57pVk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YArHiac57pVk.npy", "labels": "/m/07qjznl,/m/09x0r", "caption": "A man speaks and then two ticktocks click off" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YIvfaKPDWC00.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YIvfaKPDWC00.npy", "labels": "/m/012f08,/m/012ndj,/m/03j1ly,/m/03kmc9,/m/07yv9", "caption": "An emergency siren wailing as a large truck engine accelerates growing louder" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part7/Y6BJ455B1aAs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y6BJ455B1aAs.npy", "labels": "/m/014zdl,/m/07qsvvw", "caption": "A whooshing noise followed by an explosion" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3IScngdQA4I.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3IScngdQA4I.npy", "labels": "/m/02dgv,/m/09x0r", "caption": "Some groaning followed by a woman speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y0fMXnvD38zI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y0fMXnvD38zI.npy", "labels": "/m/019jd,/m/034srq,/m/03m9d0z,/m/05kq4,/t/dd00092", "caption": "Waves roll slowly and water swirls as the wind blows" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YXZTt1xdK8uQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YXZTt1xdK8uQ.npy", "labels": "/m/07swgks", "caption": "Water gurgles while a vehicle engine accelerates with a loud exhaust" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YWOywdRmySs0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YWOywdRmySs0.npy", "labels": "/m/09x0r,/t/dd00112", "caption": "A man talking followed by plastic crumpling and crinkling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/YhuMLK0oA3L8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YhuMLK0oA3L8.npy", "labels": "/m/01w250", "caption": "A man talking then whistling as guitar music plays" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YYk274Wr5iIE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YYk274Wr5iIE.npy", "labels": "/m/06mb1", "caption": "A vehicle driving by while splashing water as a stream of water trickles and flows followed by a thunder roaring in the distance while wind blows into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YTdl9SmBbRnA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YTdl9SmBbRnA.npy", "labels": "/m/012f08,/m/01bjv,/m/07yv9,/m/09x0r", "caption": "A vehicle engine accelerating then slowing down as a man talks in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YtfOIhQpYYe8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YtfOIhQpYYe8.npy", "labels": "/m/09ct_,/m/09x0r,/t/dd00129", "caption": "A helicopter flying as a man talks in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/Yy93cZqNCtks.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yy93cZqNCtks.npy", "labels": "/m/032s66,/m/04zjc", "caption": "A man talking as footsteps run on concrete followed by a series of gunshots firing a gun cocking while another man talks in the background before a dog growls" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YQ3vkJMVMbC8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YQ3vkJMVMbC8.npy", "labels": "/m/01jt3m", "caption": "A toilet flushing followed by an infant shouting in the distance then another toilet flushing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/Yo_3MDLl_aH0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yo_3MDLl_aH0.npy", "labels": "/m/032s66,/m/0_1c", "caption": "Artillery cannons firing several times" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YOpiWMltpj44.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YOpiWMltpj44.npy", "labels": "/m/015p6,/m/09ddx,/m/0dbvp", "caption": "Ducks quack and water splashes with some animal screeching in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YErxgH5g3Kx0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YErxgH5g3Kx0.npy", "labels": "/m/03k3r,/m/07rv9rh,/m/0jbk", "caption": "A horse clip-clops and a horse neighs from a distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/Ye4ph6bIC5zc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ye4ph6bIC5zc.npy", "labels": "/m/012f08,/m/07yv9,/m/0k4j,/m/0ltv", "caption": "Human voices followed by the movement of a vehicle" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y52IxrdTxGs4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y52IxrdTxGs4.npy", "labels": "/m/07qsvvw,/m/09x0r", "caption": "A loud burst followed by humming and a heartbeat then a man speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/Ydkiwn2FdDVw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ydkiwn2FdDVw.npy", "labels": "/m/09ddx,/m/09x0r", "caption": "Ongoing speech with the faint quacking of a duck in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part0/Y-NrFeH-kBSM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y-NrFeH-kBSM.npy", "labels": "/m/032s66", "caption": "Loading and firing of a gun with the sound of running o f footsteps at the end and a man speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4s2rRnu2PZo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4s2rRnu2PZo.npy", "labels": "/m/07rqsjt", "caption": "Music plays followed by some banging and whooshes then gunshots and a grunt from a man" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YAMQei29haCw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YAMQei29haCw.npy", "labels": "/m/01d380", "caption": "Drilling with intermittent stopping and a man moaning briefly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YAKHZMg9ba30.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YAKHZMg9ba30.npy", "labels": "/m/07rv9rh,/m/09x0r,/m/0jbk", "caption": "Male speech with people speaking in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YTwR8BA6buMI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YTwR8BA6buMI.npy", "labels": "/m/07qjznl", "caption": "A piano playing as plastic bonks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YYQGW5AwDOIo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YYQGW5AwDOIo.npy", "labels": "/m/07yv9,/m/0k4j,/m/0ltv", "caption": "Vehicles driving by as people talk in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YLxu-3_h4kc4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YLxu-3_h4kc4.npy", "labels": "/m/03q5_w", "caption": "Two large loud burps" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YIvg_q4t-3w0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YIvg_q4t-3w0.npy", "labels": "/m/02dgv,/m/09x0r", "caption": "A woman is talking followed by a tapping noise" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y6cS0FsUM-cQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y6cS0FsUM-cQ.npy", "labels": "/m/01yrx,/m/068hy,/m/07qrkrw,/m/07r81j2,/m/09x0r,/m/0jbk", "caption": "A cat meowing and hissing and then female speech" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YOr7umk40TZA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YOr7umk40TZA.npy", "labels": "/m/01jwx6", "caption": "Vibrating noise from an engine" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part24/YV4PLSw_WzVw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YV4PLSw_WzVw.npy", "labels": "/m/07r04,/m/07rknqz,/m/07yv9", "caption": "Spinning tires on pavement" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/YjXkLS_QzUrI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YjXkLS_QzUrI.npy", "labels": "/m/068hy,/m/07qrkrw", "caption": "Steam hissing followed by a bird cawing during audio feedback humming" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YK_Vre_-4KqU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YK_Vre_-4KqU.npy", "labels": "/m/07yv9,/m/0k5j,/t/dd00129", "caption": "Small aircraft taking off and receding into the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YAJtNitYMa1I.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YAJtNitYMa1I.npy", "labels": "/m/07p9k1k,/m/0dxrf", "caption": "Food sizzling while cooking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part7/Y6BJ455B1aAs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y6BJ455B1aAs.npy", "labels": "/m/014zdl,/m/07qsvvw", "caption": "A missile launching followed by an explosion and metal screeching as a motor hums in the background." }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part38/YuhSDBwVrEdo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YuhSDBwVrEdo.npy", "labels": "/m/01w250", "caption": "A whistling noise with wind blowing in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YKnXNy5Q6YS4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YKnXNy5Q6YS4.npy", "labels": "/m/01h3n,/m/03vt0,/m/09x0r", "caption": "Man speaking while insects buzz around" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part7/Y63KW_EQ72yU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y63KW_EQ72yU.npy", "labels": "/m/014zdl,/m/07qsvvw", "caption": "Loud bursts of explosions with high wind" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YR4fXcbWFhJg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YR4fXcbWFhJg.npy", "labels": "/m/03k3r,/m/09x0r,/m/0ch8v,/m/0jbk,/t/dd00129", "caption": "A man talking followed by a woman shouting then yelling as wind blows into a microphone while birds chirp in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YYflmW68gL4E.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YYflmW68gL4E.npy", "labels": "/m/03q5_w,/m/09x0r", "caption": "A person burps followed by laughter and a woman speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/YxQDq3A4Zfbo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YxQDq3A4Zfbo.npy", "labels": "/m/019jd,/m/034srq,/m/03m9d0z,/m/05kq4,/m/0hsrw,/t/dd00092", "caption": "Ocean waves crashing and water splashing as wind blows into a microphone followed by a man talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/YinSvboaSRwA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YinSvboaSRwA.npy", "labels": "/m/07k1x,/m/083vt,/m/09x0r", "caption": "A male speaking and a saw running" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/Yn74IYuCe_ms.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yn74IYuCe_ms.npy", "labels": "/m/09x0r,/m/0j6m2", "caption": "A river stream flowing followed by a kid talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YszkiW0GXEOI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YszkiW0GXEOI.npy", "labels": "/m/015p6,/m/01w250", "caption": "Someone whistles followed by a bird tweeting with chirps in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part4/Y2RjqBRzmxaM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y2RjqBRzmxaM.npy", "labels": "/m/06mb1,/m/07r10fb,/t/dd00038", "caption": "Instrumental music playing as a woman speaks followed by rain pouring then rain falling on a surface" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/Yn74IYuCe_ms.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yn74IYuCe_ms.npy", "labels": "/m/09x0r,/m/0j6m2", "caption": "A large volume of water is rushing, splashing and gurgling, and an adult male speaks briefly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/YpI_kPedctoo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YpI_kPedctoo.npy", "labels": "/m/04_sv,/m/07yv9,/m/09x0r", "caption": "An engine running and being revved and some muffled speech" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/YdmUOSyPXkUw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YdmUOSyPXkUw.npy", "labels": "/m/06wzb,/m/07rjwbb", "caption": "An idle steam engine running while steam blows and hisses and a man talks faintly in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/YeUecAF626A8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YeUecAF626A8.npy", "labels": "/m/07yv9,/m/09x0r,/m/0k4j,/m/0ltv", "caption": "Engines hum and vibrate and rev their engines" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/Yq46VXJ6JN9M.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yq46VXJ6JN9M.npy", "labels": "/m/07qlf79", "caption": "Footsteps shuffling followed by compressed air spraying then plastic camera muffling as birds chirp in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/Yhmd6pa2e_rs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yhmd6pa2e_rs.npy", "labels": "/m/01bjv,/m/07yv9,/m/09x0r", "caption": "A bus accelerating followed by a man speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part19/YMTIF_l_8d4Q.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YMTIF_l_8d4Q.npy", "labels": "/m/0463cq4,/m/09x0r", "caption": "A baby is crying, and a woman speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part19/YMTaLknnq4wc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YMTaLknnq4wc.npy", "labels": "/m/01w250", "caption": "Whistling and then a female singing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YPb6MqpdX5Jw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YPb6MqpdX5Jw.npy", "labels": "/m/0ngt1", "caption": "A horse clip-clops in a windy rain as thunder cracks in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y2KR0C5ysO8o.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y2KR0C5ysO8o.npy", "labels": "/m/02mk9,/m/07pb8fc,/m/07q2z82,/m/07yv9,/m/09x0r,/t/dd00066", "caption": "A mid-size motor vehicle engine accelerates and is accompanied by hissing and spinning tires, then it decelerates and an adult male begins to speak" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YKel-hfZ_9h8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YKel-hfZ_9h8.npy", "labels": "/m/09x0r,/m/0ytgt,/t/dd00013", "caption": "Rustling followed by a man speaking and a child laughing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/YyVjivgsU2aA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YyVjivgsU2aA.npy", "labels": "/m/012f08,/m/07rknqz,/m/07yv9,/m/09x0r,/m/0h9mv,/m/0k4j,/m/0ltv", "caption": "A motor vehicle revs and skids tires while speeding off" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/YfYTZVxQ8LJk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YfYTZVxQ8LJk.npy", "labels": "/m/09x0r,/m/0ytgt,/t/dd00125", "caption": "A woman speaks followed by a girl speaking faintly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/Yf2fSxfvmkZQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yf2fSxfvmkZQ.npy", "labels": "/m/01d380,/m/09x0r", "caption": "A drill is drilling followed by speech" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/Ydxow2DcTrwk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ydxow2DcTrwk.npy", "labels": "/m/0ngt1", "caption": "A man and a woman talking while rain falls, followed by a crash of thunder" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YPuLuZ_TXv-0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YPuLuZ_TXv-0.npy", "labels": "/m/0316dw,/m/0c2wf", "caption": "Typing is occurring on a typewriter, with fast and sharp taps and intermittent zipping of the carriage" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YsqsI2UyrcBQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YsqsI2UyrcBQ.npy", "labels": "/m/07q2z82,/m/07yv9,/m/0k4j", "caption": "A revving sound is accelerating" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/Yf2fSxfvmkZQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yf2fSxfvmkZQ.npy", "labels": "/m/01d380,/m/09x0r", "caption": "A man talking as metal thumps followed by plastic rustling then a power tool drilling while a metal pot clangs against a hard surface" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3xDZ-kdGE3o.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3xDZ-kdGE3o.npy", "labels": "/m/01jt3m,/m/0838f", "caption": "A door closes followed by a toilet flushing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YRfGapDlAYoQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YRfGapDlAYoQ.npy", "labels": "/m/01w250", "caption": "A person whistles a tune with wind noise and people talking in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YQKHpSAAjakY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YQKHpSAAjakY.npy", "labels": "/m/04_sv,/m/07yv9,/m/09x0r,/t/dd00128", "caption": "A motorcycle engine is idling and vibrating while an adult male speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/Yi1u_2eZYYlE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yi1u_2eZYYlE.npy", "labels": "/m/07pb8fc,/m/07r04,/m/07yv9", "caption": "A short loud vibration" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YUE3XnVFodMI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YUE3XnVFodMI.npy", "labels": "/m/028ght,/m/09x0r", "caption": "A crowd of people applauding followed by a woman talking on a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/Yy1a8PntuXYw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yy1a8PntuXYw.npy", "labels": "/m/01jt3m", "caption": "A woman yelling in the distance followed by a toilet flushing as an air ventilation system runs" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YkgjNIDmO8a8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YkgjNIDmO8a8.npy", "labels": "/m/012ndj,/m/03j1ly,/m/03kmc9", "caption": "An emergency vehicle siren blasts as a man speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y473wBEwC35M.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y473wBEwC35M.npy", "labels": "/m/02qldy,/m/05zppz,/m/09x0r", "caption": "A man speaking as a vehicle horn honks in the background and another man talks in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YWHRnyGXcdy8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YWHRnyGXcdy8.npy", "labels": "/t/dd00002", "caption": "An infant crying" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YRNBoH2LHQEM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YRNBoH2LHQEM.npy", "labels": "/m/028ght", "caption": "A crowd applauds, and faint speech occurs" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y473wBEwC35M.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y473wBEwC35M.npy", "labels": "/m/02qldy,/m/05zppz,/m/09x0r", "caption": "A man is talking some traffic noise in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part7/Y5ye0X5saadg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y5ye0X5saadg.npy", "labels": "/m/09ct_,/m/09x0r", "caption": "Beeping occurs, an adult male speaks, blasts and shots occur, and a helicopter is operating" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/Yr2djvq1vc68.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yr2djvq1vc68.npy", "labels": "/m/0130jx,/m/02jz0l,/m/0838f", "caption": "Water pouring out of a faucet at a high rate followed by a container filling with liquid before splashing out proceeded by scrubbing on a plastic surface" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YL8dA-2Lu2hY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YL8dA-2Lu2hY.npy", "labels": "/m/01w250", "caption": "Loud wolf whistles occur twice in a quiet environment" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YsTMKled6Q1M.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YsTMKled6Q1M.npy", "labels": "/m/015p6,/m/0h0rv,/t/dd00129", "caption": "Rustling followed by whistling then birds chirping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part38/YvEWmHtiznF8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YvEWmHtiznF8.npy", "labels": "/m/012f08,/m/01bjv,/m/07yv9,/m/09x0r", "caption": "A man talks as an engine idles loudly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/Ytpm5IOD5d4o.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ytpm5IOD5d4o.npy", "labels": "/m/01w250", "caption": "Brief speech followed by whistling a tune" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YJon_DEFqsfM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YJon_DEFqsfM.npy", "labels": "/m/020bb7,/m/06_y0by,/m/09ddx", "caption": "Several breeds of birds chirping and honking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9xoYx3lTJ9I.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9xoYx3lTJ9I.npy", "labels": "/m/019jd,/m/02rlv9,/m/03m9d0z,/t/dd00092", "caption": "Wind blowing heavily into a microphone as a speedboat drives by and water splashes in the distance followed by a man talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/YzFzPOsOKog4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YzFzPOsOKog4.npy", "labels": "/m/01h3n,/m/03vt0,/m/0h2mp", "caption": "Insects buzzing as tin containers clank and rattle while birds chirp in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YtaYKM1OSTwE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YtaYKM1OSTwE.npy", "labels": "/m/03fwl,/m/07bgp,/m/0ch8v,/m/0jbk", "caption": "Sheep bleating with a baby sheep baaing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y1GgEpRZDWN0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1GgEpRZDWN0.npy", "labels": "/m/01h8n0,/m/02zsn,/m/09x0r", "caption": "Female and male are having conversation" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part24/YVE6Ku0-ucUM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YVE6Ku0-ucUM.npy", "labels": "/m/07qsvvw,/m/09x0r", "caption": "Speech and then a pop and laughter" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part7/Y5iTRKJqUIw8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y5iTRKJqUIw8.npy", "labels": "/m/07qjznl,/m/09x0r", "caption": "Bells chiming followed by a train whistle blowing as a crowd of people talk in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4IeDBwyQ9ZQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4IeDBwyQ9ZQ.npy", "labels": "/m/04brg2", "caption": "A tin can rattling followed by a woman talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YOTLtzk0W4zg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YOTLtzk0W4zg.npy", "labels": "/m/07yv9,/m/09x0r,/m/0k4j,/t/dd00128,/t/dd00130", "caption": "A mid-size motor vehicle engine is idling, and an adult male speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YrvDcg9DoNKA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YrvDcg9DoNKA.npy", "labels": "/m/0ngt1", "caption": "It is raining and thundering, and then a man speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YnU-AI3Cmc3M.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YnU-AI3Cmc3M.npy", "labels": "/m/015p6,/m/0h0rv,/t/dd00129", "caption": "Birds are cooing, and wings flap" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part27/Y_GI7meqlYZk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y_GI7meqlYZk.npy", "labels": "/m/01yrx,/m/068hy,/m/07qrkrw,/m/09x0r,/m/0jbk", "caption": "A cat meowing and young female speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/Yh3UhoHIMfpw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yh3UhoHIMfpw.npy", "labels": "/m/02_41,/m/03m9d0z,/t/dd00092", "caption": "Wind is blowing along with some engines" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YLB6CZ0x-kns.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YLB6CZ0x-kns.npy", "labels": "/m/07r04,/m/07yv9,/t/dd00128", "caption": "Metal clanking followed by steam hissing as a truck engine is running then accelerating" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/YdmUOSyPXkUw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YdmUOSyPXkUw.npy", "labels": "/m/06wzb,/m/07rjwbb", "caption": "A steam engine runs as steam hisses and sprays while a man is talking in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YYflmW68gL4E.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YYflmW68gL4E.npy", "labels": "/m/03q5_w,/m/09x0r", "caption": "A burp followed by a two girls laughing then talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YcFHFVGOtp6g.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YcFHFVGOtp6g.npy", "labels": "/m/09ld4,/m/09x0r", "caption": "Camera rattling and muffling as a woman speaks in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y14ekd4nkpwc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y14ekd4nkpwc.npy", "labels": "/t/dd00002", "caption": "Baby crying and person tapping his mouth" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YCYUlLTKoa1Y.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YCYUlLTKoa1Y.npy", "labels": "/m/09x0r,/m/0llzx", "caption": "A woman speaks followed by a sewing machine slow stitching" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YP4qd8uodw_M.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YP4qd8uodw_M.npy", "labels": "/m/02fs_r,/m/09x0r", "caption": "Men speak with some light clicks then vibrations and then digital clicks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YnlC4UI4hZ60.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YnlC4UI4hZ60.npy", "labels": "/m/012f08,/m/02mk9,/m/07yv9,/m/0k4j", "caption": "Rapid metal rattling as a vehicle engine stalls before starting up" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part19/YMj_BO-iK1G4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YMj_BO-iK1G4.npy", "labels": "/m/0llzx", "caption": "A quick burst of vibrations from a sewing machine with clicking and rattling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/YptIksg9KEac.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YptIksg9KEac.npy", "labels": "/m/068hy,/m/07rc7d9,/m/0bt9lr,/m/0jbk,/t/dd00136", "caption": "Leaves rustling in the wind with dogs barking and birds chirping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YCchRf2jq6fc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YCchRf2jq6fc.npy", "labels": "/m/02qldy,/m/02zsn,/m/09x0r", "caption": "An adult female is speaking in a quiet environment" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YFL8KTgMGrN4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YFL8KTgMGrN4.npy", "labels": "/m/06wzb,/m/07rjwbb", "caption": "A vacuum moving back and forth" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YqPYwp1K4sZE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YqPYwp1K4sZE.npy", "labels": "/m/09x0r,/t/dd00112,/t/dd00125", "caption": "Clicking and crinkling plastic with a person speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/Yo7-X8DAToGc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yo7-X8DAToGc.npy", "labels": "/m/012f08,/m/07yv9,/m/0ltv,/t/dd00134", "caption": "A vehicle accelerating and driving by as birds chirp faintly in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y7XXSOzDQ2z0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y7XXSOzDQ2z0.npy", "labels": "/m/07yv9,/m/0h9mv,/m/0k4j,/m/0ltv", "caption": "Clicking followed by booming engines accelerating into the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YTtRtURWVYBE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YTtRtURWVYBE.npy", "labels": "/m/0395lw", "caption": "A series of bell chime" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YPkmpxrsidZM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YPkmpxrsidZM.npy", "labels": "/m/028ght,/m/09x0r", "caption": "A crowd applauds with laughter while people communicate followed by a woman speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/Ykx6Rj4MDIAw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ykx6Rj4MDIAw.npy", "labels": "/m/07rjwbb", "caption": "A train clicks on a track" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YlHh0SwUhP8U.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YlHh0SwUhP8U.npy", "labels": "/m/09ddx", "caption": "A gunshot is followed by a click and clack and then a second gunshot" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part38/Yvigslb0kClE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yvigslb0kClE.npy", "labels": "/m/03fwl,/m/09x0r,/m/0jbk", "caption": "Rustling and knocking and then male speech with a goat vocalizing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YXf5LjaE_JQ0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YXf5LjaE_JQ0.npy", "labels": "/m/07qlf79,/m/09x0r", "caption": "A man is speaking with rumbling in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/Ydkiwn2FdDVw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ydkiwn2FdDVw.npy", "labels": "/m/09ddx,/m/09x0r", "caption": "A young boy talking as a duck is quacking while water trickles and frogs croak in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YU3CAjsm1sec.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YU3CAjsm1sec.npy", "labels": "/m/01yrx,/m/068hy,/m/07qrkrw,/m/0jbk", "caption": "Several cats meowing followed by a man singing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/YonBZOH88OYs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YonBZOH88OYs.npy", "labels": "/m/07qlf79", "caption": "White noise followed by intermittent hissing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YPLHXGDnig4M.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YPLHXGDnig4M.npy", "labels": "/m/01yrx,/m/07qrkrw", "caption": "A man talking then meowing and hissing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/YdZDgJzGtLLU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YdZDgJzGtLLU.npy", "labels": "/m/07pqc89", "caption": "Water is running, gurgling and splashing, and a quiet thump occurs" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YBL8ksJ0sTXk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBL8ksJ0sTXk.npy", "labels": "/m/01jwx6,/m/07pb8fc,/m/07yv9,/m/09x0r,/m/0k4j", "caption": "A vehicle engine running idle as a man is talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YXL8JV9qXGLE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YXL8JV9qXGLE.npy", "labels": "/m/0463cq4,/m/09x0r,/m/0ytgt,/t/dd00002,/t/dd00125", "caption": "Children speak and a woman speaks then a baby cries" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part9/Y8b9z7N25DmU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y8b9z7N25DmU.npy", "labels": "/m/01bjv,/m/07yv9,/m/09x0r,/t/dd00129", "caption": "Humming of an approaching bus with squeaking brakes and people speaking in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/Ykdflh3akyH8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ykdflh3akyH8.npy", "labels": "/m/0ghcn6,/m/0jbk,/t/dd00136", "caption": "A group of puppies whimpering as cardboard rustles" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/YyfYNPWs7mWY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YyfYNPWs7mWY.npy", "labels": "/m/02dgv,/m/05zppz,/m/09x0r", "caption": "Male speech, a door closing, and then male speech" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part7/Y6NBPiArs2-w.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y6NBPiArs2-w.npy", "labels": "/m/032s66", "caption": "Rapid gunfire with far away voice" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YE3D_z0aoUEg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YE3D_z0aoUEg.npy", "labels": "/m/07st88b,/m/09ld4", "caption": "A frog croaking and insects vocalizing with a humming" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part24/YUQtBt6CQpwg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YUQtBt6CQpwg.npy", "labels": "/m/09x0r,/m/0llzx", "caption": "A sewing machine operating idle followed by a man talking then several instances of metal ratcheting" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/YhV4bDCBDCy0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YhV4bDCBDCy0.npy", "labels": "/m/07r04,/m/07yv9,/m/09x0r", "caption": "Vehicle running with a far away voice in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y6TO9PEGpZcQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y6TO9PEGpZcQ.npy", "labels": "/m/012n7d,/m/012ndj,/m/03j1ly,/m/03kmc9", "caption": "A fire truck sounds the siren, and an engine is idling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YbAqgL5dCQOE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YbAqgL5dCQOE.npy", "labels": "/m/06mb1,/m/07r10fb,/t/dd00038", "caption": "Rain pouring on a hard surface as a vehicle drives by while water splashes in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YbJMMp6PLKqM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YbJMMp6PLKqM.npy", "labels": "/m/0463cq4,/m/09x0r,/m/0ytgt,/t/dd00125", "caption": "A woman talking followed by a young girl talking while an infant cries" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YNeZerAPXR-A.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YNeZerAPXR-A.npy", "labels": "/m/01j3sz,/m/09x0r,/t/dd00125", "caption": "A man and a woman laughing then talking followed by someone claps as a bell jingles repeatedly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/Yfx4r_KuW6No.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yfx4r_KuW6No.npy", "labels": "/m/09x0r,/m/0ytgt,/t/dd00126", "caption": "An adult female speaks, a child cries and speaks, the adult female speaks again, while the child continues to cry and speak, and the adult female speaks once more" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YOr7umk40TZA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YOr7umk40TZA.npy", "labels": "/m/01jwx6", "caption": "Vibrations from an engine" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y6cyKp3EDm-0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y6cyKp3EDm-0.npy", "labels": "/m/015p6,/m/09x0r,/m/0h0rv", "caption": "Pigeons peck, coo, and flap their wings before a man speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y1N_DtRpdAp8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1N_DtRpdAp8.npy", "labels": "/m/01jwx6", "caption": "A sound of vibrating motor" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/Ytpm5IOD5d4o.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ytpm5IOD5d4o.npy", "labels": "/m/01w250", "caption": "A woman talking followed by a bird whistling then a woman whistling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part38/Yv7BaYF0kagM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yv7BaYF0kagM.npy", "labels": "/m/07yv9,/m/0k5j,/t/dd00129", "caption": "A muffled helicopter engine operating as paper crinkles in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YrN2rpLV3brs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YrN2rpLV3brs.npy", "labels": "/m/04brg2", "caption": "A man talking as metal clanks repeatedly on a porcelain dish" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YOr7umk40TZA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YOr7umk40TZA.npy", "labels": "/m/01jwx6", "caption": "An engine is idling with vibrating noises" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YQvATUKXYFBs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YQvATUKXYFBs.npy", "labels": "/m/01g50p,/m/0284vy3,/m/06d_3,/m/07jdr,/m/07rwm0c", "caption": "Warning bells ring and a horn blows as a train passes" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YbIiiIo20PsY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YbIiiIo20PsY.npy", "labels": "/m/01h3n,/m/09x0r", "caption": "An adult male speaks while a many insects buzz" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/Yt1hj7se76wQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yt1hj7se76wQ.npy", "labels": "/m/0316dw,/m/07qn4z3,/m/0c2wf", "caption": "Rapid typing and then a ding" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part9/Y8BPTQO_cx7E.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y8BPTQO_cx7E.npy", "labels": "/m/028ght", "caption": "A man talking followed by a crowd laughing and applauding" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4SZ7JXDCNps.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4SZ7JXDCNps.npy", "labels": "/m/07yv9,/m/0k4j,/m/0ltv", "caption": "A car is accelerating" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3n05BjV7r7M.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3n05BjV7r7M.npy", "labels": "/m/02dgv,/m/02y_763", "caption": "A motor is running, and metal clanging is present" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YB-gTt3_rceQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YB-gTt3_rceQ.npy", "labels": "/m/09x0r,/m/0ytgt,/t/dd00125", "caption": "Children speak along with speech from a woman and a man" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YO90Qy2xG6oA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YO90Qy2xG6oA.npy", "labels": "/m/068hy,/m/0jbk,/t/dd00002", "caption": "A bird cawing followed by an infant crying" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YrvDcg9DoNKA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YrvDcg9DoNKA.npy", "labels": "/m/0ngt1", "caption": "A man talking as rain falls and thunder roars in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YTtRtURWVYBE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YTtRtURWVYBE.npy", "labels": "/m/0395lw", "caption": "A series of bell chime and ringing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part9/Y8DLcBdC5UrE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y8DLcBdC5UrE.npy", "labels": "/m/07swgks", "caption": "Muffled static followed by a popping and water dripping as birds chirp and vehicles drive by in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part27/Y_C2HinL8VlM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y_C2HinL8VlM.npy", "labels": "/m/03j1ly,/m/03kmc9,/m/04qvtq", "caption": "Police car siren starts with two horn blasts then becomes a high pitched wail" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YAWGnTI0e2Fs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YAWGnTI0e2Fs.npy", "labels": "/m/09ct_", "caption": "High frequency humming slows down and stops then begins again" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YrgrmLLhxoCQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YrgrmLLhxoCQ.npy", "labels": "/t/dd00112", "caption": "Continuous scraping and scratching against a surface" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YrPkCYq4Zjwk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YrPkCYq4Zjwk.npy", "labels": "/m/02fs_r", "caption": "A synthesized rumble followed by a robotic woman talking alongside electronic beeps followed by a man speaking then another man speaking through an intercom as music plays in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YCfxWJ1Qoufg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YCfxWJ1Qoufg.npy", "labels": "/m/01jt3m,/m/09x0r", "caption": "A man speaking while crinkling paper followed by plastic creaking then a toilet flushing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YBA-lFjpzad4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBA-lFjpzad4.npy", "labels": "/m/012f08,/m/04_sv,/m/07yv9,/m/09x0r,/t/dd00134", "caption": "Vehicle approaching while downshifting and passing by" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YC8kR19NvynA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YC8kR19NvynA.npy", "labels": "/m/02qldy,/m/05zppz,/m/09x0r", "caption": "A man speaks during a monologue" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/Ypgq2KPX5_SA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ypgq2KPX5_SA.npy", "labels": "/t/dd00112", "caption": "Plastic and paper crinkling as cardboard clacks against a hard surface" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YtIM-H2rdq8U.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YtIM-H2rdq8U.npy", "labels": "/m/032s66", "caption": "Gunshots firing before and after a person loudly exhaling followed by a revolver chamber spinning as a heart beats and footsteps walking on a stone surface" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YBvw2gv1fcZw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBvw2gv1fcZw.npy", "labels": "/m/03q5_w,/m/09x0r", "caption": "A loud burping followed by a laughing from young girls" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YlYhwCRX2wNc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YlYhwCRX2wNc.npy", "labels": "/m/04brg2,/m/09x0r", "caption": "Plates rattling and clanking as a woman talks and a faucet pours water" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part19/YMdlEswBfZMQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YMdlEswBfZMQ.npy", "labels": "/m/07rgt08,/m/09x0r,/m/0ytgt,/t/dd00125", "caption": "People are laughing followed by a kid speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part19/YMBP4RcnwGZw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YMBP4RcnwGZw.npy", "labels": "/m/02zsn,/m/07qfr4h,/m/09x0r", "caption": "A woman speaks while a crowd talks and chuckles" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/YpPLisQ_QXxw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YpPLisQ_QXxw.npy", "labels": "/m/07yv9,/m/0912c9,/m/0k4j", "caption": "Honking of a high pitched horn with vibrations of passing traffic" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part7/Y5ye0X5saadg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y5ye0X5saadg.npy", "labels": "/m/09ct_,/m/09x0r", "caption": "Beep then radio voice followed by gunshots and explosion" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4_DjmCg8Ra8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4_DjmCg8Ra8.npy", "labels": "/m/032s66,/m/0_1c", "caption": "Rapid gunfire with male yelling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y1DKLyH3FixM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1DKLyH3FixM.npy", "labels": "/m/015p6,/m/020bb7,/m/07pggtn", "caption": "Nature sounds with birds chirping and singing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part19/YNX0gR9Eebp0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YNX0gR9Eebp0.npy", "labels": "/m/03dnzn,/m/09x0r,/m/0ytgt", "caption": "Water splashing and then a speech." }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/Yb1PXsfgQw5w.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yb1PXsfgQw5w.npy", "labels": "/m/01j3sz,/m/07r660_,/m/09x0r", "caption": "People are giggling, and a man speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part19/YN_s9F4CI_98.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YN_s9F4CI_98.npy", "labels": "/m/015p6,/m/020bb7,/m/07r_25d,/m/0h0rv", "caption": "Bird cooing then the sounds of wings flapping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YWqXFAY4k79s.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YWqXFAY4k79s.npy", "labels": "/m/06mb1,/t/dd00038", "caption": "Rain falling with young female speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y13CBvjHZhOA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y13CBvjHZhOA.npy", "labels": "/m/012f08,/m/07yv9,/m/0k4j,/t/dd00134", "caption": "Car racing by with light click and tapping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YPb6MqpdX5Jw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YPb6MqpdX5Jw.npy", "labels": "/m/0ngt1", "caption": "A horse gallops then trot on grass as gusts of wind blow and thunderclaps in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YWq4OD3olO2w.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YWq4OD3olO2w.npy", "labels": "/m/07r660_,/m/09x0r,/m/0ytgt,/t/dd00125", "caption": "An adult male speaks and an adult female laugh, a group of kids shout and speak, and then an adult female speaks in the foreground while the kids talk" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YXPebkNzsnRI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YXPebkNzsnRI.npy", "labels": "/m/01w250,/m/09x0r", "caption": "Whistling and then laughing with a male speaking in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part4/Y2t82STv2GR8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y2t82STv2GR8.npy", "labels": "/m/0395lw", "caption": "Several church bells ringing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/Ye9MWXS34o48.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ye9MWXS34o48.npy", "labels": "/m/01hsr_", "caption": "A woman breathing heavily followed by two sneezes then nose sniffling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YNi3dIj90Oa4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YNi3dIj90Oa4.npy", "labels": "/m/032s66", "caption": "Several gunshots firing followed by two men talking then music playing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9F3sutgYTvo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9F3sutgYTvo.npy", "labels": "/m/09x0r,/t/dd00002", "caption": "A man speaks followed by a child speaking and crying with adults speaking and laughing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/YdP5DbAzTl5M.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YdP5DbAzTl5M.npy", "labels": "/m/019jd,/m/02rlv9,/m/07yv9,/m/09x0r", "caption": "A motorboat engine running as a man is talking followed by a plastic clank while wind blows into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YPYP-r0nvbFk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YPYP-r0nvbFk.npy", "labels": "/m/07bgp,/m/07q0h5t,/m/09x0r", "caption": "A man yelling while a sheep talks as wind blows into a microphone and a helicopter flies in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part27/Y_duNX6Vyd6g.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y_duNX6Vyd6g.npy", "labels": "/m/019jd,/m/02rlv9,/m/07yv9", "caption": "Wind blows hard and an engine hums loud" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YCxaPpRJRkn0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YCxaPpRJRkn0.npy", "labels": "/m/01d3sd", "caption": "Footsteps walking on a hard surface followed by a person snoring" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/YgwQMkQmBITE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YgwQMkQmBITE.npy", "labels": "/m/083vt,/m/09x0r,/t/dd00125", "caption": "Wood thumping as a man is talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/YwrQDkX0NbTA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YwrQDkX0NbTA.npy", "labels": "/m/019jd,/m/02rlv9,/m/07yv9", "caption": "A boat engine running" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YC_ga5m6nOhI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YC_ga5m6nOhI.npy", "labels": "/m/06hck5,/m/06wzb,/m/07rjwbb", "caption": "Rhythmic metal clacking is ongoing, and a train steam whistle blows and fades" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part38/Yu84FiZ_omhA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yu84FiZ_omhA.npy", "labels": "/m/015p6,/m/07pggtn,/m/0jbk", "caption": "An adult female holds a high musical note and then gags, after which birds chirp" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/Yd1tL-9BILy8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yd1tL-9BILy8.npy", "labels": "/m/015p6,/m/020bb7,/m/07r_25d,/m/0h0rv", "caption": "Birds coo quietly, engine runs in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3kBlVLkN0zo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3kBlVLkN0zo.npy", "labels": "/m/03fwl,/m/09x0r,/m/0ch8v,/m/0jbk", "caption": "A muffled man talking as a goat baas before and after two goats baaing in the distance while wind blows into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YFDwK7T1JO_0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YFDwK7T1JO_0.npy", "labels": "/m/01d380,/m/07k1x,/m/09x0r,/t/dd00125", "caption": "An adult male speaks while two metal clinks occur, then a small drill operates with whirring and slight grinding" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part15/YGkb4f6yodPE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YGkb4f6yodPE.npy", "labels": "/m/01b82r,/m/07pdjhy,/m/083vt", "caption": "Knocking noises followed by a machine sawing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YlJayhiVzl_E.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YlJayhiVzl_E.npy", "labels": "/m/019jd,/m/02rlv9,/m/03m9d0z,/t/dd00092", "caption": "Humming and rumbling of a powerful engine with wind blowing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YtxeXrpoMST4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YtxeXrpoMST4.npy", "labels": "/m/0130jx,/m/02jz0l,/m/03dnzn,/m/0838f", "caption": "Water running and someone gets closer as the water gets louder" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YQOmV7O9mFwg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YQOmV7O9mFwg.npy", "labels": "/m/01bjv,/m/07yv9,/m/09x0r", "caption": "A group of kids talking and laughing as a young girl talks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part27/YZsTZ7jqbd9M.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YZsTZ7jqbd9M.npy", "labels": "/m/01h3n,/m/09x0r", "caption": "A man speaking and birds chirping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YlfO471Rn61k.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YlfO471Rn61k.npy", "labels": "/m/06wzb,/m/07rjwbb", "caption": "Humming and hissing with some mechanical ringing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/YzIgGMlZENTs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YzIgGMlZENTs.npy", "labels": "/m/07qdb04,/m/09ddx,/m/09x0r", "caption": "A duck quacking followed by a man speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YPVvi2SDOjVc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YPVvi2SDOjVc.npy", "labels": "/m/07yv9,/m/0912c9,/m/0k4j,/t/dd00128", "caption": "A car engine idles and then the horn blows" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YkVYNXZd0MMY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YkVYNXZd0MMY.npy", "labels": "/m/01jwx6,/m/02mk9,/m/07yv9,/m/0k4j", "caption": "A vibrating car engine idles" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YK2kIOBeCfuo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YK2kIOBeCfuo.npy", "labels": "/m/028ght,/m/09x0r", "caption": "A man speaking on a microphone followed by a crowd of people laughing then applauding" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/Yos_2U4xqTqw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yos_2U4xqTqw.npy", "labels": "/m/014zdl,/m/07qsvvw,/m/07s2xch", "caption": "An explosion and then gunfire and a speech followed by another explosion" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/YeNG6fEiAE8c.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YeNG6fEiAE8c.npy", "labels": "/m/07bgp,/m/07q0h5t,/m/09x0r", "caption": "Man talks while sheep bleats followed by another man laughing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part19/YMjSegUnQXr4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YMjSegUnQXr4.npy", "labels": "/m/015p6,/m/0h0rv,/t/dd00125", "caption": "Bird tweeting then flapping wings" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YC5kmOK_l4jc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YC5kmOK_l4jc.npy", "labels": "/m/09x0r,/m/0ytgt,/t/dd00001", "caption": "A young girl talking while an infant laughs" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/Yq4YFJA5pFXc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yq4YFJA5pFXc.npy", "labels": "/m/09ct_,/t/dd00129", "caption": "Plastic clicking and camera muffling followed by a toy helicopter motor starting up" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YtxeXrpoMST4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YtxeXrpoMST4.npy", "labels": "/m/0130jx,/m/02jz0l,/m/03dnzn,/m/0838f", "caption": "Water running then growing louder" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YSNIaYhri76w.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YSNIaYhri76w.npy", "labels": "/m/05tny_,/m/07rc7d9,/m/09x0r,/m/0bt9lr,/m/0ghcn6,/m/0jbk,/t/dd00129", "caption": "Squealing from a pig with dogs barking and a man speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YHVz-FJBf_iM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YHVz-FJBf_iM.npy", "labels": "/m/01jt3m,/m/0838f", "caption": "Water gurgling in a drain while a man talks followed by a toilet flushing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3kBlVLkN0zo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3kBlVLkN0zo.npy", "labels": "/m/03fwl,/m/09x0r,/m/0ch8v,/m/0jbk", "caption": "Wind blows and people speak before goats bleat near and far with distant birds chirping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y1OyEgzXCkYE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1OyEgzXCkYE.npy", "labels": "/m/02qldy,/m/05zppz,/m/09x0r", "caption": "An adult male gives a speech" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part7/Y6BJ455B1aAs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y6BJ455B1aAs.npy", "labels": "/m/014zdl,/m/07qsvvw", "caption": "Whistling and an explosion" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part9/Y86dNVnTwH6U.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y86dNVnTwH6U.npy", "labels": "/m/09x0r,/m/0llzx", "caption": "A sewing machine clicks and then is used rapidly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part0/Y-aYumc8KoXg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y-aYumc8KoXg.npy", "labels": "/m/07yv9,/m/0912c9,/m/0k4j", "caption": "The sound of horn from a car approaching from a distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/YhxbmDeNSO6Q.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YhxbmDeNSO6Q.npy", "labels": "/m/09x0r,/m/0llzx", "caption": "A sewing machine lightly operating as a man speaks before plastic clicking followed by a man speaking again" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YJp64Whpr3BA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YJp64Whpr3BA.npy", "labels": "/m/0llzx", "caption": "An engine buzzing together with rustling and followed by brief sewing machine noise" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3fomsZXG3aM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3fomsZXG3aM.npy", "labels": "/m/07q2z82,/m/07yv9,/t/dd00066", "caption": "An idle vehicle engine running followed by a gear cranking then revving" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YrtgVoZCcBw8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YrtgVoZCcBw8.npy", "labels": "/m/03fwl,/m/09x0r,/m/0jbk", "caption": "A cat meowing followed by a goat screaming while a crowd of people talk in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/Yzq00Oe1ecpE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yzq00Oe1ecpE.npy", "labels": "/m/012f08,/m/01bjv,/m/07yv9", "caption": "A bus engine slowing down then accelerating" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part24/YVOXl8iR-HnI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YVOXl8iR-HnI.npy", "labels": "/m/014yck,/m/07yv9,/m/09x0r,/m/0cmf2,/m/0k5j", "caption": "A man talking as gusts of wind blow followed by an aircraft flying by" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/YeNG6fEiAE8c.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YeNG6fEiAE8c.npy", "labels": "/m/07bgp,/m/07q0h5t,/m/09x0r", "caption": "Loud laughter followed by a brief baa rustling and male speech" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YHUwXtfYRFwk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YHUwXtfYRFwk.npy", "labels": "/m/012f08,/m/01bjv,/m/07yv9,/m/0k4j", "caption": "Loud hums and rumblings from passing vehicles" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4pf-PIymDhU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4pf-PIymDhU.npy", "labels": "/m/01d380,/m/07k1x,/m/0_ksk", "caption": "A jackhammer operating then slowing down before operating at a normal rate again" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YsJrFyjfrL-g.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YsJrFyjfrL-g.npy", "labels": "/m/0llzx", "caption": "A sewing machine operating during several metal clacks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YCvNAwby6Xos.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YCvNAwby6Xos.npy", "labels": "/m/09x0r,/m/0llzx,/t/dd00125", "caption": "A sewing machine operating several times as a man is speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4_Cak7gvly4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4_Cak7gvly4.npy", "labels": "/m/07rqsjt", "caption": "Drums play as swooshing occurs" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y1j5NMuq1X30.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1j5NMuq1X30.npy", "labels": "/m/07qlf79", "caption": "Loud humming followed by hissing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/YdJYO3RbBabE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YdJYO3RbBabE.npy", "labels": "/m/02fs_r", "caption": "An electronic beep followed by a man talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part38/YvEWmHtiznF8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YvEWmHtiznF8.npy", "labels": "/m/012f08,/m/01bjv,/m/07yv9,/m/09x0r", "caption": "An adult male is speaking while a large motor vehicle engine is idling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YIPfaRF76gVU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YIPfaRF76gVU.npy", "labels": "/m/012ndj,/m/03j1ly,/m/07r04,/m/07yv9,/m/09x0r", "caption": "Emergency vehicle racing by with siren and a man yelling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YriM7b5bJ9KQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YriM7b5bJ9KQ.npy", "labels": "/m/01j3sz,/m/09x0r", "caption": "A bell clanking as a couple of men laugh then a man speaks in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part27/YaMhu5eMQAsI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YaMhu5eMQAsI.npy", "labels": "/m/07yv9,/m/0k5j,/t/dd00129", "caption": "An aircraft engine running" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YPuLuZ_TXv-0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YPuLuZ_TXv-0.npy", "labels": "/m/0316dw,/m/0c2wf", "caption": "Typing on a typewriter" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YHqnSyliKTKA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YHqnSyliKTKA.npy", "labels": "/m/03k3r,/m/07q5rw0,/m/07rv9rh,/m/09x0r,/m/0jbk", "caption": "A woman talking as a crowd of people talk in the background while a lawn mower engine runs followed by a horse neighing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/YdZDgJzGtLLU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YdZDgJzGtLLU.npy", "labels": "/m/07pqc89", "caption": "A stream of water trickling followed by dirt and gravel shuffling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/YhpDltmawxIM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YhpDltmawxIM.npy", "labels": "/m/0130jx,/m/02jz0l,/m/0838f", "caption": "A faucet pouring water as water splashes against a metal surface and water fills a container" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/Yazh_-OkQ-uI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yazh_-OkQ-uI.npy", "labels": "/m/07bgp,/m/07q0h5t,/m/09x0r", "caption": "A woman talking as goats are baaing followed by footsteps on gravel then a man talking while an airplane flies in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y0ury8KHQdL4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y0ury8KHQdL4.npy", "labels": "/m/01m2v,/m/0316dw,/m/09x0r", "caption": "A man is speaking while typing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YBLMWD6fxhpo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBLMWD6fxhpo.npy", "labels": "/t/dd00018", "caption": "Footsteps are followed by oinking and then a squeal" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part24/YUV1kdjwpy6U.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YUV1kdjwpy6U.npy", "labels": "/m/01jwx6,/m/09x0r", "caption": "A vehicle engine running then powering down followed by a man talking in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YIhvXtS9-IxM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YIhvXtS9-IxM.npy", "labels": "/m/07yv9,/m/09ct_", "caption": "Helicopter engine running" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/Yrp3CQsWxVgE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yrp3CQsWxVgE.npy", "labels": "/m/07yv9,/m/0912c9,/m/0k4j,/t/dd00128", "caption": "A musical horn" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y1Uh74_rZ72k.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1Uh74_rZ72k.npy", "labels": "/m/07swgks", "caption": "Metal shuffling followed by plastic clicking as wind blows into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YKSHpYhuTotY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YKSHpYhuTotY.npy", "labels": "/m/01h3n,/m/03vt0,/m/0h2mp", "caption": "A man talking as metal clanks together followed by footsteps on grass as insects buzz in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YLCwSUVuTyvg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YLCwSUVuTyvg.npy", "labels": "/m/02dgv", "caption": "Glass doors slamming and sliding shut" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part38/YvruDH_YLaPI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YvruDH_YLaPI.npy", "labels": "/m/032s66", "caption": "A gun is fired few times followed by magazine clinking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part27/Y_AcJVyToQUQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y_AcJVyToQUQ.npy", "labels": "/m/01j3sz,/m/09x0r", "caption": "A child and a woman laughing followed by a woman talking then a man shouting" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YlTfNLKEy1RU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YlTfNLKEy1RU.npy", "labels": "/m/01d3sd,/m/0bt9lr,/m/0jbk", "caption": "Faint snoring and gurgling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YLVvS3s9dFKw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YLVvS3s9dFKw.npy", "labels": "/m/0130jx,/m/02jz0l,/m/0838f", "caption": "A man speaking while water is spraying into a sink and draining" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part1/Y0_ogYGDGDco.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y0_ogYGDGDco.npy", "labels": "/m/019jd,/m/034srq,/m/03m9d0z,/m/056ks2,/m/05kq4,/t/dd00092", "caption": "Water splashing and trickling as wind blows into a microphone while a man speaks over a radio" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part27/YaMhu5eMQAsI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YaMhu5eMQAsI.npy", "labels": "/m/07yv9,/m/0k5j,/t/dd00129", "caption": "An aircraft engine is running smoothly and consistently" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y2EsxcKe1A4w.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y2EsxcKe1A4w.npy", "labels": "/m/068hy,/m/07rc7d9,/m/09x0r,/m/0bt9lr,/m/0jbk", "caption": "A dog barks with distant birds chirping then people speak" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part7/Y5rh5-MCjqq8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y5rh5-MCjqq8.npy", "labels": "/m/01d3sd", "caption": "A person snoring with repeated soft tapping on a wooden surface in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YFL8KTgMGrN4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YFL8KTgMGrN4.npy", "labels": "/m/06wzb,/m/07rjwbb", "caption": "Escaping steam is hissing, while a tool motor runs and suction is present" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YDzKjogSVOLM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YDzKjogSVOLM.npy", "labels": "/m/07qdb04,/m/09ddx,/m/09x0r,/m/0jbk", "caption": "A duck quacks while a rooster crows and a crowd chatters followed by a girl laughing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part15/YGIOApFAWDOc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YGIOApFAWDOc.npy", "labels": "/m/015p6,/m/020bb7,/m/07pggtn", "caption": "Birds chirping and tweeting" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part4/Y35b9BSmN5JM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y35b9BSmN5JM.npy", "labels": "/m/07q2z82,/m/07yv9,/m/0k4j", "caption": "A wooden thud as an idle car engine runs then accelerates" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YAJtNitYMa1I.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YAJtNitYMa1I.npy", "labels": "/m/07p9k1k,/m/0dxrf", "caption": "Frying food is sizzling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y5G6b_QWL3nY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y5G6b_QWL3nY.npy", "labels": "/m/07p9k1k,/m/0dxrf", "caption": "A woman speaks as food sizzles in a pan" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part1/Y-oy0BkpMGAk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y-oy0BkpMGAk.npy", "labels": "/m/012f08,/m/07rknqz,/m/07yv9,/m/0k4j,/t/dd00134", "caption": "An engine revving and then tires squealing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/Yoklu5ZJD_2U.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yoklu5ZJD_2U.npy", "labels": "/m/015p6,/m/068hy,/m/07pggtn", "caption": "Plastic crackling as a bird is singing and chirping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/YinQOrxc_oZo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YinQOrxc_oZo.npy", "labels": "/t/dd00018", "caption": "A person making noises and screaming" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YECw5Yf7QoMo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YECw5Yf7QoMo.npy", "labels": "/m/02qldy,/m/05zppz,/m/09x0r", "caption": "A man speaking in the background as another man speaks in the foreground followed by a crowd of people applauding" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4abZbau8tZo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4abZbau8tZo.npy", "labels": "/m/07swgks,/m/09x0r", "caption": "An engine idling and ticking with distant traffic and a man speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YK_Vre_-4KqU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YK_Vre_-4KqU.npy", "labels": "/m/07yv9,/m/0k5j,/t/dd00129", "caption": "An aircraft engine runs and vibrates, metal spinning and grinding occur, and the engine accelerates and fades into the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/YpuZL08fzpXk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YpuZL08fzpXk.npy", "labels": "/m/032s66,/m/04zjc", "caption": "Men speak with gunshots and booms" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/Yx5AH2gW_8S4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yx5AH2gW_8S4.npy", "labels": "/m/0h0rv,/m/0jbk,/t/dd00125", "caption": "Pigeons are cooing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/YpCQEWAFGEjc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YpCQEWAFGEjc.npy", "labels": "/m/06wzb,/m/07rjwbb", "caption": "A steam engine running on railroad tracks as steam hisses and a crowd of people talk in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YZNEZLlDVgrE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YZNEZLlDVgrE.npy", "labels": "/m/01h3n,/m/03vt0,/m/0h2mp", "caption": "A man talking as insects buzz by" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3IguMJkqpl4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3IguMJkqpl4.npy", "labels": "/m/07qdb04,/m/09ddx,/m/09x0r", "caption": "A man and a woman talking as an infant cries while a duck quacks in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/Yn74IYuCe_ms.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yn74IYuCe_ms.npy", "labels": "/m/09x0r,/m/0j6m2", "caption": "A stream of water rushing and trickling followed by a young man whooshing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YK03ydb1uaoQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YK03ydb1uaoQ.npy", "labels": "/m/01d3sd,/t/dd00125", "caption": "A person snoring" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part15/YGMP8m09j5vk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YGMP8m09j5vk.npy", "labels": "/m/015p6,/m/020bb7,/m/07pggtn", "caption": "Birds chirp with a low whirring background noise" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4fz0-Kx2oNs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4fz0-Kx2oNs.npy", "labels": "/m/0dxrf", "caption": "Sizzling of food frying" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part24/YVZLZ08k3YeA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YVZLZ08k3YeA.npy", "labels": "/m/01d3sd,/m/09x0r", "caption": "A man talking as a man is snoring" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YJTHMXLC9YRs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YJTHMXLC9YRs.npy", "labels": "/m/09ddx,/m/0jbk", "caption": "Ducks quack with distant passing traffic" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YnD1K1Zo0qrM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YnD1K1Zo0qrM.npy", "labels": "/m/032s66,/m/04zjc", "caption": "Loud clicks with gusting wind and several rapid fire gunshots" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/YpWQeV08kYR0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YpWQeV08kYR0.npy", "labels": "/m/012n7d,/m/03j1ly,/m/03kmc9,/m/07yv9,/t/dd00128", "caption": "An emergency siren wailing as a truck drives by" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/YhDMHIDJdfDA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YhDMHIDJdfDA.npy", "labels": "/m/01d3sd,/t/dd00125", "caption": "Snoring occurs in a rhythmic pattern" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/Yjlwe9jtu5Gw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yjlwe9jtu5Gw.npy", "labels": "/m/01w250", "caption": "While an electronic device plays in the background, two wolf whistles occur followed by metal thumping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YTtRtURWVYBE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YTtRtURWVYBE.npy", "labels": "/m/0395lw", "caption": "Bells chiming as a clock is ticking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YQv1HXaT-28U.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YQv1HXaT-28U.npy", "labels": "/m/07qsvvw", "caption": "Liquid splashing and dripping as a kid laughs" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/YinQOrxc_oZo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YinQOrxc_oZo.npy", "labels": "/t/dd00018", "caption": "A pig oinking followed by a man screaming" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YC4JwGJQ2dUA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YC4JwGJQ2dUA.npy", "labels": "/m/02qldy,/m/05zppz,/m/09x0r,/m/0brhx", "caption": "Man yelling in anger" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/YfWvWhLJ5Fow.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YfWvWhLJ5Fow.npy", "labels": "/m/07qlf79", "caption": "Running footsteps followed by spraying noise" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9F3sutgYTvo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9F3sutgYTvo.npy", "labels": "/m/09x0r,/t/dd00002", "caption": "A man is speaking and a baby whimpers followed by a woman talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YBzHTqyX69pI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBzHTqyX69pI.npy", "labels": "/m/07pdjhy,/m/083vt", "caption": "Rustling with scraping as pigeons coo" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part7/Y5iTRKJqUIw8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y5iTRKJqUIw8.npy", "labels": "/m/07qjznl,/m/09x0r", "caption": "Various conversation occur in a crowd. A train bell dings followed by a train whistle, cheering occurs at the end" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9XqkKuTqEOM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9XqkKuTqEOM.npy", "labels": "/m/02dgv", "caption": "Rustling and some knocks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YljrL7Cb-jr8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YljrL7Cb-jr8.npy", "labels": "/m/07qlf79", "caption": "A sprayer is emitting liquids with a loud whooshing noise" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y1Uh74_rZ72k.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1Uh74_rZ72k.npy", "labels": "/m/07swgks", "caption": "Wind is blowing and water gurgles" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YJon_DEFqsfM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YJon_DEFqsfM.npy", "labels": "/m/020bb7,/m/06_y0by,/m/09ddx", "caption": "Wind blowing with ducks quacking and birds chirping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YOMGHnJV0l2U.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YOMGHnJV0l2U.npy", "labels": "/m/02p01q,/m/07pdjhy,/m/083vt", "caption": "Rapid filing and scraping of wood occurs, followed by brushing and a thump" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YrBUCIK8JRLg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YrBUCIK8JRLg.npy", "labels": "/m/034srq,/m/03m9d0z,/m/05kq4,/t/dd00092", "caption": "Muffled water splashing and ocean waves crashing during plastic camera muffling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YTSnq6n8tElo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YTSnq6n8tElo.npy", "labels": "/m/0242l,/m/04brg2", "caption": "A tapping noise followed by a child speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YPO8Nu3F8mkA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YPO8Nu3F8mkA.npy", "labels": "/m/014zdl,/m/07qsvvw", "caption": "A gunshot firing in the distance followed by steam hissing and fire crackling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/Ypaf0nyjg1Js.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ypaf0nyjg1Js.npy", "labels": "/m/0dxrf", "caption": "A woman talking followed by a plate rattling as food and oil sizzle" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YBL8ksJ0sTXk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBL8ksJ0sTXk.npy", "labels": "/m/01jwx6,/m/07pb8fc,/m/07yv9,/m/09x0r,/m/0k4j", "caption": "An engine is idling followed by a male speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/YemGPabOePzA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YemGPabOePzA.npy", "labels": "/m/03q5_w,/m/09x0r", "caption": "Two people are speaking and laughing, and their voices are distorted by slowing down the audio" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/Yh3UhoHIMfpw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yh3UhoHIMfpw.npy", "labels": "/m/02_41,/m/03m9d0z,/t/dd00092", "caption": "Wind blowing and an engine humming" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YPTyFYxXdut4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YPTyFYxXdut4.npy", "labels": "/m/07pqc89,/m/0838f,/m/09x0r", "caption": "A woman speaks as water splashes" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part27/Y_oKXrY5Ff0g.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y_oKXrY5Ff0g.npy", "labels": "/m/01j3sz,/m/09x0r", "caption": "A woman talking followed by a group of people laughing as plastic crinkles" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YJBWJQCS4SvA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YJBWJQCS4SvA.npy", "labels": "/m/034srq,/m/03m9d0z,/m/05kq4,/t/dd00092", "caption": "Wind blowing heavily into a microphone as seagulls squawk and ocean waves crash in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YKOBkbROPv4c.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YKOBkbROPv4c.npy", "labels": "/m/07rknqz,/m/07yv9,/m/0h9mv,/m/0ltv", "caption": "Humming of an engine with squealing tires" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part4/Y32565FEuksc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y32565FEuksc.npy", "labels": "/m/02qldy,/m/02zsn,/m/09x0r", "caption": "A woman gives a speech followed by applause" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YI_vN_BFUr0Y.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YI_vN_BFUr0Y.npy", "labels": "/m/01g50p,/m/0284vy3,/m/04zmvq,/m/06d_3,/m/07jdr,/m/07yv9", "caption": "A train horn blows several times as railroad warning signals ring in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/YwBs02amFGXs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YwBs02amFGXs.npy", "labels": "/m/015p6,/m/0h0rv,/t/dd00125,/t/dd00129", "caption": "Pigeons coo and a distant rooster crows" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/YwVi5w_NU6CM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YwVi5w_NU6CM.npy", "labels": "/m/012f08,/m/012ndj,/m/03j1ly,/m/03kmc9,/m/07r04,/m/07yv9", "caption": "Emergency sirens wail as a truck engine accelerates and drives by" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YIvfaKPDWC00.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YIvfaKPDWC00.npy", "labels": "/m/012f08,/m/012ndj,/m/03j1ly,/m/03kmc9,/m/07yv9", "caption": "A siren ringing with a vehicle speeding closer" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part1/Y0a9wVat2PWk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y0a9wVat2PWk.npy", "labels": "/m/0284vy3,/m/07jdr,/m/07yv9", "caption": "A train horn blowing as a train runs on railroad tracks while a man talks quietly in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y7WkB6pflr6o.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y7WkB6pflr6o.npy", "labels": "/m/02qldy,/m/02zsn,/m/09x0r", "caption": "A woman speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YrE6BJ0Bo4w4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YrE6BJ0Bo4w4.npy", "labels": "/m/02jz0l,/m/09x0r,/t/dd00125", "caption": "A woman talking before and after a water faucet pouring followed by clapping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YbA5zPFSFZAA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YbA5zPFSFZAA.npy", "labels": "/m/07rqsjt", "caption": "Digital beeps followed by static electric hissing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part9/Y8F-ndyrEWJ8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y8F-ndyrEWJ8.npy", "labels": "/m/012n7d,/m/03j1ly,/m/03kmc9", "caption": "Race cars speed on the road, and a man talks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YBa92IrXFvJo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBa92IrXFvJo.npy", "labels": "/m/019jd,/m/02rlv9,/m/07yv9", "caption": "Humming and rattling of an engine idling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part15/YFhimNYClv40.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YFhimNYClv40.npy", "labels": "/m/012ndj,/m/03j1ly,/m/03kmc9", "caption": "Emergency horns go off as a truck accelerates and drives by" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YKtinboYbmHQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YKtinboYbmHQ.npy", "labels": "/m/07rknqz,/m/07yv9,/m/0h9mv,/m/0k4j", "caption": "A motor vehicle speeds and skids the tires" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YIFRmbxWK8u0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YIFRmbxWK8u0.npy", "labels": "/m/07qjznl", "caption": "A clock ticking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/Yi2yhbckq3p0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yi2yhbckq3p0.npy", "labels": "/m/012f08,/m/04_sv,/m/07yv9,/m/0k4j", "caption": "A motorbike engine running while a series of vehicle horns sound and a car alarm goes off in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YkHIe4CfaccQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YkHIe4CfaccQ.npy", "labels": "/m/03fwl,/m/068hy,/m/0ch8v,/m/0jbk", "caption": "A goat bleats several times" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YAizmnCDlXos.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YAizmnCDlXos.npy", "labels": "/m/07qjznl,/m/07qjznt", "caption": "A bell chiming as a clock is ticking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YlTJLvSvjUZk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YlTJLvSvjUZk.npy", "labels": "/m/01w250", "caption": "Instrumental music playing as a person whistles" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YlfAFQ0-wDJU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YlfAFQ0-wDJU.npy", "labels": "/m/034srq,/m/03m9d0z", "caption": "Ocean waves crashing as wind blows into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YPMMkPq5jJXY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YPMMkPq5jJXY.npy", "labels": "/m/03q5_w,/m/09x0r", "caption": "A person burps while people laugh" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y2JV3emH50XU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y2JV3emH50XU.npy", "labels": "/m/07yv9,/m/0k4j,/m/0ltv", "caption": "A car is passing by with leaves rustling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YmlnUJH4BQnk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YmlnUJH4BQnk.npy", "labels": "/m/07pdjhy", "caption": "A woman speaks with some light sanding" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/YinSvboaSRwA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YinSvboaSRwA.npy", "labels": "/m/07k1x,/m/083vt,/m/09x0r", "caption": "Continuous buzzing and clanking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part0/Y-NsC63dA01g.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y-NsC63dA01g.npy", "labels": "/m/01yrx,/m/068hy,/m/07qrkrw,/m/09x0r,/m/0jbk", "caption": "A woman speaks and a cat meows" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/Ytpm5IOD5d4o.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ytpm5IOD5d4o.npy", "labels": "/m/01w250", "caption": "An adult female speaks and claps, a bird whistles in the foreground, another bird chirps in the background, and then a human whistles a tune" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YS0YE96w0YRk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YS0YE96w0YRk.npy", "labels": "/m/028ght", "caption": "An adult male speaks and then an audience laughs and claps somewhat, followed by the adult male speaking again and then the audience laughing and clapping harder" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3wV3ST-c4PE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3wV3ST-c4PE.npy", "labels": "/m/07qjznl", "caption": "Ticking is ongoing, and slight rustling occurs" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YNwoBDrTlbTI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YNwoBDrTlbTI.npy", "labels": "/t/dd00018", "caption": "A series of high pitched squeals occur" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YC4JwGJQ2dUA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YC4JwGJQ2dUA.npy", "labels": "/m/02qldy,/m/05zppz,/m/09x0r,/m/0brhx", "caption": "A man delivering a speech" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part9/Y8b9z7N25DmU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y8b9z7N25DmU.npy", "labels": "/m/01bjv,/m/07yv9,/m/09x0r,/t/dd00129", "caption": "A vehicle comes to a stop, air brakes release, and someone speaks in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/Yq3SEOW2m4WY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yq3SEOW2m4WY.npy", "labels": "/m/01g50p,/m/0284vy3,/m/06d_3,/m/07jdr,/m/07rwm0c", "caption": "An idle vehicle engine running and a bird chirping in the distance followed by a train horn honking then a train on railroad tracks moving" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/Yr2djvq1vc68.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yr2djvq1vc68.npy", "labels": "/m/0130jx,/m/02jz0l,/m/0838f", "caption": "Water is running followed by a gurgling sound." }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part15/YH-vTZh81qAU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YH-vTZh81qAU.npy", "labels": "/m/01jwx6", "caption": "Humming and a rattle" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YRtenf2XSXRc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YRtenf2XSXRc.npy", "labels": "/m/07q2z82,/m/07yv9,/m/0k4j", "caption": "A vehicle engine is idling and rooms" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/YilspW7JRjAg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YilspW7JRjAg.npy", "labels": "/m/012f08,/m/02mk9,/m/07yv9,/m/0k4j", "caption": "A motor vehicle engine is revving" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YlHh0SwUhP8U.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YlHh0SwUhP8U.npy", "labels": "/m/09ddx", "caption": "Ducks squeaking in the distance followed by a shotgun blast" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part4/Y2UNuMbxz9ds.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y2UNuMbxz9ds.npy", "labels": "/m/012f08,/m/07yv9,/m/0k4j,/t/dd00134", "caption": "A vehicle engine revving then accelerating at a high rate as a metal surface is whipped followed by tires skidding" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/Yfx4r_KuW6No.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yfx4r_KuW6No.npy", "labels": "/m/09x0r,/m/0ytgt,/t/dd00126", "caption": "Adult female is speaking and a young child is crying" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/YdYZSKX7vuRI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YdYZSKX7vuRI.npy", "labels": "/m/01d3sd,/m/09x0r", "caption": "Snoring and then a speech" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/Yek9Fsmm3xqk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yek9Fsmm3xqk.npy", "labels": "/m/019jd,/m/03m9d0z,/m/056ks2,/m/07yv9", "caption": "Some rowing sounds in water with light wind" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YQ87LBiwJjTE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YQ87LBiwJjTE.npy", "labels": "/m/07p9k1k,/m/0dxrf", "caption": "Wood stirring in a pot followed by a wooden object falling as a woman is talking as food is sizzling and light guitar music is playing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YBGEMgl1xjac.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBGEMgl1xjac.npy", "labels": "/m/03vt0,/m/06hps,/m/09xqv", "caption": "Insects and birds vocalizing together" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/YfWvWhLJ5Fow.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YfWvWhLJ5Fow.npy", "labels": "/m/07qlf79", "caption": "Footsteps running on dirt followed by compressed air spraying as wind blows in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part19/YMBP4RcnwGZw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YMBP4RcnwGZw.npy", "labels": "/m/02zsn,/m/07qfr4h,/m/09x0r", "caption": "An adult female speaks, an adult male speaks, and a crowd of people laugh and talk in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YtaYKM1OSTwE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YtaYKM1OSTwE.npy", "labels": "/m/03fwl,/m/07bgp,/m/0ch8v,/m/0jbk", "caption": "Sheep baaing as leaves rustle followed by a person giggling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4lv9aLXtud0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4lv9aLXtud0.npy", "labels": "/m/03q5_w,/m/09x0r,/t/dd00125", "caption": "Man yelling and belching" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YF7QtqKtllK0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YF7QtqKtllK0.npy", "labels": "/m/01d3sd", "caption": "Snoring is occurring, and an electronic entertainment device is playing in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/Yg6CY7qvu81k.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yg6CY7qvu81k.npy", "labels": "/m/07p9k1k", "caption": "Music plays followed by a man speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YAR8-MVl_Mf8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YAR8-MVl_Mf8.npy", "labels": "/m/02dgv,/m/07rjzl8,/m/09x0r", "caption": "A man screaming followed by a door slamming shut then a series of cardboard thumping and metal bars clacking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part4/Y2a6GNu6uCDE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y2a6GNu6uCDE.npy", "labels": "/m/02qldy,/m/02zsn,/m/09x0r", "caption": "A woman is speaking over a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YZ1Cyj4N05lk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YZ1Cyj4N05lk.npy", "labels": "/m/01w250", "caption": "Whistling with small rustling and groaning" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YPLHXGDnig4M.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YPLHXGDnig4M.npy", "labels": "/m/01yrx,/m/07qrkrw", "caption": "A man talks like a cat before growling then meowing and finally hissing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/Yc0IggDOisOo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yc0IggDOisOo.npy", "labels": "/m/0395lw,/m/09x0r", "caption": "Ringing of a bell with people speaking in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YbIV3bJZpkgA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YbIV3bJZpkgA.npy", "labels": "/m/07yv9,/m/09ct_", "caption": "A muffled helicopter engine flying" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/YynHdcJ9Oqaw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YynHdcJ9Oqaw.npy", "labels": "/m/07rqsjt", "caption": "Several loud whooshes" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/YA2mcp0N__7U.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YA2mcp0N__7U.npy", "labels": "/m/07qlf79,/m/09x0r", "caption": "Hissing with people speaking and some sneezes" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YajheseWZmmU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YajheseWZmmU.npy", "labels": "/m/01yrx,/m/07qrkrw,/m/0jbk", "caption": "A cat meowing as a man giggles" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/YzF3xXn6NTyU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YzF3xXn6NTyU.npy", "labels": "/m/0j6m2", "caption": "A woman talking followed by someone coughs then another woman talking as a stream of water flows and trickles" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part24/YUXGzbBGbqAA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YUXGzbBGbqAA.npy", "labels": "/m/07ryjzk,/m/0dxrf", "caption": "Footsteps shuffling while a person heavily breathes with a series of cloth slapping against a hard surface" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part1/Y0UJtGcoPYa0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y0UJtGcoPYa0.npy", "labels": "/m/07jdr,/m/07yv9,/m/0912c9,/t/dd00128", "caption": "A vehicle motor running idle followed by a car horn honking then a group of men groaning" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part38/YvfNKduToki4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YvfNKduToki4.npy", "labels": "/m/07r04,/m/07yv9,/m/09x0r", "caption": "Beeping with men speaking faintly in the distance with an air release" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/YyfYNPWs7mWY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YyfYNPWs7mWY.npy", "labels": "/m/02dgv,/m/05zppz,/m/09x0r", "caption": "A man speaking, followed by a door shutting, and then the man speaks some more" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YajheseWZmmU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YajheseWZmmU.npy", "labels": "/m/01yrx,/m/07qrkrw,/m/0jbk", "caption": "A cat meowing a few times" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YKVbmN9ZRg5Q.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YKVbmN9ZRg5Q.npy", "labels": "/m/01g50p,/m/0284vy3,/m/06d_3,/m/07jdr,/m/07rwm0c", "caption": "A train running on railroad tracks as a train horn blows and steam hisses" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part15/YGPj8h-WcjWs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YGPj8h-WcjWs.npy", "labels": "/m/01bjv,/m/07yv9,/m/09x0r", "caption": "A bus is idling when a voice from a speaker starts to talk" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3ue0gJM0THk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3ue0gJM0THk.npy", "labels": "/m/02l6bg,/m/02mk9,/m/07pb8fc,/m/07q2z82,/t/dd00066", "caption": "Loud vibrations from a revving engine that increases" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part7/Y5xC4hkAWiao.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y5xC4hkAWiao.npy", "labels": "/m/012f08,/m/02mk9,/m/07yv9", "caption": "Car engine running and then slowly turning off with a loud stuttering noise going off twice with slight pause between" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/YeRU-rABp8nk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YeRU-rABp8nk.npy", "labels": "/m/04_sv,/m/07yv9,/m/09x0r", "caption": "Two adult males speak, while a motorcycle engine idles and people talk in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YU3CAjsm1sec.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YU3CAjsm1sec.npy", "labels": "/m/01yrx,/m/068hy,/m/07qrkrw,/m/0jbk", "caption": "Several cats meowing followed by a man singing in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YTd2EEDdFlRY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YTd2EEDdFlRY.npy", "labels": "/m/07p9k1k", "caption": "A man talking as music plays followed by a guitar strumming as steam hisses in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/YhV4bDCBDCy0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YhV4bDCBDCy0.npy", "labels": "/m/07r04,/m/07yv9,/m/09x0r", "caption": "A truck engine running then accelerating followed by a man talking as wind blows into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YrbO727iF03I.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YrbO727iF03I.npy", "labels": "/m/03q5_w,/m/09x0r", "caption": "Someone belches followed by a group of people laughing and talking then a man talking in the foreground" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YO90Qy2xG6oA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YO90Qy2xG6oA.npy", "labels": "/m/068hy,/m/0jbk,/t/dd00002", "caption": "Crying and screaming with some coughing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YNi3dIj90Oa4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YNi3dIj90Oa4.npy", "labels": "/m/032s66", "caption": "Loud explosions and bangs followed by men speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part24/YUQtBt6CQpwg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YUQtBt6CQpwg.npy", "labels": "/m/09x0r,/m/0llzx", "caption": "A man speaks followed by a sewing machine stitching" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YZY4aGEniU_E.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YZY4aGEniU_E.npy", "labels": "/m/07p9k1k", "caption": "Food and oil sizzling followed by oil popping then steam hissing as a man talks and light music plays in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YKVAIaRPry24.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YKVAIaRPry24.npy", "labels": "/m/01h3n,/m/03vt0,/m/0h2mp", "caption": "An insect buzzing as plastic clacks and plastic slaps a hard surface" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YRrmBGjJqlEo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YRrmBGjJqlEo.npy", "labels": "/m/0316dw", "caption": "Typing on a keyboard with a man speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YnU-AI3Cmc3M.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YnU-AI3Cmc3M.npy", "labels": "/m/015p6,/m/0h0rv,/t/dd00129", "caption": "Birds are cooing and softy cheeping, and wings flap" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YARFFw0e_jig.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YARFFw0e_jig.npy", "labels": "/m/03q5_w", "caption": "Loud burping repeating" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YTdl9SmBbRnA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YTdl9SmBbRnA.npy", "labels": "/m/012f08,/m/01bjv,/m/07yv9,/m/09x0r", "caption": "A man is talking as a motor vehicle engine travels" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/Yj1AiqT5oHZc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yj1AiqT5oHZc.npy", "labels": "/m/02fs_r,/m/09x0r,/t/dd00125", "caption": "An adult male speaks hesitantly, and electronic beeps randomly occur" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YZ_smJ66Tb3c.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YZ_smJ66Tb3c.npy", "labels": "/m/015p6,/m/020bb7,/m/07r_25d,/m/0h0rv", "caption": "A man is speaking with bird sounds in the background followed by a whistling sound" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/YzoxFl3pddMg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YzoxFl3pddMg.npy", "labels": "/m/09ld4", "caption": "A frog chirping as a woman talks over an intercom and water splashes in the background followed by wood falling on a hard surface" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YDc2WEiRk0rA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YDc2WEiRk0rA.npy", "labels": "/m/07qlf79", "caption": "Water spraying on a plastic surface" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YNlKlRKz8OKI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YNlKlRKz8OKI.npy", "labels": "/m/015p6,/m/020bb7,/m/07pggtn", "caption": "A woman speaks with flapping wings and chirping birds" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/YfK4QBQZ6i7w.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YfK4QBQZ6i7w.npy", "labels": "/m/01j3sz,/m/07rgt08,/m/07s04w4", "caption": "Multiple people laughing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YQARuiRtfy-k.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YQARuiRtfy-k.npy", "labels": "/m/01d380", "caption": "Drilling sound with light music in background then a man speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YlVr-PxhZo8s.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YlVr-PxhZo8s.npy", "labels": "/m/07pb8fc,/m/07yv9,/t/dd00126", "caption": "An idle vehicle engine running as wind blows into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/YzwoqJY03yHE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YzwoqJY03yHE.npy", "labels": "/m/03fwl,/m/068hy,/m/09x0r,/m/0jbk", "caption": "Two woman communicating with each other as a goat is baaing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y1_z6NcidGzM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1_z6NcidGzM.npy", "labels": "/m/07swgks,/m/09x0r,/m/0j6m2", "caption": "Splashing water with children speaking and people screaming with a distant blow of a whistle" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YatmDP_fmK_8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YatmDP_fmK_8.npy", "labels": "/m/014zdl,/m/07qsvvw", "caption": "A very low-pitched hum occurs, followed by an explosion" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/Ye6jSpvTvfJ0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ye6jSpvTvfJ0.npy", "labels": "/m/06mb1,/m/0cj0r", "caption": "Rain and light thunder" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/Ygf6H_MWCqjw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ygf6H_MWCqjw.npy", "labels": "/m/015p6,/m/09ddx", "caption": "A duck quacking followed by plastic camera muffling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/YwnqUgK_-fo4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YwnqUgK_-fo4.npy", "labels": "/m/07bgp,/m/09x0r,/m/0jbk", "caption": "Firecrackers popping as a crowd of people cheer and whistle" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YbQNX7vDalQw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YbQNX7vDalQw.npy", "labels": "/m/07p9k1k", "caption": "Whispering followed by loud, consistent sizzling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YUCy1BEx8jBE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YUCy1BEx8jBE.npy", "labels": "/m/0j6m2", "caption": "A man speaks while water splashes" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YPg2cWEnEEvc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YPg2cWEnEEvc.npy", "labels": "/m/03q5_w", "caption": "Rhythmic oinking is followed by repeated short squeaks, then more oinking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YrPkCYq4Zjwk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YrPkCYq4Zjwk.npy", "labels": "/m/02fs_r", "caption": "A whooshing effect followed by a robotic woman speaking and electronic beeps then a man speaking and music playing along with a man speaking through an intercom" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YJfaj4P3us9M.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YJfaj4P3us9M.npy", "labels": "/m/02c8p,/m/07cx4", "caption": "A telephone dialing tone followed by a plastic switch flipping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YZYWCwfCkBp4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YZYWCwfCkBp4.npy", "labels": "/m/01b82r,/m/07pdjhy,/m/083vt", "caption": "Repeated scraping with faint music in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9ZZHvwaH-CU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9ZZHvwaH-CU.npy", "labels": "/m/032s66", "caption": "Rapid gunfire and faint screaming" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YSePTNAN7s-w.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YSePTNAN7s-w.npy", "labels": "/m/01jt3m,/m/0838f", "caption": "A female speaking and then a toilet flushing with multiple females speaking during and after" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YY3lNEe-ZGF0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YY3lNEe-ZGF0.npy", "labels": "/m/07qjznl,/m/07qjznt", "caption": "A clock ticking followed by a some wooden clacking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/YeJCaRgf1M20.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YeJCaRgf1M20.npy", "labels": "/m/07qjznl", "caption": "Bells chiming as birds chirp in the background followed by plastic clanking and shuffling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part0/Y-AheI8Epim4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y-AheI8Epim4.npy", "labels": "/m/07qsvvw,/m/09x0r", "caption": "Muffled sounds followed by metal being hit" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YZY4aGEniU_E.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YZY4aGEniU_E.npy", "labels": "/m/07p9k1k", "caption": "Sizzling and male speech with more sizzling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y7XXSOzDQ2z0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y7XXSOzDQ2z0.npy", "labels": "/m/07yv9,/m/0h9mv,/m/0k4j,/m/0ltv", "caption": "Two vehicle engines running idle before accelerating" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YtmLAXm1WlnE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YtmLAXm1WlnE.npy", "labels": "/m/01h3n,/m/03vt0,/m/0h2mp", "caption": "Speech and insects buzzing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YXamQAY_WXRY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YXamQAY_WXRY.npy", "labels": "/m/0j6m2", "caption": "Water lapping in waves as a man talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y79XDcI6xZm0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y79XDcI6xZm0.npy", "labels": "/m/02qldy,/m/05zppz,/m/09x0r", "caption": "A man speaking on a microphone as a crowd of people chant and clap" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YZ-SIyOChVh8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YZ-SIyOChVh8.npy", "labels": "/m/06mb1,/m/0jb2l,/m/0ngt1", "caption": "Rain and thunder continuously" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/YwSHzVxdMiTo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YwSHzVxdMiTo.npy", "labels": "/m/09x0r,/t/dd00018", "caption": "Plastic camera muffling followed by a man yelling as a pig squeals" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/Yjs4dr5JusdM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yjs4dr5JusdM.npy", "labels": "/m/07cx4,/m/09x0r", "caption": "A woman and a man talking through a telephone speaker" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/Yh0M4RS8p_mo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yh0M4RS8p_mo.npy", "labels": "/m/01j3sz,/m/0463cq4", "caption": "Scary laughter by an adult male occurs, followed by a click and a buzz, and a baby begins crying" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YWCYfCfW9NA0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YWCYfCfW9NA0.npy", "labels": "/m/07yv9,/m/09ct_,/t/dd00129", "caption": "An idle helicopter engine running as birds chirp in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part0/Y-EaZ7EJJUl0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y-EaZ7EJJUl0.npy", "labels": "/m/023pjk,/m/04brg2", "caption": "A man speaks with some clinking and clanking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YPg2cWEnEEvc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YPg2cWEnEEvc.npy", "labels": "/m/03q5_w", "caption": "Burping noises followed by tongue clapping sounds" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/Ypgq2KPX5_SA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ypgq2KPX5_SA.npy", "labels": "/t/dd00112", "caption": "Some crinkling of cellophane" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YCfxWJ1Qoufg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YCfxWJ1Qoufg.npy", "labels": "/m/01jt3m,/m/09x0r", "caption": "A man speaks with some clicking and rattling followed by a flushing toilet" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YZ3wDry8nnJs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YZ3wDry8nnJs.npy", "labels": "/m/09x0r,/m/0ytgt,/t/dd00125", "caption": "Water pouring from a faucet and draining into a pipe while a young girl talks followed by a brush scrubbing then a person spitting" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YBLMWD6fxhpo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBLMWD6fxhpo.npy", "labels": "/t/dd00018", "caption": "A man makes sound followed by oinking sounds" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/YwOFBldBFRNk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YwOFBldBFRNk.npy", "labels": "/m/0395lw", "caption": "Large church bells ring as rain falls on a hard surface and wind blows lightly into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YnLZeG9LaLgw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YnLZeG9LaLgw.npy", "labels": "/m/07yv9,/m/0k4j,/m/0ltv", "caption": "Race car revving its engine" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part9/Y8b9z7N25DmU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y8b9z7N25DmU.npy", "labels": "/m/01bjv,/m/07yv9,/m/09x0r,/t/dd00129", "caption": "A bus engine driving in the distance then nearby followed by compressed air releasing while a woman and a child talk in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/YilspW7JRjAg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YilspW7JRjAg.npy", "labels": "/m/012f08,/m/02mk9,/m/07yv9,/m/0k4j", "caption": "A vehicle engine running and revving several times" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YPMMdAKZxI_I.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YPMMdAKZxI_I.npy", "labels": "/m/03q5_w,/m/09x0r", "caption": "A burping noise followed by laughter and a woman speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YlfO471Rn61k.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YlfO471Rn61k.npy", "labels": "/m/06wzb,/m/07rjwbb", "caption": "Steam escapes with a hissing noise" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y1slvoNgzBLE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1slvoNgzBLE.npy", "labels": "/m/01g50p,/m/06d_3,/m/07jdr,/m/07yv9,/m/0912c9", "caption": "A large motor vehicle engine is running, clacking occurs, and a horn blows" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part27/Y_z-bidQYVao.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y_z-bidQYVao.npy", "labels": "/m/07qjznl,/m/09x0r", "caption": "A man making a horn sound and then speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y2ErfX6ZT5pM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y2ErfX6ZT5pM.npy", "labels": "/m/01jt3m", "caption": "A toilet flushing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y1QNLMF-Kl_s.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1QNLMF-Kl_s.npy", "labels": "/m/02qldy,/m/02zsn,/m/09x0r", "caption": "A woman speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/YwOFBldBFRNk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YwOFBldBFRNk.npy", "labels": "/m/0395lw", "caption": "Church bells ringing as a crowd of people talk in the distance while rain falls alongside wind blowing into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YWWkhzcmx3VE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YWWkhzcmx3VE.npy", "labels": "/m/09ddx", "caption": "L duck quacks in rapid succession" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YAR8-MVl_Mf8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YAR8-MVl_Mf8.npy", "labels": "/m/02dgv,/m/07rjzl8,/m/09x0r", "caption": "A ring followed by a crash then a scream and a man speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part24/YVQnmlf2OsUg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YVQnmlf2OsUg.npy", "labels": "/m/09ct_", "caption": "High pitched vibrations from a small motor" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y7XUt6sQS7nM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y7XUt6sQS7nM.npy", "labels": "/m/07bgp,/m/07q0h5t,/m/09x0r", "caption": "Rustling noises in the background while people talk and animals bleat" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/Ycz0FSQDVBMw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ycz0FSQDVBMw.npy", "labels": "/m/06wzb,/m/07rjwbb", "caption": "Continuous hissing and clanking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/YdlsiellSFf0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YdlsiellSFf0.npy", "labels": "/m/019jd,/m/02rlv9,/m/07yv9", "caption": "High frequency vibrations with faint splashing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/YptIksg9KEac.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YptIksg9KEac.npy", "labels": "/m/068hy,/m/07rc7d9,/m/0bt9lr,/m/0jbk,/t/dd00136", "caption": "A person clapping followed by a dog barking then knocking on a glass surface as birds chirp during outdoor ambiance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/Yt1hj7se76wQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yt1hj7se76wQ.npy", "labels": "/m/0316dw,/m/07qn4z3,/m/0c2wf", "caption": "Loud, continuous tapping on a typewriter" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YS_3aeOvniZc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YS_3aeOvniZc.npy", "labels": "/m/07yv9,/m/0k4j,/m/0ltv", "caption": "Humming of a loud engine accelerating and revving" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YSZ6CcXINiiE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YSZ6CcXINiiE.npy", "labels": "/m/014zdl,/m/07qsvvw,/m/09x0r", "caption": "A man speaks followed by a loud burst then laughter" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/YfBYDJWChe5c.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YfBYDJWChe5c.npy", "labels": "/m/01d3sd", "caption": "A person snoring" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YIJ6pm5Kns8A.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YIJ6pm5Kns8A.npy", "labels": "/m/03q5_w,/m/09x0r", "caption": "A man talking followed by a woman talking while an electronic beep plays with a person claps before someone belches then a man and woman laugh" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YJC2ZrXzCX4Y.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YJC2ZrXzCX4Y.npy", "labels": "/m/01d3sd,/m/09x0r", "caption": "A group of people talk as a man snores" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YR4fXcbWFhJg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YR4fXcbWFhJg.npy", "labels": "/m/03k3r,/m/09x0r,/m/0ch8v,/m/0jbk,/t/dd00129", "caption": "A man talking followed by a woman shouting as wind blows into a microphone and birds chirp in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part0/Y-AheI8Epim4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y-AheI8Epim4.npy", "labels": "/m/07qsvvw,/m/09x0r", "caption": "Some clicking and rattling followed by distant banging" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part38/Yvsy1IpYmrSY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yvsy1IpYmrSY.npy", "labels": "/m/0h9mv", "caption": "A muffled car engine revving several times as tires skid followed by a vehicle engine accelerating" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YKSHpYhuTotY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YKSHpYhuTotY.npy", "labels": "/m/01h3n,/m/03vt0,/m/0h2mp", "caption": "A person speaks with the buzzing of nearby insects" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YFR7BDRhMATo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YFR7BDRhMATo.npy", "labels": "/m/06hck5,/m/06wzb,/m/07rjwbb", "caption": "A train whistle blowing as a train runs on railroad tracks and a railroad crossing warning signal rings" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part24/YV4PLSw_WzVw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YV4PLSw_WzVw.npy", "labels": "/m/07r04,/m/07rknqz,/m/07yv9", "caption": "Tires skidding as a vehicle engine revs several times" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YrJVXE6Axtrg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YrJVXE6Axtrg.npy", "labels": "/m/09x0r,/m/0llzx", "caption": "A machine operating as a rapid rate between metal clacks while two men communicate with each other" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YTgxst7Ft9js.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YTgxst7Ft9js.npy", "labels": "/m/02p01q,/m/07pdjhy", "caption": "Wood scrapping followed by a man talking as a dog barks in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YsVYTOURVsQ0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YsVYTOURVsQ0.npy", "labels": "/m/07pqc89,/m/09x0r", "caption": "Water trickling while a man speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part7/Y5YzNSjmZ3Wg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y5YzNSjmZ3Wg.npy", "labels": "/m/01h3n,/m/09x0r", "caption": "Bee buzzes while man speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YD2Xc_jZllDY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YD2Xc_jZllDY.npy", "labels": "/m/068hy,/m/07r_k2n,/m/07rc7d9,/m/09x0r,/m/0bt9lr,/m/0jbk", "caption": "A dog barking as a man is talking while wind blows into a microphone as birds chirp in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YOxUVcZmeiyI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YOxUVcZmeiyI.npy", "labels": "/m/07qjznl,/m/07qjznt", "caption": "U'A clock ticking followed by a cuckoo bird cooing then music playing." }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YkXjzsroVTtw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YkXjzsroVTtw.npy", "labels": "/m/020bb7,/m/07pggtn,/m/09x0r", "caption": "A man speaking followed by footsteps on gravel as birds chirp in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/Yos_2U4xqTqw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yos_2U4xqTqw.npy", "labels": "/m/014zdl,/m/07qsvvw,/m/07s2xch", "caption": "Four gunshots occur followed by a man screaming and then an explosion" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y14izd_i3ryE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y14izd_i3ryE.npy", "labels": "/m/07rv9rh,/m/09x0r,/m/0jbk", "caption": "A man talking as a vehicle engine is running and wind is blowing into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4YodC6RnplI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4YodC6RnplI.npy", "labels": "/m/01d3sd", "caption": "A girl laughing as a person is snoring" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YD9tinq3RMpU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YD9tinq3RMpU.npy", "labels": "/m/019jd,/m/02rlv9,/m/07yv9,/m/09x0r", "caption": "A motorboat engine operating as a crowd of people talk followed by metal creaking and a man speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3ue0gJM0THk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3ue0gJM0THk.npy", "labels": "/m/02l6bg,/m/02mk9,/m/07pb8fc,/m/07q2z82,/t/dd00066", "caption": "Loud high frequency buzzing and revving of a propeller" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YIsUG5SKWNZA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YIsUG5SKWNZA.npy", "labels": "/m/09x0r,/t/dd00002", "caption": "A woman whispering, then a baby cries. The woman calls out loudly, a male voice answers over the baby whining" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YS0YE96w0YRk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YS0YE96w0YRk.npy", "labels": "/m/028ght", "caption": "A man speaking followed by a crowd of people laughing then applauding" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YsJrFyjfrL-g.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YsJrFyjfrL-g.npy", "labels": "/m/0llzx", "caption": "Slow vibrations of a sewing machine with several clicks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part27/YZsTZ7jqbd9M.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YZsTZ7jqbd9M.npy", "labels": "/m/01h3n,/m/09x0r", "caption": "A man talking as footsteps walk on dirt and gravel followed by a police siren in the distance as birds chirp in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YSL3wB5sDcdw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YSL3wB5sDcdw.npy", "labels": "/m/09t49,/m/0d31p", "caption": "A vacuum cleaner running as leaves rustle and a swarm of insects buzz while wind blows into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YLWng-4PDzPM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YLWng-4PDzPM.npy", "labels": "/m/01w250", "caption": "Some rustling followed by whistling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YTgxst7Ft9js.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YTgxst7Ft9js.npy", "labels": "/m/02p01q,/m/07pdjhy", "caption": "Scrapping and filing of wood followed by a man talking as a dog barks in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4lv9aLXtud0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4lv9aLXtud0.npy", "labels": "/m/03q5_w,/m/09x0r,/t/dd00125", "caption": "A man shouting before and after a person belches loudly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YbQNX7vDalQw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YbQNX7vDalQw.npy", "labels": "/m/07p9k1k", "caption": "A man talks followed by whispering and food sizzling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/YfmEft49sPfE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YfmEft49sPfE.npy", "labels": "/m/05zppz,/m/09t49,/m/09x0r", "caption": "Man speaking with light wind sounds" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YPg2cWEnEEvc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YPg2cWEnEEvc.npy", "labels": "/m/03q5_w", "caption": "Continuous burping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YtxeXrpoMST4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YtxeXrpoMST4.npy", "labels": "/m/0130jx,/m/02jz0l,/m/03dnzn,/m/0838f", "caption": "Water turning on and running continuously" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/YwFiCblfZ-vg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YwFiCblfZ-vg.npy", "labels": "/m/07pqc89,/m/09x0r", "caption": "A male speech and static" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YsbW7XwwUtSU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YsbW7XwwUtSU.npy", "labels": "/m/07qjznl,/m/07qjznt", "caption": "A clock chiming" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y79XDcI6xZm0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y79XDcI6xZm0.npy", "labels": "/m/02qldy,/m/05zppz,/m/09x0r", "caption": "A crowd chants, an adult male speaks in the foreground, a member of the crowd shouts, and the adult male continues to speak" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YmYQrjcYNrW0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YmYQrjcYNrW0.npy", "labels": "/m/01bjv,/m/07qv_d5,/m/07yv9", "caption": "A horn beeping rapidly then a long loud beep" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/YinQOrxc_oZo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YinQOrxc_oZo.npy", "labels": "/t/dd00018", "caption": "Hog snorting with male screaming" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YkagkXkAVPNo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YkagkXkAVPNo.npy", "labels": "/m/07yv9,/m/0912c9,/m/09x0r,/m/0k4j", "caption": "A vehicle engine running then accelerating as a series of vehicle horns honk and a group of people talk in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YCh0LMmhBUg4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YCh0LMmhBUg4.npy", "labels": "/m/03m9d0z,/m/06q74,/m/07yv9,/m/09x0r,/t/dd00129", "caption": "A man speaking and a child yelling with wind blowing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part9/Y8VOibo9Q_Dc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y8VOibo9Q_Dc.npy", "labels": "/m/09ddx,/m/09x0r,/m/0jbk", "caption": "A duck chirping as water lightly trickles and splashes" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YlfO471Rn61k.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YlfO471Rn61k.npy", "labels": "/m/06wzb,/m/07rjwbb", "caption": "Loud hissing followed by a low frequency, consistent beep then more hissing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part19/YMBP4RcnwGZw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YMBP4RcnwGZw.npy", "labels": "/m/02zsn,/m/07qfr4h,/m/09x0r", "caption": "A woman talking then laughing as a crowd of people talk in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/YinSvboaSRwA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YinSvboaSRwA.npy", "labels": "/m/07k1x,/m/083vt,/m/09x0r", "caption": "A machine motor running as a man is speaking followed by rapid buzzing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YCvNAwby6Xos.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YCvNAwby6Xos.npy", "labels": "/m/09x0r,/m/0llzx,/t/dd00125", "caption": "A man speaking followed by a sewing machine operating as a machine motor hums in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/YwVi5w_NU6CM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YwVi5w_NU6CM.npy", "labels": "/m/012f08,/m/012ndj,/m/03j1ly,/m/03kmc9,/m/07r04,/m/07yv9", "caption": "A fire engine horn blows, followed by a fire engine siren blowing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YW7OJevEgq7w.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YW7OJevEgq7w.npy", "labels": "/m/05tny_,/m/068hy,/m/07rc7d9,/m/0bt9lr,/m/0jbk", "caption": "A dog is panting, barking and yipping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YIPfaRF76gVU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YIPfaRF76gVU.npy", "labels": "/m/012ndj,/m/03j1ly,/m/07r04,/m/07yv9,/m/09x0r", "caption": "A crowd of people talking as emergency sirens sound and a truck accelerates followed by a man speaking over an intercom" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/YpO8kbg9IJnc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YpO8kbg9IJnc.npy", "labels": "/m/0130jx,/m/02jz0l,/m/0838f", "caption": "Metal squeaking and clanking followed by a man talking then a faucet pouring water" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YLxu-3_h4kc4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YLxu-3_h4kc4.npy", "labels": "/m/03q5_w", "caption": "A kid laughing as someone does a series of belching" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3XcIVh40pTI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3XcIVh40pTI.npy", "labels": "/m/01d3sd", "caption": "A person snoring" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part24/YUQtBt6CQpwg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YUQtBt6CQpwg.npy", "labels": "/m/09x0r,/m/0llzx", "caption": "A man speaks, and a sewing machine sews material" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part27/Ya0yXS7PmVR0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ya0yXS7PmVR0.npy", "labels": "/m/07qlf79", "caption": "Continuous white noise" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YrBUCIK8JRLg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YrBUCIK8JRLg.npy", "labels": "/m/034srq,/m/03m9d0z,/m/05kq4,/t/dd00092", "caption": "White noise continues then something begins clicking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YqWYncqPSy9A.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YqWYncqPSy9A.npy", "labels": "/m/03vt0,/m/09f96,/m/0h2mp", "caption": "A female speaking and an insect buzzing and then a male speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/YjjfUaMQaG1A.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YjjfUaMQaG1A.npy", "labels": "/m/01d380,/m/09x0r", "caption": "A man talking followed by metal shuffling then a power tool drilling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part9/Y8OTd45_6cvY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y8OTd45_6cvY.npy", "labels": "/m/07qlf79", "caption": "White noise as footsteps run on concrete followed by liquid spraying and a person groaning" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YbmEF-c-M174.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YbmEF-c-M174.npy", "labels": "/m/015p6,/m/09ddx,/m/09x0r", "caption": "A duck quacking and a bird chirping followed by footsteps on a wooden surface then a man talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/YwOFBldBFRNk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YwOFBldBFRNk.npy", "labels": "/m/0395lw", "caption": "Church bells ringing as rain pours and wind blows into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YRdC8cviN6Bs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YRdC8cviN6Bs.npy", "labels": "/m/06mb1,/t/dd00038", "caption": "Rain falls soft and steadily and a person closes a car door and walks away through leaves" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YnLtNjMimLE0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YnLtNjMimLE0.npy", "labels": "/m/07pqc89,/m/0838f", "caption": "Water trickling and pouring" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YESjMIqrvRj4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YESjMIqrvRj4.npy", "labels": "/m/09t49,/t/dd00092", "caption": "Rain falling as birds are chirping followed by thunder" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part7/Y5rh5-MCjqq8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y5rh5-MCjqq8.npy", "labels": "/m/01d3sd", "caption": "Snoring with some light rustling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4_DjmCg8Ra8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4_DjmCg8Ra8.npy", "labels": "/m/032s66,/m/0_1c", "caption": "Artillery cannons firing followed by a man talking as someone whistles while a group of men shout and gunshots fire in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part27/Y_YS5uKWoB6g.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y_YS5uKWoB6g.npy", "labels": "/m/09x0r,/t/dd00002", "caption": "A child cries followed by a man and woman speaking and then the child resumes sobbing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4abZbau8tZo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4abZbau8tZo.npy", "labels": "/m/07swgks,/m/09x0r", "caption": "A man talking with light tapping and a vehicle passing by in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9F3sutgYTvo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9F3sutgYTvo.npy", "labels": "/m/09x0r,/t/dd00002", "caption": "A man speaks followed by a child crying and then a woman speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part7/Y5t6tSW0yT40.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y5t6tSW0yT40.npy", "labels": "/m/07qlf79", "caption": "A machine is used to spray an object" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YmUGmCSNETcg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YmUGmCSNETcg.npy", "labels": "/m/07ptfmf,/m/0dxrf", "caption": "A woman talking as food and oil sizzles and metal clacks in a pot followed by a girl speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part1/Y096oTVzc5Gs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y096oTVzc5Gs.npy", "labels": "/m/09x0r,/m/0bt9lr,/m/0jbk,/t/dd00136", "caption": "A woman speaks followed by groaning and grunting" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/Yl5KdHAWwJCw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yl5KdHAWwJCw.npy", "labels": "/m/07qjznl", "caption": "A clock ticking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YSmdj6JFB9MQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YSmdj6JFB9MQ.npy", "labels": "/m/01jt3m,/m/09x0r", "caption": "A kid speaking followed by a toilet flushing then a girl talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YRp4Ct_TQvAM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YRp4Ct_TQvAM.npy", "labels": "/m/06mb1,/m/09x0r", "caption": "Rain falling with distant humming and a man speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YAUmY0YRAFQE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YAUmY0YRAFQE.npy", "labels": "/m/04qvtq,/m/07yv9,/m/0k4j,/t/dd00134", "caption": "A blaring siren from a vehicle passes by, then echoes and fades into the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9BGLAUSF0sk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9BGLAUSF0sk.npy", "labels": "/m/01jwx6,/m/0chx_", "caption": "A vehicle engine running and hissing loudly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part19/YMjSegUnQXr4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YMjSegUnQXr4.npy", "labels": "/m/015p6,/m/0h0rv,/t/dd00125", "caption": "Metal clanging as a construction vehicle operates in the background followed by bird wings flapping and pigeons cooing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YrN2rpLV3brs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YrN2rpLV3brs.npy", "labels": "/m/04brg2", "caption": "A man talking during a series of metal clacking against a dish" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part9/Y8Zo30kV5aiI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y8Zo30kV5aiI.npy", "labels": "/m/012n7d,/m/03j1ly,/m/03kmc9", "caption": "Ambulance driving past the black car" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YE6FH_xp3I54.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YE6FH_xp3I54.npy", "labels": "/m/07pggtn,/m/09x0r,/m/0jbk,/t/dd00129", "caption": "A man speaks with some humming and birds chirping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part19/YMTaLknnq4wc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YMTaLknnq4wc.npy", "labels": "/m/01w250", "caption": "A person whistling followed by a young woman singing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YPvWI4p74UOs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YPvWI4p74UOs.npy", "labels": "/m/019jd,/m/02rlv9,/m/07yv9,/m/09x0r", "caption": "A man laughs followed by distant hums and birds chirping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YCfxWJ1Qoufg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YCfxWJ1Qoufg.npy", "labels": "/m/01jt3m,/m/09x0r", "caption": "A man talking as paper crinkles followed by plastic creaking then a toilet flushing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/YynHdcJ9Oqaw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YynHdcJ9Oqaw.npy", "labels": "/m/07rqsjt", "caption": "Repetitive whoosh noises with a loud boom" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YAizmnCDlXos.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YAizmnCDlXos.npy", "labels": "/m/07qjznl,/m/07qjznt", "caption": "A bell ticks with a thumping noise" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/YhuMLK0oA3L8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YhuMLK0oA3L8.npy", "labels": "/m/01w250", "caption": "A man speaks followed by whistling and guitar music" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part15/YH7-orYrKBeo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YH7-orYrKBeo.npy", "labels": "/m/01bjv,/m/0463cq4,/m/07yv9,/m/09x0r", "caption": "A baby cries, and people are communicating" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YYflmW68gL4E.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YYflmW68gL4E.npy", "labels": "/m/03q5_w,/m/09x0r", "caption": "Burping and laughing from a young girl" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YXrJcmftCY04.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YXrJcmftCY04.npy", "labels": "/m/028ght", "caption": "A crowd of people applaud and cheer" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YPZBUdlKwX04.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YPZBUdlKwX04.npy", "labels": "/m/09x0r,/m/0j2kx,/m/0j6m2", "caption": "Water splashing with multiple voices in background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/YyVjivgsU2aA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YyVjivgsU2aA.npy", "labels": "/m/012f08,/m/07rknqz,/m/07yv9,/m/09x0r,/m/0h9mv,/m/0k4j,/m/0ltv", "caption": "A man talks in the background while a vehicle engine revs as tires skid then accelerates" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YTaQKhIRwii4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YTaQKhIRwii4.npy", "labels": "/m/028ght", "caption": "A crowd applauds and there is a muffled speaker in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YHVz-FJBf_iM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YHVz-FJBf_iM.npy", "labels": "/m/01jt3m,/m/0838f", "caption": "A toilet flushing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YBa92IrXFvJo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBa92IrXFvJo.npy", "labels": "/m/019jd,/m/02rlv9,/m/07yv9", "caption": "A large motor chugging" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/Yazh_-OkQ-uI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yazh_-OkQ-uI.npy", "labels": "/m/07bgp,/m/07q0h5t,/m/09x0r", "caption": "Goats bleat and a man talks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YAgh2EKINlSw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YAgh2EKINlSw.npy", "labels": "/m/06mb1,/t/dd00038", "caption": "Rain noise on surface as men are speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/Yk4XyfaWVLEY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yk4XyfaWVLEY.npy", "labels": "/m/01bjv,/m/07yv9,/m/09x0r", "caption": "Traffic sounds of vehicles with birds chirping and far away voices" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YIvfaKPDWC00.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YIvfaKPDWC00.npy", "labels": "/m/012f08,/m/012ndj,/m/03j1ly,/m/03kmc9,/m/07yv9", "caption": "A vehicle accelerates in the distance as emergency and police sirens sound" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YROootH-mtEI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YROootH-mtEI.npy", "labels": "/m/0j6m2", "caption": "A river stream of water flowing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YAxd__X2rixk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YAxd__X2rixk.npy", "labels": "/m/03k3r,/m/07rv9rh,/m/0jbk", "caption": "An animal is galloping with a clip-clop noise" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YnaPgJvWTIY4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YnaPgJvWTIY4.npy", "labels": "/m/04_sv,/m/07yv9,/t/dd00066,/t/dd00128", "caption": "An engine running and then revving" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YBMayJId0X1s.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBMayJId0X1s.npy", "labels": "/m/0463cq4,/m/09x0r", "caption": "A man speaking as a baby is crying over a radio" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y5I8lmN8rwDM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y5I8lmN8rwDM.npy", "labels": "/m/01d380,/m/07k1x,/t/dd00125", "caption": "Drilling noise loud and continue" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/YA2mcp0N__7U.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YA2mcp0N__7U.npy", "labels": "/m/07qlf79,/m/09x0r", "caption": "A crowd speak in the distance followed by sneezing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YszkiW0GXEOI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YszkiW0GXEOI.npy", "labels": "/m/015p6,/m/01w250", "caption": "Whistling and birds chirping back and forth" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/YhVUmQfBIYe8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YhVUmQfBIYe8.npy", "labels": "/m/02dgv", "caption": "An adult male speaks while crunching footfalls occur, then a metal car door clicks open, slight rustling occurs, and metal clinks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/Yz4MeV9IGVo0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yz4MeV9IGVo0.npy", "labels": "/m/01bjv,/m/07yv9,/m/09x0r", "caption": "Distant humming followed by men speaking over a radio" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/YdJYO3RbBabE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YdJYO3RbBabE.npy", "labels": "/m/02fs_r", "caption": "A short, single beep followed by a man talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y6cS0FsUM-cQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y6cS0FsUM-cQ.npy", "labels": "/m/01yrx,/m/068hy,/m/07qrkrw,/m/07r81j2,/m/09x0r,/m/0jbk", "caption": "An adult male speaks, a cat caterwauls and hisses angrily, and an adult female speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y0jGH7A_hpBM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y0jGH7A_hpBM.npy", "labels": "/m/02qldy,/m/05zppz,/m/09x0r", "caption": "Two men are speaking and paper is being shuffled" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YTSnq6n8tElo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YTSnq6n8tElo.npy", "labels": "/m/0242l,/m/04brg2", "caption": "Mechanical humming with some tapping on glass followed by rattling and a person speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3fomsZXG3aM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3fomsZXG3aM.npy", "labels": "/m/07q2z82,/m/07yv9,/t/dd00066", "caption": "An engine is idling and then is revved up" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/YzBXoaQ1GVlc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YzBXoaQ1GVlc.npy", "labels": "/m/09x0r,/m/0ytgt,/t/dd00013,/t/dd00126", "caption": "A woman speaking together with a crowd of children murmuring" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YTaQKhIRwii4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YTaQKhIRwii4.npy", "labels": "/m/028ght", "caption": "Loud crumpling followed by loud, high pitched buzzing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YP12nvSpKXcs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YP12nvSpKXcs.npy", "labels": "/m/01h3n,/m/03vt0,/m/0h2mp", "caption": "Insects buzzing followed by plastic camera muffling and a kid speaking then footsteps walking on foliage" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y6ZFU4PqXmoI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y6ZFU4PqXmoI.npy", "labels": "/m/019jd,/m/02rlv9,/m/07yv9,/m/09x0r", "caption": "Water sloshes as a motor runs, then a man briefly speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YEzWEO2WD_MM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YEzWEO2WD_MM.npy", "labels": "/m/01d380", "caption": "Toy helicopter whirring and crashing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YkgjNIDmO8a8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YkgjNIDmO8a8.npy", "labels": "/m/012ndj,/m/03j1ly,/m/03kmc9", "caption": "Distant rings of sirens get closer as traffic passes and people speak" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/YxpZna_FwDhI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YxpZna_FwDhI.npy", "labels": "/m/09x0r,/m/0llzx", "caption": "A click occurs then a woman speaks followed by a sewing machine stitching" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YtaYKM1OSTwE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YtaYKM1OSTwE.npy", "labels": "/m/03fwl,/m/07bgp,/m/0ch8v,/m/0jbk", "caption": "Sheep baaing as gusts of wind blows followed by a person chuckling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9dLLsZVRSZI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9dLLsZVRSZI.npy", "labels": "/m/07r04,/m/07yv9,/t/dd00129", "caption": "A truck engine running followed by a truck horn honking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YKJKHDKKW3XU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YKJKHDKKW3XU.npy", "labels": "/m/07swgks", "caption": "Water softly trickling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part19/YMj_BO-iK1G4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YMj_BO-iK1G4.npy", "labels": "/m/0llzx", "caption": "A burst of vibration from a sewing machine followed by scraping and clicking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YEBCH7TPgiPc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YEBCH7TPgiPc.npy", "labels": "/m/07q2z82,/m/07yv9,/m/0k4j", "caption": "A vehicle accelerates and then slows down" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YSCow4mpBsGY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YSCow4mpBsGY.npy", "labels": "/m/01d3sd", "caption": "A person is snoring" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part0/Y-BUWGM7qeUM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y-BUWGM7qeUM.npy", "labels": "/m/06mb1", "caption": "Wind is blowing and heavy rain is falling and splashing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/YhFCmq9pCBbM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YhFCmq9pCBbM.npy", "labels": "/m/09x0r,/t/dd00112", "caption": "A woman speaks with crinkling plastic" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9b6RqajfAmw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9b6RqajfAmw.npy", "labels": "/m/015p6,/m/0h0rv,/t/dd00129", "caption": "Pigeons coo and flap their wings" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/Ybpv_LneHmfU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ybpv_LneHmfU.npy", "labels": "/m/014yck,/m/07yv9,/m/0cmf2,/m/0k5j,/t/dd00129", "caption": "Humming of a distant aircraft engine" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YD4s5aHrsBgs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YD4s5aHrsBgs.npy", "labels": "/m/01w250", "caption": "Music is playing as a person whistles" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YIvg_q4t-3w0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YIvg_q4t-3w0.npy", "labels": "/m/02dgv,/m/09x0r", "caption": "White noise followed by brief, muffled speech and rustling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y404cD3bVXDc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y404cD3bVXDc.npy", "labels": "/m/09x0r,/t/dd00002", "caption": "A man speaks over the television and a baby cries" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YI4HpYGMMsz4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YI4HpYGMMsz4.npy", "labels": "/m/083vt,/m/09x0r", "caption": "A man talking as wood clanking as steam hisses in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YCfxWJ1Qoufg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YCfxWJ1Qoufg.npy", "labels": "/m/01jt3m,/m/09x0r", "caption": "Rustling followed by brief speech and water running" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part9/Y83j4GgHXTLE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y83j4GgHXTLE.npy", "labels": "/m/01j3sz,/m/09x0r,/m/0ytgt,/t/dd00125", "caption": "Children screaming as a man laughs followed by someone whispering then a young boy talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YBMayJId0X1s.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBMayJId0X1s.npy", "labels": "/m/0463cq4,/m/09x0r", "caption": "A baby crying over a radio as a man is talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part38/YuY4fe5DT1gI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YuY4fe5DT1gI.npy", "labels": "/m/01m2v,/m/0316dw", "caption": "Typing on a computer keyboard" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part0/Y-CcGuq0yoKo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y-CcGuq0yoKo.npy", "labels": "/m/02qldy,/m/02zsn,/m/09x0r", "caption": "A woman is speaking from a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YWUyeFOyKIg0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YWUyeFOyKIg0.npy", "labels": "/m/07yv9,/m/09x0r,/m/0k4j,/m/0ltv,/t/dd00129", "caption": "Man speaks midst a crowd, a distant horn blow, then a race car goes by" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YSL3wB5sDcdw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YSL3wB5sDcdw.npy", "labels": "/m/09t49,/m/0d31p", "caption": "A vacuum cleaner is operating with wind noise" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YQt0_xTadAT0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YQt0_xTadAT0.npy", "labels": "/m/09ld4", "caption": "Frogs croaking with rustling in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part15/YGuizRlAQ8qQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YGuizRlAQ8qQ.npy", "labels": "/m/01d380", "caption": "Power tools make drilling sounds" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9zstu_IfAm4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9zstu_IfAm4.npy", "labels": "/m/07r04,/m/07yv9,/m/09x0r", "caption": "An engine revving followed by horn honking and more revving" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part7/Y5iTRKJqUIw8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y5iTRKJqUIw8.npy", "labels": "/m/07qjznl,/m/09x0r", "caption": "Muffled crowd noise while a bell dings" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YaZAXO2WZn84.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YaZAXO2WZn84.npy", "labels": "/m/06wzb,/m/07rjwbb", "caption": "Bells chiming followed by a lawn mower engine running then a steam engine running and train whistle blowing while a crowd of people talk in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part9/Y86dNVnTwH6U.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y86dNVnTwH6U.npy", "labels": "/m/09x0r,/m/0llzx", "caption": "A machine motor running loudly followed by audio beeping and metal cranking then compressed air releasing proceeded by steam hissing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y466ucPGoNSQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y466ucPGoNSQ.npy", "labels": "/m/01yrx,/m/068hy,/m/07qrkrw,/m/09x0r,/m/0jbk", "caption": "A cat meowing repeatedly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y0yxEvdnimGg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y0yxEvdnimGg.npy", "labels": "/m/068hy,/m/07rc7d9,/m/09x0r,/m/0bt9lr,/m/0jbk", "caption": "Dogs barking and muffled speech" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YTd2EEDdFlRY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YTd2EEDdFlRY.npy", "labels": "/m/07p9k1k", "caption": "A man talking followed by footsteps on gravel as guitar music is playing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3wV3ST-c4PE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3wV3ST-c4PE.npy", "labels": "/m/07qjznl", "caption": "Tick-tocking by a clock" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/YfK4QBQZ6i7w.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YfK4QBQZ6i7w.npy", "labels": "/m/01j3sz,/m/07rgt08,/m/07s04w4", "caption": "People are laughing and chuckling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YFf8bCCJfVX4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YFf8bCCJfVX4.npy", "labels": "/m/032s66", "caption": "Rapid and repeated gunfire and then a male speech" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YUAmDLPjNyMg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YUAmDLPjNyMg.npy", "labels": "/m/07yv9,/m/0cmf2,/m/0k5j", "caption": "Wind blowing and an engine running" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y0yxEvdnimGg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y0yxEvdnimGg.npy", "labels": "/m/068hy,/m/07rc7d9,/m/09x0r,/m/0bt9lr,/m/0jbk", "caption": "Dogs are barking with wind noise while people are speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y0qbHT34qTZE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y0qbHT34qTZE.npy", "labels": "/m/032s66,/m/06q74,/m/09x0r", "caption": "A group of men speaking as cannons fire while rain falls and water splashes followed by thunder roaring" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part38/YwAZrOPvul4Y.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YwAZrOPvul4Y.npy", "labels": "/m/09x0r,/t/dd00112", "caption": "Plastic crinkling as a man is talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/Yt4prXmPwthg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yt4prXmPwthg.npy", "labels": "/m/09x0r,/m/0llzx", "caption": "Vibrations from a sewing machine followed by a woman speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4xrL4TSgHwU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4xrL4TSgHwU.npy", "labels": "/m/02mk9,/m/07pb8fc,/m/07q2z82,/m/07yv9,/t/dd00066,/t/dd00130", "caption": "A vehicle engine stalling then starting up and running idle" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part1/Y-nQHwrRLfc0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y-nQHwrRLfc0.npy", "labels": "/m/02mk9,/m/07pb8fc,/t/dd00066", "caption": "Clicking and vibrating of a humming rattling engine" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part0/Y-R69Fa-mCaY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y-R69Fa-mCaY.npy", "labels": "/m/01j4z9,/m/083vt", "caption": "A chainsaw cutting as wood is cracking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YLxu-3_h4kc4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YLxu-3_h4kc4.npy", "labels": "/m/03q5_w", "caption": "Burping and then laughter" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YSE_3nszEw7o.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YSE_3nszEw7o.npy", "labels": "/m/06wzb,/m/07rjwbb", "caption": "A steam engine running on railroad tracks as steam hisses and metal clacking occur in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3XuyGJqaXv8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3XuyGJqaXv8.npy", "labels": "/m/068hy,/m/07rc7d9,/m/09x0r,/m/0bt9lr,/m/0jbk", "caption": "An adult male speaks in the foreground, and dogs are barking and people are talking in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/Ym_U506sf9p4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ym_U506sf9p4.npy", "labels": "/m/07p9k1k,/m/07ptfmf,/m/0dxrf", "caption": "An adult female speaks while sizzling and crackling are ongoing, and metal thumping and clinking occur" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YatmDP_fmK_8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YatmDP_fmK_8.npy", "labels": "/m/014zdl,/m/07qsvvw", "caption": "Synthesized rumbling followed by an explosion" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YKSHpYhuTotY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YKSHpYhuTotY.npy", "labels": "/m/01h3n,/m/03vt0,/m/0h2mp", "caption": "A man speaking as footsteps walk on grass while insects are buzzing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/YeRU-rABp8nk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YeRU-rABp8nk.npy", "labels": "/m/04_sv,/m/07yv9,/m/09x0r", "caption": "People are talking as an engine is running" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YC9NC7wJ7C3w.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YC9NC7wJ7C3w.npy", "labels": "/m/02qldy,/m/02zsn,/m/09x0r", "caption": "A woman speaking very quickly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/YzoctgurhvHE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YzoctgurhvHE.npy", "labels": "/m/012f08,/m/02dgv,/m/04gxbd,/m/07yv9", "caption": "A man speaking with some rustling and humming" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YT9_ep-3BZDY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YT9_ep-3BZDY.npy", "labels": "/m/09x0r,/t/dd00112,/t/dd00125", "caption": "A female voice briefly speaks followed by crinkling noises" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y6cyKp3EDm-0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y6cyKp3EDm-0.npy", "labels": "/m/015p6,/m/09x0r,/m/0h0rv", "caption": "Something clicks repeatedly and then a man begins talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y1PvMtRIlZNI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1PvMtRIlZNI.npy", "labels": "/m/07swgks", "caption": "Tapping noise followed by splashing and gurgling water" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/Yd6gu2w19YQo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yd6gu2w19YQo.npy", "labels": "/m/01j3sz", "caption": "An infant laughing moderately" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YlmPMhs-9IYE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YlmPMhs-9IYE.npy", "labels": "/m/07yv9,/m/09x0r,/m/0k4j,/m/0ltv", "caption": "Revving of loud engines with people speaking and cheering" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y7_smJ8VbfSU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y7_smJ8VbfSU.npy", "labels": "/m/02qldy,/m/02zsn,/m/09x0r", "caption": "A woman speaking while a crowd murmurs in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y1e98HeU9Vrg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1e98HeU9Vrg.npy", "labels": "/m/034srq,/m/03m9d0z,/m/05kq4", "caption": "Waves of water colliding repeatedly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YFXdoNvmrYxo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YFXdoNvmrYxo.npy", "labels": "/m/03vt0,/m/09x0r,/t/dd00129", "caption": "A child talking followed by a man talking as a young boy mumbles while birds chirp in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YTwR8BA6buMI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YTwR8BA6buMI.npy", "labels": "/m/07qjznl", "caption": "A ticktock sound playing at the same rhythm with piano notes" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/YhiJB_95IWiE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YhiJB_95IWiE.npy", "labels": "/m/02p01q,/m/07pdjhy", "caption": "A man speaks with some clicking and some sanding" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YAxd__X2rixk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YAxd__X2rixk.npy", "labels": "/m/03k3r,/m/07rv9rh,/m/0jbk", "caption": "A horse making clip-clop noises" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/Yq4YFJA5pFXc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yq4YFJA5pFXc.npy", "labels": "/m/09ct_,/t/dd00129", "caption": "Electrical humming with wind blowing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part27/Ya3GzZKxUTy8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ya3GzZKxUTy8.npy", "labels": "/m/015p6,/m/09ddx,/m/0bt9lr,/m/0jbk", "caption": "Birds chirp and a duck quacks followed by a dog barking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part4/Y2bq2lc3DLwM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y2bq2lc3DLwM.npy", "labels": "/m/07yv9,/m/09x0r,/m/0k4j,/t/dd00134", "caption": "A man speaks and a vehicle passes" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y7-HCqJFwHoI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y7-HCqJFwHoI.npy", "labels": "/m/01m2v,/m/0316dw", "caption": "A person clicking on a keyboard" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YKtTLsveexOg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YKtTLsveexOg.npy", "labels": "/m/0llzx", "caption": "A sewing machine operating several times as a loud motor hum in the background followed by steam hissing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part7/Y6CDl4CqOgMg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y6CDl4CqOgMg.npy", "labels": "/m/068hy,/m/0bt9lr,/m/0jbk,/t/dd00136", "caption": "A dog breathes heavily with a whirring background noise" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YU90e2P9jy30.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YU90e2P9jy30.npy", "labels": "/m/07pqc89,/m/09x0r", "caption": "Several basketballs bouncing and shoes squeaking on a hardwood surface as a man yells in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YPYP-r0nvbFk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YPYP-r0nvbFk.npy", "labels": "/m/07bgp,/m/07q0h5t,/m/09x0r", "caption": "A man talking as sheep baa while wind blows into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YmWqH2xwjkYA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YmWqH2xwjkYA.npy", "labels": "/m/01j3sz,/m/09x0r", "caption": "An infant and a woman laughing followed by someone spits then a woman talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part9/Y8IdCiapDYCU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y8IdCiapDYCU.npy", "labels": "/m/068hy,/m/07rc7d9,/m/0bt9lr,/m/0jbk", "caption": "Birds coo, and a dog growls and barks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YTQr9v-PQOc4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YTQr9v-PQOc4.npy", "labels": "/m/01hsr_", "caption": "Several faint clicks are followed by a person sneezing and coughing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4s2rRnu2PZo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4s2rRnu2PZo.npy", "labels": "/m/07rqsjt", "caption": "Music playing with some whooshes and gunshots with faint brief speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YPMMkPq5jJXY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YPMMkPq5jJXY.npy", "labels": "/m/03q5_w,/m/09x0r", "caption": "A person burps as people laugh" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YPtW0cZVprJQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YPtW0cZVprJQ.npy", "labels": "/m/01d3sd,/m/09x0r", "caption": "A person snoring followed by a man talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YDn3buZWMzwY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YDn3buZWMzwY.npy", "labels": "/m/01d3sd,/m/09x0r", "caption": "Men speak as someone snores" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part15/YFhimNYClv40.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YFhimNYClv40.npy", "labels": "/m/012ndj,/m/03j1ly,/m/03kmc9", "caption": "An ambulance travels with the siren blaring loudly and moves through traffic" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/YyLu4b01t53k.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YyLu4b01t53k.npy", "labels": "/m/012f08,/m/07pb8fc,/m/07yv9", "caption": "An idle vehicle engine running" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3MoF8myFs8Y.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3MoF8myFs8Y.npy", "labels": "/m/034srq,/m/03m9d0z,/m/05kq4,/t/dd00092", "caption": "Strong wind noise under a microphone as waves travel" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4xrL4TSgHwU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4xrL4TSgHwU.npy", "labels": "/m/02mk9,/m/07pb8fc,/m/07q2z82,/m/07yv9,/t/dd00066,/t/dd00130", "caption": "A vehicle engine stuttering while starting up then running idle" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part4/Y2sZhC_mKeic.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y2sZhC_mKeic.npy", "labels": "/m/01yrx,/m/068hy,/m/07qrkrw", "caption": "A cat meowing once with a thud" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part38/Yu9px4Lwv9XI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yu9px4Lwv9XI.npy", "labels": "/m/07st88b,/m/09ld4", "caption": "Frogs croaking with wet slaps and brief drums" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YFR7BDRhMATo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YFR7BDRhMATo.npy", "labels": "/m/06hck5,/m/06wzb,/m/07rjwbb", "caption": "A train running on railroad tracks as a train horn whistle blows several times while railroad crossing warning signals are ringing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YtTB0BK39JI8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YtTB0BK39JI8.npy", "labels": "/m/0395lw", "caption": "Bells ringing as wood shuffles and clacks while a muffled clock ticks in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part15/YH-vTZh81qAU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YH-vTZh81qAU.npy", "labels": "/m/01jwx6", "caption": "Clicking followed by humming noise" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YP4qd8uodw_M.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YP4qd8uodw_M.npy", "labels": "/m/02fs_r,/m/09x0r", "caption": "A male speaks then a click followed by a whine and a series of loud beeps" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YsqWyxUObwkw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YsqWyxUObwkw.npy", "labels": "/m/019jd,/m/02rlv9,/m/07yv9", "caption": "A motorboat engine turns on" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YRtenf2XSXRc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YRtenf2XSXRc.npy", "labels": "/m/07q2z82,/m/07yv9,/m/0k4j", "caption": "A vehicle engine running idle then revving several times before a car door slams shut" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part24/YVeCSHwtkBZU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YVeCSHwtkBZU.npy", "labels": "/m/012n7d,/m/03j1ly,/m/03kmc9", "caption": "Ambulance siren repeatedly and then continuous" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YD1Sy7kRoaR8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YD1Sy7kRoaR8.npy", "labels": "/m/03k3r,/m/07rv9rh,/m/09x0r,/m/0jbk", "caption": "A woman is speaking, and a horse brays" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YTaQKhIRwii4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YTaQKhIRwii4.npy", "labels": "/m/028ght", "caption": "A crowd of people applauding followed by a woman speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YYH4qi8Ul6v0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YYH4qi8Ul6v0.npy", "labels": "/m/09x0r,/t/dd00002", "caption": "A man talking as an infant is crying followed by a man humming" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YrtgVoZCcBw8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YrtgVoZCcBw8.npy", "labels": "/m/03fwl,/m/09x0r,/m/0jbk", "caption": "Animal sounds and a scream" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YKSHpYhuTotY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YKSHpYhuTotY.npy", "labels": "/m/01h3n,/m/03vt0,/m/0h2mp", "caption": "A man talking as metal clanks together followed by footsteps on grass while insects buzz in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YtjCNwdOUiGc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YtjCNwdOUiGc.npy", "labels": "/m/07qv_d5,/m/07yv9,/m/0912c9", "caption": "A bus engine accelerating followed by a bus horn honking while plastic clacks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YHqndxoujCYI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YHqndxoujCYI.npy", "labels": "/m/07qjznl,/m/09x0r", "caption": "Loud ringing of a clock followed by faint tick rocks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y0jGH7A_hpBM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y0jGH7A_hpBM.npy", "labels": "/m/02qldy,/m/05zppz,/m/09x0r", "caption": "An adult male speaks, followed by another adult male speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part4/Y2a6GNu6uCDE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y2a6GNu6uCDE.npy", "labels": "/m/02qldy,/m/02zsn,/m/09x0r", "caption": "An adult female speaks in a quiet environment, and her voice is electronically amplified" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YZ_smJ66Tb3c.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YZ_smJ66Tb3c.npy", "labels": "/m/015p6,/m/020bb7,/m/07r_25d,/m/0h0rv", "caption": "A man talking as a person hisses while pigeons coo and bird wings flap in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YL6rnV0oNIII.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YL6rnV0oNIII.npy", "labels": "/m/07qjznl", "caption": "A series of electronic beeps alongside plastic clicking and laser effects followed by a wooden thud and synthesized explosion" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YsI7_ycEYzAY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YsI7_ycEYzAY.npy", "labels": "/m/07qjznl,/m/07qjznt", "caption": "A clock ticking during high-pitched humming followed by a person sniffing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YAFgGoY8Ihhg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YAFgGoY8Ihhg.npy", "labels": "/m/03j1ly,/m/03kmc9,/m/04qvtq", "caption": "Police sirens sounding as wind is blowing heavily into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y1L_OyngNZMA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1L_OyngNZMA.npy", "labels": "/m/01j3sz,/m/07p6fty,/m/09x0r", "caption": "Male speaking, laughter and shouting and clapping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YU5ij0M7T-hk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YU5ij0M7T-hk.npy", "labels": "/m/02dgv,/m/09x0r", "caption": "Rustling and then male speech and then creaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part7/Y5ye0X5saadg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y5ye0X5saadg.npy", "labels": "/m/09ct_,/m/09x0r", "caption": "Helicopter running, speech on a radio, and then gunfire" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part27/Y_GI7meqlYZk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y_GI7meqlYZk.npy", "labels": "/m/01yrx,/m/068hy,/m/07qrkrw,/m/09x0r,/m/0jbk", "caption": "A young kid is talking as a cat is growling then meowing with a series of electronic buzzing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part0/Y-CcGuq0yoKo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y-CcGuq0yoKo.npy", "labels": "/m/02qldy,/m/02zsn,/m/09x0r", "caption": "A female speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YCbe2B6ohBpw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YCbe2B6ohBpw.npy", "labels": "/m/015p6,/m/068hy,/m/09ddx,/m/0ch8v,/m/0dbvp,/m/0jbk", "caption": "A duck quacking repeatedly, and a horses hooves clopping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part15/YFlk-X0gwjF4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YFlk-X0gwjF4.npy", "labels": "/m/020bb7,/m/09x0r,/t/dd00129", "caption": "A man talking followed by footsteps on foliage and twigs as birds chirp in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part0/Y-mb4Fw4Z0xg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y-mb4Fw4Z0xg.npy", "labels": "/m/012f08,/m/07yv9,/m/09x0r,/m/0k4j,/t/dd00134", "caption": "Race cars are racing followed by people talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YcFHFVGOtp6g.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YcFHFVGOtp6g.npy", "labels": "/m/09ld4,/m/09x0r", "caption": "Muffled speech and buzzing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/Ycz0FSQDVBMw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ycz0FSQDVBMw.npy", "labels": "/m/06wzb,/m/07rjwbb", "caption": "Steam hisses and vibration occurs while a child speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/Ym_U506sf9p4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ym_U506sf9p4.npy", "labels": "/m/07p9k1k,/m/07ptfmf,/m/0dxrf", "caption": "A woman talks before plastic clanking as food and oil are sizzling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YPvWI4p74UOs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YPvWI4p74UOs.npy", "labels": "/m/019jd,/m/02rlv9,/m/07yv9,/m/09x0r", "caption": "Laughing and a motor running with birds chirping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/Yn74IYuCe_ms.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yn74IYuCe_ms.npy", "labels": "/m/09x0r,/m/0j6m2", "caption": "Sounds of a river with man briefly mumbling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/Ym_NCf-q4Gn0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ym_NCf-q4Gn0.npy", "labels": "/m/04_sv,/m/07qnq_y,/m/07yv9,/t/dd00128", "caption": "Motor cycle motor running on idle" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YC5kmOK_l4jc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YC5kmOK_l4jc.npy", "labels": "/m/09x0r,/m/0ytgt,/t/dd00001", "caption": "A baby is laughing while a young girl speaks repeatedly, and an adult female chuckles softly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part19/YNX0gR9Eebp0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YNX0gR9Eebp0.npy", "labels": "/m/03dnzn,/m/09x0r,/m/0ytgt", "caption": "Water pouring with female speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y6aWnK1GyeJY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y6aWnK1GyeJY.npy", "labels": "/m/0463cq4,/m/09x0r", "caption": "Crying and then sneezing followed by more crying and a female speech." }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part4/Y2ceUOv8A3FE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y2ceUOv8A3FE.npy", "labels": "/m/01g50p,/m/0284vy3,/m/06d_3,/m/07jdr", "caption": "A rolling train blows its horn multiple times" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/YfsBR7e_X_0Y.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YfsBR7e_X_0Y.npy", "labels": "/m/09x0r,/m/0ytgt,/t/dd00125", "caption": "A child speaks followed by second child speaking as well" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YE3Q1jfTeuWs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YE3Q1jfTeuWs.npy", "labels": "/t/dd00002", "caption": "A baby is crying and then breathing heavily" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YRk-ujWKzPuc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YRk-ujWKzPuc.npy", "labels": "/m/06mb1,/t/dd00038", "caption": "Heavy rain hitting the ground" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part27/Y_xylo5_IiaM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y_xylo5_IiaM.npy", "labels": "/m/09x0r,/m/0ytgt,/t/dd00125", "caption": "A woman and a baby are having a conversation" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/YoiIi6H83Y38.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YoiIi6H83Y38.npy", "labels": "/m/04_sv,/m/07yv9,/m/09x0r", "caption": "A motorcycle engine starting up then revving several times as a man talks in the background while wind blows into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YDzKjogSVOLM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YDzKjogSVOLM.npy", "labels": "/m/07qdb04,/m/09ddx,/m/09x0r,/m/0jbk", "caption": "Ducks quacking and chirping as a rooster crows and a crowd of people talks in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part7/Y5ORpSk5CIWc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y5ORpSk5CIWc.npy", "labels": "/m/09ct_", "caption": "Vibrations from a small engine get louder as they pass by then into the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YkgjNIDmO8a8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YkgjNIDmO8a8.npy", "labels": "/m/012ndj,/m/03j1ly,/m/03kmc9", "caption": "Emergency vehicle siren blasts while a man talks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/Yf8WPf5F22xI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yf8WPf5F22xI.npy", "labels": "/m/01hsr_", "caption": "A person sneezing twice followed by a man speaking then a kid chuckling as a clock ticks in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/YwnqUgK_-fo4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YwnqUgK_-fo4.npy", "labels": "/m/07bgp,/m/09x0r,/m/0jbk", "caption": "Firecrackers popping as a crowd of people cheer and whistle" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y1ed87LLY97k.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1ed87LLY97k.npy", "labels": "/m/07rjwbb", "caption": "Thuds on floor" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/YemGPabOePzA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YemGPabOePzA.npy", "labels": "/m/03q5_w,/m/09x0r", "caption": "Eructation sounds in slow motion followed by speech in slow motion" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part9/Y8F-ndyrEWJ8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y8F-ndyrEWJ8.npy", "labels": "/m/012n7d,/m/03j1ly,/m/03kmc9", "caption": "Passing engines with loud hums and police sirens then a man speaks on a radio" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YC5kmOK_l4jc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YC5kmOK_l4jc.npy", "labels": "/m/09x0r,/m/0ytgt,/t/dd00001", "caption": "A young girl talking as an infant is laughing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3IguMJkqpl4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3IguMJkqpl4.npy", "labels": "/m/07qdb04,/m/09ddx,/m/09x0r", "caption": "People speaking followed by a duck quacking and a child crying" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y6cyKp3EDm-0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y6cyKp3EDm-0.npy", "labels": "/m/015p6,/m/09x0r,/m/0h0rv", "caption": "Pigeons are cooing flapping and a man talks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YFeHndzYAUkg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YFeHndzYAUkg.npy", "labels": "/m/01d380,/m/07k1x,/m/0_ksk", "caption": "A power tool drilling as music plays in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/Yne2DpKCIr4Y.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yne2DpKCIr4Y.npy", "labels": "/m/034srq,/m/03m9d0z,/m/05kq4,/t/dd00092", "caption": "Ocean waves crashing and water streaming as wind blows into a microphone while a man talks faintly in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3iLGu2Omgrw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3iLGu2Omgrw.npy", "labels": "/m/02qldy,/m/05zppz,/m/09x0r", "caption": "An adult male is speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YYk274Wr5iIE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YYk274Wr5iIE.npy", "labels": "/m/06mb1", "caption": "Rain and water splashing sounds while the wind blows" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/Ygf6H_MWCqjw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ygf6H_MWCqjw.npy", "labels": "/m/015p6,/m/09ddx", "caption": "A duck quacking followed by plastic camera muffling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YAj_VMUSNjNM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YAj_VMUSNjNM.npy", "labels": "/m/02mk9,/m/07q2z82,/m/07yv9,/m/0k4j", "caption": "A powerful engine revs as it idles" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YtxeXrpoMST4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YtxeXrpoMST4.npy", "labels": "/m/0130jx,/m/02jz0l,/m/03dnzn,/m/0838f", "caption": "Water flowing and splashing, increases in volume suddenly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part0/Y-SkjbQVgJ0M.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y-SkjbQVgJ0M.npy", "labels": "/m/07yv9,/m/09x0r,/m/0k4j,/t/dd00134", "caption": "A man speaking as vehicles drive by and leaves rustling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part27/Y_duNX6Vyd6g.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y_duNX6Vyd6g.npy", "labels": "/m/019jd,/m/02rlv9,/m/07yv9", "caption": "A motorboat drives on water quickly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y1a2XWJ8NA_Q.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1a2XWJ8NA_Q.npy", "labels": "/m/019jd,/m/02rlv9,/m/07yv9,/m/09x0r", "caption": "Clicking and sputtering of a running engine with people speaking and wind blowing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/YpCQEWAFGEjc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YpCQEWAFGEjc.npy", "labels": "/m/06wzb,/m/07rjwbb", "caption": "Hissing and rattling of a passing train with people speaking in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part24/YUmNrhFKpWIY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YUmNrhFKpWIY.npy", "labels": "/m/07q2z82,/m/07yv9,/m/0k4j", "caption": "Humming of an engine as it revs" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/YzBXoaQ1GVlc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YzBXoaQ1GVlc.npy", "labels": "/m/09x0r,/m/0ytgt,/t/dd00013,/t/dd00126", "caption": "Several children speaking and screaming with a woman speaking briefly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/Yq46VXJ6JN9M.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yq46VXJ6JN9M.npy", "labels": "/m/07qlf79", "caption": "Birds are chirping in the background, rustling and clattering ensue, then a hissing spray and more rustling and clattering occur" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YtaYKM1OSTwE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YtaYKM1OSTwE.npy", "labels": "/m/03fwl,/m/07bgp,/m/0ch8v,/m/0jbk", "caption": "Several goats bleat" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part24/YVMsbrcHPBfk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YVMsbrcHPBfk.npy", "labels": "/m/03fwl", "caption": "A man mimics goat bleating" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/YoZaEHkfh5Eg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YoZaEHkfh5Eg.npy", "labels": "/m/07yv9,/m/0912c9,/m/0k4j", "caption": "A vehicle horn honking as a series of electronic beeps chime followed by a plastic click" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/YynHdcJ9Oqaw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YynHdcJ9Oqaw.npy", "labels": "/m/07rqsjt", "caption": "Loud booming bursts and whooshes" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YZ7yDwpdGelM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YZ7yDwpdGelM.npy", "labels": "/m/07pqc89,/m/09x0r", "caption": "A man talking followed by sawing then a metal click and plastic crinkling as water trickles and wind blows into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YkF1KWybdRpM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YkF1KWybdRpM.npy", "labels": "/m/014yck,/m/07yv9,/m/0cmf2,/m/0k5j", "caption": "An aircraft taking off with some wind noises in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9zstu_IfAm4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9zstu_IfAm4.npy", "labels": "/m/07r04,/m/07yv9,/m/09x0r", "caption": "Vibrations and humming from an oncoming large vehicle with people speaking in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YCMNlIW6Lkwc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YCMNlIW6Lkwc.npy", "labels": "/m/014zdl,/m/07qsvvw,/m/09x0r", "caption": "Gun shot then an explosion followed by male laughter" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YWq4OD3olO2w.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YWq4OD3olO2w.npy", "labels": "/m/07r660_,/m/09x0r,/m/0ytgt,/t/dd00125", "caption": "A man talks followed by laughter, and a woman and children communicate" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9zstu_IfAm4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9zstu_IfAm4.npy", "labels": "/m/07r04,/m/07yv9,/m/09x0r", "caption": "A truck horn honking as a large truck engine drives by while a crowd of people talk in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y6cS0FsUM-cQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y6cS0FsUM-cQ.npy", "labels": "/m/01yrx,/m/068hy,/m/07qrkrw,/m/07r81j2,/m/09x0r,/m/0jbk", "caption": "A man talking as a cat wails and hisses while a woman laughs then talks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part1/Y0UJtGcoPYa0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y0UJtGcoPYa0.npy", "labels": "/m/07jdr,/m/07yv9,/m/0912c9,/t/dd00128", "caption": "A motor is running and a horn blows" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y0yETgW44MZU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y0yETgW44MZU.npy", "labels": "/m/01g50p,/m/0284vy3,/m/04zmvq,/m/06d_3,/m/07jdr,/m/07yv9,/t/dd00129", "caption": "A sudden horn blare as a train passes" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/YgwQMkQmBITE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YgwQMkQmBITE.npy", "labels": "/m/083vt,/m/09x0r,/t/dd00125", "caption": "A man is talking with tapping background noises" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YE3D_z0aoUEg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YE3D_z0aoUEg.npy", "labels": "/m/07st88b,/m/09ld4", "caption": "A croaking frog with brief bird chirps" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part7/Y67BsqRkh-dU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y67BsqRkh-dU.npy", "labels": "/m/01jt3m,/m/0838f", "caption": "A toilet flushes and water drains" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y1HCuBnPLMqQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1HCuBnPLMqQ.npy", "labels": "/m/07pqc89", "caption": "Plastic clacking followed by as person breathing then liquid pouring into containers" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YLBe33dw9ezg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YLBe33dw9ezg.npy", "labels": "/m/09ct_,/m/09x0r", "caption": "An electronic device buzzing as music plays in the background followed by a woman talking faintly in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YPtW0cZVprJQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YPtW0cZVprJQ.npy", "labels": "/m/01d3sd,/m/09x0r", "caption": "Snoring followed by male speech" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YL6rnV0oNIII.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YL6rnV0oNIII.npy", "labels": "/m/07qjznl", "caption": "An electronic device beeping as plastic clacks with a toy zapping followed by a wooden thud and audio static" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part1/Y0Dt-pH0pW-Y.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y0Dt-pH0pW-Y.npy", "labels": "/m/04_sv,/m/07yv9,/m/09x0r", "caption": "An engine and speech on a loudspeaker" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part15/YGE1aZSnPr2Q.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YGE1aZSnPr2Q.npy", "labels": "/m/01j3sz", "caption": "A man laughing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YTOaQMYc79Mw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YTOaQMYc79Mw.npy", "labels": "/m/07yv9,/t/dd00130", "caption": "A motor vehicle engine clicks and whirs and tries to start three times, metal clinks softly, then a deep buzz occurs" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YSCow4mpBsGY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YSCow4mpBsGY.npy", "labels": "/m/01d3sd", "caption": "A person snoring as metal creaks in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/YztSjcZNUY7A.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YztSjcZNUY7A.npy", "labels": "/m/09x0r,/t/dd00002", "caption": "Woman making a soothing sound while baby cries" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YJ0yeFeKvIt8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YJ0yeFeKvIt8.npy", "labels": "/m/09t49", "caption": "Water splashes and wind blows" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YKJhGuhNHToA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YKJhGuhNHToA.npy", "labels": "/m/083vt", "caption": "Rough sanding and scraping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YKnsKf9KoNds.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YKnsKf9KoNds.npy", "labels": "/m/07cx4,/m/09x0r", "caption": "A man speaking and another speaks over the phone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9E8BmPZ9mWc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9E8BmPZ9mWc.npy", "labels": "/m/07r04,/m/07yv9,/m/09x0r", "caption": "Humming of loud engines with men speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YqWYncqPSy9A.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YqWYncqPSy9A.npy", "labels": "/m/03vt0,/m/09f96,/m/0h2mp", "caption": "A man talking as an insect buzzes followed by a woman laughing then a man talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YmJ6ZO3xEcgw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YmJ6ZO3xEcgw.npy", "labels": "/m/01hsr_", "caption": "A woman coughs and sneezes several times" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part24/YVkbp8VmL3pM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YVkbp8VmL3pM.npy", "labels": "/m/0463cq4", "caption": "A baby cries and shout from time to time" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YCBwXKOpJY_o.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YCBwXKOpJY_o.npy", "labels": "/m/01h8n0,/m/02zsn,/m/09x0r,/m/0ytgt", "caption": "A woman and a child speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part9/Y8ipe6b1LwHQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y8ipe6b1LwHQ.npy", "labels": "/m/023pjk,/m/04brg2", "caption": "The clinking of glasses with some rustling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part24/YUXGzbBGbqAA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YUXGzbBGbqAA.npy", "labels": "/m/07ryjzk,/m/0dxrf", "caption": "Muted knocking, thumping and smacking are occurring, accompanied by rapid and irregular breathing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YBlbGXalLNVU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBlbGXalLNVU.npy", "labels": "/m/07pqc89", "caption": "Waves crashing onto shore followed by a man talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YCBwXKOpJY_o.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YCBwXKOpJY_o.npy", "labels": "/m/01h8n0,/m/02zsn,/m/09x0r,/m/0ytgt", "caption": "A woman speaking with a child speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part7/Y6Pywt0f_NFY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y6Pywt0f_NFY.npy", "labels": "/m/02jz0l,/m/03dnzn,/m/0838f", "caption": "Water is splashing down into a bathtub" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3MoF8myFs8Y.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3MoF8myFs8Y.npy", "labels": "/m/034srq,/m/03m9d0z,/m/05kq4,/t/dd00092", "caption": "A strong wind is blowing and constant background waves can be heard" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YXPebkNzsnRI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YXPebkNzsnRI.npy", "labels": "/m/01w250,/m/09x0r", "caption": "Young children are whistling and laughing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YbJMMp6PLKqM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YbJMMp6PLKqM.npy", "labels": "/m/0463cq4,/m/09x0r,/m/0ytgt,/t/dd00125", "caption": "A young girl talking as a woman is talking in the background as an infant is crying" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YSZ6CcXINiiE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YSZ6CcXINiiE.npy", "labels": "/m/014zdl,/m/07qsvvw,/m/09x0r", "caption": "A man talking followed by footsteps shuffling then a loud popping explosion proceeded by a man laughing as music plays in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/Yyrxa6_P2I80.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yyrxa6_P2I80.npy", "labels": "/m/015p6,/m/0h0rv,/t/dd00129", "caption": "Birds chirping continuously" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part4/Y2ceUOv8A3FE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y2ceUOv8A3FE.npy", "labels": "/m/01g50p,/m/0284vy3,/m/06d_3,/m/07jdr", "caption": "Honking of horns of an oncoming train" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3n05BjV7r7M.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3n05BjV7r7M.npy", "labels": "/m/02dgv,/m/02y_763", "caption": "Rustling with a small motor running" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YUE3XnVFodMI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YUE3XnVFodMI.npy", "labels": "/m/028ght,/m/09x0r", "caption": "Applause from a crowd with women briefly speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/YA0E_UiD-fR4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YA0E_UiD-fR4.npy", "labels": "/m/02fs_r", "caption": "A bleeping noise followed by a loud object in use" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YLs1zyPjs3k8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YLs1zyPjs3k8.npy", "labels": "/m/02fs_r", "caption": "A few digital hums followed by scratching" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/YfwhkCnOeyC0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YfwhkCnOeyC0.npy", "labels": "/m/028ght,/m/09x0r", "caption": "A man and woman speak and people clap and a bell rings" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part1/Y0G7rb74R-2A.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y0G7rb74R-2A.npy", "labels": "/m/02qldy,/m/05zppz,/m/09x0r", "caption": "A man speaking on a microphone as a crowd of people laugh followed by glass clinking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part9/Y8VOibo9Q_Dc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y8VOibo9Q_Dc.npy", "labels": "/m/09ddx,/m/09x0r,/m/0jbk", "caption": "A bird chirps and water splashes lightly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/Yjlwe9jtu5Gw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yjlwe9jtu5Gw.npy", "labels": "/m/01w250", "caption": "A couple of whistling sounds one after another" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/YwoadpeAGHUQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YwoadpeAGHUQ.npy", "labels": "/m/012ndj,/m/03j1ly,/m/03kmc9", "caption": "An fire engine sounds the siren as an engine idles and a man speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y6aWnK1GyeJY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y6aWnK1GyeJY.npy", "labels": "/m/0463cq4,/m/09x0r", "caption": "A baby cries and women speak" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/YeNG6fEiAE8c.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YeNG6fEiAE8c.npy", "labels": "/m/07bgp,/m/07q0h5t,/m/09x0r", "caption": "Men laughing with goat bleating in background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YlYhwCRX2wNc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YlYhwCRX2wNc.npy", "labels": "/m/04brg2,/m/09x0r", "caption": "Water splashes and a woman speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/YdP5DbAzTl5M.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YdP5DbAzTl5M.npy", "labels": "/m/019jd,/m/02rlv9,/m/07yv9,/m/09x0r", "caption": "A motorboat engine running and a man speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part9/Y86dNVnTwH6U.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y86dNVnTwH6U.npy", "labels": "/m/09x0r,/m/0llzx", "caption": "Hissing followed by sewing machine running" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/YdZDgJzGtLLU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YdZDgJzGtLLU.npy", "labels": "/m/07pqc89", "caption": "Water splashing with some rustling and wind blowing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YLvhvAA11oxE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YLvhvAA11oxE.npy", "labels": "/m/07yv9,/m/09x0r,/m/0h9mv,/m/0ltv,/t/dd00128", "caption": "A voice on loudspeakers is drowned out by tires squealing and engines repeatedly revving" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/YwnqUgK_-fo4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YwnqUgK_-fo4.npy", "labels": "/m/07bgp,/m/09x0r,/m/0jbk", "caption": "Several loud pops with people cheering" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YCMUuelJFJ7Q.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YCMUuelJFJ7Q.npy", "labels": "/m/07qjznl,/m/07qjznt", "caption": "A bell tolls followed by ticking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YNmmbNqmsPaY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YNmmbNqmsPaY.npy", "labels": "/m/07pb8fc,/m/07yv9,/m/0k4j", "caption": "An auto engine running loudly with some metallic sounds in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part27/Y_duNX6Vyd6g.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y_duNX6Vyd6g.npy", "labels": "/m/019jd,/m/02rlv9,/m/07yv9", "caption": "Wind blowing hard and a loud humming engine" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/YjinJkonlrWc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YjinJkonlrWc.npy", "labels": "/m/09ct_,/m/09x0r", "caption": "The wind is blowing, a motor is buzzing and vibration is present, and an adult male is speaking in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/YzIgGMlZENTs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YzIgGMlZENTs.npy", "labels": "/m/07qdb04,/m/09ddx,/m/09x0r", "caption": "A duck quacks followed by a man talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part24/YVeCSHwtkBZU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YVeCSHwtkBZU.npy", "labels": "/m/012n7d,/m/03j1ly,/m/03kmc9", "caption": "A police siren going off" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YAgaiowyYt88.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YAgaiowyYt88.npy", "labels": "/m/02dgv", "caption": "A door slamming shut" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YLBe33dw9ezg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YLBe33dw9ezg.npy", "labels": "/m/09ct_,/m/09x0r", "caption": "Music playing in the background followed by a woman speaking through a speaker as an electronic toy motor buzzes" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YtfOIhQpYYe8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YtfOIhQpYYe8.npy", "labels": "/m/09ct_,/m/09x0r,/t/dd00129", "caption": "Loud rustling and the chop of a helicopter blade" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y5I8lmN8rwDM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y5I8lmN8rwDM.npy", "labels": "/m/01d380,/m/07k1x,/t/dd00125", "caption": "A loud machine running" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YR_g4RpU9mO0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YR_g4RpU9mO0.npy", "labels": "/m/019jd,/m/02rlv9,/m/07yv9", "caption": "Boat motor idles then accelerates" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y1wW0YJQ-Xa0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1wW0YJQ-Xa0.npy", "labels": "/m/07qlf79,/m/09x0r", "caption": "A group of people talking in the background as compressed air sprays while a tin can rattles followed by a man talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YkHIe4CfaccQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YkHIe4CfaccQ.npy", "labels": "/m/03fwl,/m/068hy,/m/0ch8v,/m/0jbk", "caption": "A goat baaing as footsteps shuffle on foliage followed by a series of licking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YOxUVcZmeiyI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YOxUVcZmeiyI.npy", "labels": "/m/07qjznl,/m/07qjznt", "caption": "A clock ticking as plastic clanks followed by a cuckoo bird cooing then music box music playing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YBOB65Nd0pXo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBOB65Nd0pXo.npy", "labels": "/m/02l6bg,/m/07yv9,/m/09ct_", "caption": "A helicopter engine running as wind blows heavily into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/YyhDw7PZje3g.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YyhDw7PZje3g.npy", "labels": "/m/01h3n,/m/09x0r,/t/dd00129", "caption": "A man speaks with wind blowing and buzzing of insects" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/YxbLW9Wt1Jsg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YxbLW9Wt1Jsg.npy", "labels": "/m/0llzx", "caption": "An engine running continuously together with clanking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YnLtNjMimLE0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YnLtNjMimLE0.npy", "labels": "/m/07pqc89,/m/0838f", "caption": "Water drips and splashes, birds sing quietly in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3ndid3jni7M.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3ndid3jni7M.npy", "labels": "/m/01g50p,/m/0284vy3,/m/06d_3,/m/07jdr,/m/07rwm0c", "caption": "A train running on railroad tracks drives by as a train horn blows several times alongside a railroad crossing signal ringing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YtJhVH3VIrnE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YtJhVH3VIrnE.npy", "labels": "/m/02dgv", "caption": "Wood cracking as metal clanks and slams against a wooden surface" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YWqXFAY4k79s.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YWqXFAY4k79s.npy", "labels": "/m/06mb1,/t/dd00038", "caption": "A girl speaks while rain pitter-patters followed by male sneezing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/YyRoKi7rhSRo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YyRoKi7rhSRo.npy", "labels": "/m/01jt3m,/m/0838f", "caption": "A toilet flushing followed by a person speaking in the distance as birds chirp in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/Yb1PXsfgQw5w.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yb1PXsfgQw5w.npy", "labels": "/m/01j3sz,/m/07r660_,/m/09x0r", "caption": "A group of people laughing followed by a man talking then more laughter" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YSL3wB5sDcdw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YSL3wB5sDcdw.npy", "labels": "/m/09t49,/m/0d31p", "caption": "Leaves rustling as a leaf blower operates and wind blows into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3XuyGJqaXv8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3XuyGJqaXv8.npy", "labels": "/m/068hy,/m/07rc7d9,/m/09x0r,/m/0bt9lr,/m/0jbk", "caption": "A man is speaking and a dog is barking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YB4SZwi9Ce3o.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YB4SZwi9Ce3o.npy", "labels": "/m/07q2z82,/m/07yv9,/m/09x0r,/m/0k4j", "caption": "A man speaking, accelerating a vehicle" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/YxYwpABpZed4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YxYwpABpZed4.npy", "labels": "/m/07ptfmf,/m/0dxrf", "caption": "A woman speeches while cooks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YSZ6CcXINiiE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YSZ6CcXINiiE.npy", "labels": "/m/014zdl,/m/07qsvvw,/m/09x0r", "caption": "A man speaks followed by a loud bursts and then laughter" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part0/Y-NsC63dA01g.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y-NsC63dA01g.npy", "labels": "/m/01yrx,/m/068hy,/m/07qrkrw,/m/09x0r,/m/0jbk", "caption": "An adult female speaks as a cat meows three times, and an electronic device plays in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YIsUG5SKWNZA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YIsUG5SKWNZA.npy", "labels": "/m/09x0r,/t/dd00002", "caption": "A woman whispering then yelling as an infant is crying followed by a man yelling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part4/Y2msevPMQB4M.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y2msevPMQB4M.npy", "labels": "/m/01d380,/m/07k1x", "caption": "A drilling sound with humming in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y7MLERaOgK_Y.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y7MLERaOgK_Y.npy", "labels": "/m/0llzx", "caption": "A child sings happily over the clattering of a running machine" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YNlKlRKz8OKI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YNlKlRKz8OKI.npy", "labels": "/m/015p6,/m/020bb7,/m/07pggtn", "caption": "A woman speaks followed by birds chirping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part24/YUhCzD6EBJBU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YUhCzD6EBJBU.npy", "labels": "/m/01d380,/m/07k1x,/m/0_ksk", "caption": "A power tool drilling followed by a man talking then wooden thump followed by a door closing shut" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3VHpLxtd498.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3VHpLxtd498.npy", "labels": "/m/015p6,/m/09x0r,/m/0h0rv", "caption": "Pigeons are coo- cooing as a man is yelling for someone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y6ZFU4PqXmoI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y6ZFU4PqXmoI.npy", "labels": "/m/019jd,/m/02rlv9,/m/07yv9,/m/09x0r", "caption": "A construction vehicle engine running and water splashing as wood crackles and snaps followed by electronic beeping and a man talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y11SEBDuoqSk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y11SEBDuoqSk.npy", "labels": "/m/07yv9,/m/0cmf2,/m/0k5j", "caption": "Vibrating followed by rapid gunshots with an airplane engine" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YnuZEAuAl8hQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YnuZEAuAl8hQ.npy", "labels": "/m/015p6,/m/09ddx,/m/0ch8v", "caption": "Ducks quack and honk" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YOVQMFBeCHq0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YOVQMFBeCHq0.npy", "labels": "/m/012n7d,/m/03j1ly,/m/03kmc9", "caption": "Sirens blaring from a vehicle passes by and starts to diminish in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YXz56Q2Q5j5c.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YXz56Q2Q5j5c.npy", "labels": "/m/07k1x,/m/083vt", "caption": "Rubbing occurs while the electric motor runs" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9z2OwpftxUE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9z2OwpftxUE.npy", "labels": "/m/0ngt1", "caption": "Thundering sounds while rain pours" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YSGaIvgwwWSE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YSGaIvgwwWSE.npy", "labels": "/m/06mb1,/m/0jb2l,/m/0ngt1", "caption": "Rain pitter-patters as thunder rumbles" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YSNIaYhri76w.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YSNIaYhri76w.npy", "labels": "/m/05tny_,/m/07rc7d9,/m/09x0r,/m/0bt9lr,/m/0ghcn6,/m/0jbk,/t/dd00129", "caption": "A dog barking followed by a man talking as footsteps walk on grass while a pig oinks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YtmLAXm1WlnE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YtmLAXm1WlnE.npy", "labels": "/m/01h3n,/m/03vt0,/m/0h2mp", "caption": "Woman speaking with fly buzzing around" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YbUTOsLXYyxg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YbUTOsLXYyxg.npy", "labels": "/m/01j3sz,/m/09x0r", "caption": "Men speak followed by laughing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YAj_VMUSNjNM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YAj_VMUSNjNM.npy", "labels": "/m/02mk9,/m/07q2z82,/m/07yv9,/m/0k4j", "caption": "Humming of a powerful engine revving" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part1/Y0_ogYGDGDco.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y0_ogYGDGDco.npy", "labels": "/m/019jd,/m/034srq,/m/03m9d0z,/m/056ks2,/m/05kq4,/t/dd00092", "caption": "Wind blowing and water splashes with a man speaking over a radio" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YTOaQMYc79Mw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YTOaQMYc79Mw.npy", "labels": "/m/07yv9,/t/dd00130", "caption": "Vibrating and squealing form an engine" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YAtkD-3GjXMw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YAtkD-3GjXMw.npy", "labels": "/m/032s66,/m/04zjc", "caption": "Singing and music with faint gunshots" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/YfK4QBQZ6i7w.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YfK4QBQZ6i7w.npy", "labels": "/m/01j3sz,/m/07rgt08,/m/07s04w4", "caption": "Woman laughs loudly as others chuckle as well" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/Yn4VktYihtJU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yn4VktYihtJU.npy", "labels": "/m/07swgks,/m/09x0r", "caption": "Light wind with people screaming and engine running" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y14izd_i3ryE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y14izd_i3ryE.npy", "labels": "/m/07rv9rh,/m/09x0r,/m/0jbk", "caption": "A man talking followed by another man talking through a megaphone as wind blows into a microphone and a vehicle engine runs" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YPZBUdlKwX04.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YPZBUdlKwX04.npy", "labels": "/m/09x0r,/m/0j2kx,/m/0j6m2", "caption": "A man shouting as a stream of water splashes and a crowd of people talk in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YSNIaYhri76w.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YSNIaYhri76w.npy", "labels": "/m/05tny_,/m/07rc7d9,/m/09x0r,/m/0bt9lr,/m/0ghcn6,/m/0jbk,/t/dd00129", "caption": "A pig squeals and dogs bark followed by a man speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/YhDMHIDJdfDA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YhDMHIDJdfDA.npy", "labels": "/m/01d3sd,/t/dd00125", "caption": "A man snoring while someone chuckles in background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/Yh0M4RS8p_mo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yh0M4RS8p_mo.npy", "labels": "/m/01j3sz,/m/0463cq4", "caption": "A man laughs followed by a baby crying" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YW7OJevEgq7w.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YW7OJevEgq7w.npy", "labels": "/m/05tny_,/m/068hy,/m/07rc7d9,/m/0bt9lr,/m/0jbk", "caption": "A dog barking and panting" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part1/Y0_K6OKtoBBU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y0_K6OKtoBBU.npy", "labels": "/m/01yrx,/m/068hy,/m/07qrkrw,/m/0jbk", "caption": "Some rustling then silence then traffic passing in the distance with a cat meowing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YlmPMhs-9IYE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YlmPMhs-9IYE.npy", "labels": "/m/07yv9,/m/09x0r,/m/0k4j,/m/0ltv", "caption": "A vehicle engine revving as a crowd of people talk and whistle in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/YjXkLS_QzUrI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YjXkLS_QzUrI.npy", "labels": "/m/068hy,/m/07qrkrw", "caption": "A domestic animal meows" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y0ury8KHQdL4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y0ury8KHQdL4.npy", "labels": "/m/01m2v,/m/0316dw,/m/09x0r", "caption": "A man is speaking while typing on a keyboard" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3VHpLxtd498.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3VHpLxtd498.npy", "labels": "/m/015p6,/m/09x0r,/m/0h0rv", "caption": "Humming with coos of pigeons and brief distant speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9hxFqltp3xw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9hxFqltp3xw.npy", "labels": "/m/07qlf79,/m/09x0r", "caption": "A woman speaks with some rustling and hissing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YLvMA1Wcgu3w.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YLvMA1Wcgu3w.npy", "labels": "/m/09ld4", "caption": "Frogs croaking together with a man speaking followed by rustling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part24/YW4GEwnXc9tQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YW4GEwnXc9tQ.npy", "labels": "/m/09ld4", "caption": "A woman speaks with chirping frogs and distant music playing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YsqWyxUObwkw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YsqWyxUObwkw.npy", "labels": "/m/019jd,/m/02rlv9,/m/07yv9", "caption": "Plastic camera muffling followed by a ripcord being pulled then a motorboat engine starting up" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YC_ga5m6nOhI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YC_ga5m6nOhI.npy", "labels": "/m/06hck5,/m/06wzb,/m/07rjwbb", "caption": "Hissing and ticking with whistling of a horn" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part4/Y2ymiXjImwGs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y2ymiXjImwGs.npy", "labels": "/m/012ndj,/m/01bjv,/m/09x0r", "caption": "A fire siren with people talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YHxZADVzNIqs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YHxZADVzNIqs.npy", "labels": "/m/015p6,/m/020bb7,/m/07pggtn", "caption": "Birds chirping and water trickling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/YptIksg9KEac.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YptIksg9KEac.npy", "labels": "/m/068hy,/m/07rc7d9,/m/0bt9lr,/m/0jbk,/t/dd00136", "caption": "A person clapping followed by a dog barking then wood clanking as birds chirp and gusts of wind blow in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/YpO8kbg9IJnc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YpO8kbg9IJnc.npy", "labels": "/m/0130jx,/m/02jz0l,/m/0838f", "caption": "Speaking followed by water running" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part9/Y8BPTQO_cx7E.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y8BPTQO_cx7E.npy", "labels": "/m/028ght", "caption": "Male speaking and then laughter and applause" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part4/Y2j8pxiFvElM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y2j8pxiFvElM.npy", "labels": "/m/01yrx,/m/068hy,/m/07qrkrw,/m/0jbk", "caption": "A cat is meowing in a quiet environment" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9vZDsGjyh5M.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9vZDsGjyh5M.npy", "labels": "/m/07r04,/m/07yv9,/m/0k4j", "caption": "An engine running" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9MgGaTbmc6g.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9MgGaTbmc6g.npy", "labels": "/m/02mk9,/m/07q2z82,/m/07yv9,/m/0k4j,/t/dd00066", "caption": "A vehicle accelerating and revving while tires are skidding" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YZNEZLlDVgrE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YZNEZLlDVgrE.npy", "labels": "/m/01h3n,/m/03vt0,/m/0h2mp", "caption": "A man speaks as bees buzz in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YlX3k5p2I_g0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YlX3k5p2I_g0.npy", "labels": "/m/014yck,/m/02mk9,/m/07yv9,/m/09x0r,/m/0cmf2,/m/0k5j", "caption": "Man speaks followed by second man speaking then aircraft engine whines while starting" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/Yeu5bq0A3XVQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yeu5bq0A3XVQ.npy", "labels": "/m/03q5_w,/m/09x0r", "caption": "A man exhaling then gasping for air followed by talking and gurgling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YSE_3nszEw7o.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YSE_3nszEw7o.npy", "labels": "/m/06wzb,/m/07rjwbb", "caption": "Hissing and clinking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YJQz40TkjymY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YJQz40TkjymY.npy", "labels": "/m/01m2v,/m/0316dw", "caption": "Typing on a keyboard is occurring in a quiet environment" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/YjYPU6aSDo88.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YjYPU6aSDo88.npy", "labels": "/m/014yck,/m/07yv9,/m/09x0r,/m/0k5j", "caption": "Loud humming with wind blowing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YEcihYbSlyck.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YEcihYbSlyck.npy", "labels": "/m/01bjv,/m/07yv9,/m/09x0r", "caption": "Train horns honking as wind blows into a microphone while a group of people talk and an electronic beep repeatedly sounds during a vehicle engine running idle" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YFJkvAMLmejY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YFJkvAMLmejY.npy", "labels": "/m/0912c9,/m/09x0r,/t/dd00125", "caption": "People speak followed by a loud air horn and people laughing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/YdYZSKX7vuRI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YdYZSKX7vuRI.npy", "labels": "/m/01d3sd,/m/09x0r", "caption": "Snoring occurs and then slight rustling, then an adult male speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YD1Sy7kRoaR8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YD1Sy7kRoaR8.npy", "labels": "/m/03k3r,/m/07rv9rh,/m/09x0r,/m/0jbk", "caption": "A woman speaks via a public address system" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part1/Y0_K6OKtoBBU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y0_K6OKtoBBU.npy", "labels": "/m/01yrx,/m/068hy,/m/07qrkrw,/m/0jbk", "caption": "A door creaking open followed by wind blowing and leaves rustling then a cat meowing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YC4JwGJQ2dUA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YC4JwGJQ2dUA.npy", "labels": "/m/02qldy,/m/05zppz,/m/09x0r,/m/0brhx", "caption": "A man yelling very loudly while speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YmVjub3o_IxE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YmVjub3o_IxE.npy", "labels": "/m/02jz0l,/m/09x0r,/t/dd00125", "caption": "A man talking while another person talks in the distance as water trickles and birds chirp in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y0qbHT34qTZE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y0qbHT34qTZE.npy", "labels": "/m/032s66,/m/06q74,/m/09x0r", "caption": "A man speaks then a sudden explosion which is followed by smaller explosions and thunder" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/YjjfUaMQaG1A.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YjjfUaMQaG1A.npy", "labels": "/m/01d380,/m/09x0r", "caption": "A man talking followed by plastic clacking then a power tool drilling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YQRtuOWWya30.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YQRtuOWWya30.npy", "labels": "/m/0dxrf", "caption": "Splashing water with some rustling followed by a man speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YAKHZMg9ba30.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YAKHZMg9ba30.npy", "labels": "/m/07rv9rh,/m/09x0r,/m/0jbk", "caption": "A man talking as a man laughs then talks in the background while a horse snorts and trots" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YESjMIqrvRj4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YESjMIqrvRj4.npy", "labels": "/m/09t49,/t/dd00092", "caption": "Wind with rain followed by thunder" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part1/Y096oTVzc5Gs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y096oTVzc5Gs.npy", "labels": "/m/09x0r,/m/0bt9lr,/m/0jbk,/t/dd00136", "caption": "A woman talking as a dog snorts followed by an air ventilation system running" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YrjUrB1WUpcI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YrjUrB1WUpcI.npy", "labels": "/m/07swgks", "caption": "A faucet pouring water then turning off followed by water draining down a pipe" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YCO6-i8NLbeo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YCO6-i8NLbeo.npy", "labels": "/m/03fwl,/m/09x0r,/m/0jbk", "caption": "A man talking as goats baa while wind blows into a microphone followed by another goat baaing and a metal gate sliding" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YBn4lc01q9vE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBn4lc01q9vE.npy", "labels": "/m/0130jx,/m/02jz0l,/m/03dnzn,/m/0838f", "caption": "Water splashing followed by women speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/YoNHCc_izsDE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YoNHCc_izsDE.npy", "labels": "/m/01j3sz,/m/07rrlb6", "caption": "Water splashing as a baby is laughing and birds chirp in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4pv3w--cRrA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4pv3w--cRrA.npy", "labels": "/m/09t49", "caption": "Small quick vibrations" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3ejndVEAcmQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3ejndVEAcmQ.npy", "labels": "/m/01yrx,/m/068hy,/m/07qrkrw,/m/07r81j2,/m/0jbk", "caption": "A cat meows and hisses" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/Ybgbnu5YKTDg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ybgbnu5YKTDg.npy", "labels": "/m/032s66", "caption": "A man speaking as a muffled helicopter engine runs over an intercom before and after several gunshots firing followed by an electronic beep then radio static" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3fomsZXG3aM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3fomsZXG3aM.npy", "labels": "/m/07q2z82,/m/07yv9,/t/dd00066", "caption": "A vehicle engine running idle then revving after two metal clicks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y14izd_i3ryE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y14izd_i3ryE.npy", "labels": "/m/07rv9rh,/m/09x0r,/m/0jbk", "caption": "A man speaks as an engine runs and wind rushes by, another man speaks over a loudspeaker" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y22L_3pBa1AI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y22L_3pBa1AI.npy", "labels": "/m/07yv9,/m/0k4j,/t/dd00134", "caption": "Race cars are passing by" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y6TO9PEGpZcQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y6TO9PEGpZcQ.npy", "labels": "/m/012n7d,/m/012ndj,/m/03j1ly,/m/03kmc9", "caption": "An emergency vehicle sounds siren followed by a vehicle engine idling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/YoNHCc_izsDE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YoNHCc_izsDE.npy", "labels": "/m/01j3sz,/m/07rrlb6", "caption": "Splashing, a baby laughs, then a woman laughs" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YIdBDl9Wr51A.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YIdBDl9Wr51A.npy", "labels": "/m/07rqsjt", "caption": "A man speaks with several loud explosions and deep booming whooshes" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y2KR0C5ysO8o.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y2KR0C5ysO8o.npy", "labels": "/m/02mk9,/m/07pb8fc,/m/07q2z82,/m/07yv9,/m/09x0r,/t/dd00066", "caption": "A vehicle engine is revving followed by a man speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/Yktc_tJxw8sc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yktc_tJxw8sc.npy", "labels": "/m/0463cq4", "caption": "Low scratching groaning" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part0/Y-FW109cbv0g.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y-FW109cbv0g.npy", "labels": "/m/01hsr_,/m/09x0r", "caption": "Speech followed by quietness and a man speaks and laughs" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3qrVku794u0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3qrVku794u0.npy", "labels": "/m/02fs_r,/m/09x0r,/m/0fx9l", "caption": "Man talking with cranking noises in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part9/Y8DQfjqPCTI8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y8DQfjqPCTI8.npy", "labels": "/m/01h3n,/m/03vt0,/m/0h2mp", "caption": "Outside noises of insects buzzing around, birds communicating and a man exchanging information with another man" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part9/Y8DLcBdC5UrE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y8DLcBdC5UrE.npy", "labels": "/m/07swgks", "caption": "Water is flowing and dripping then suddenly something is broken and birds are communicating in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/YcPiSd5nJLrI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YcPiSd5nJLrI.npy", "labels": "/m/014zdl,/m/07pxg6y,/m/07qsvvw", "caption": "A group of people screaming and laughing as firecrackers ignite then explode followed by a muffled explosion" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4IeDBwyQ9ZQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4IeDBwyQ9ZQ.npy", "labels": "/m/04brg2", "caption": "Woman speaking, plastic container opening" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YHdxfbpnd2-8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YHdxfbpnd2-8.npy", "labels": "/m/01w250", "caption": "A man talking then whistling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YlHh0SwUhP8U.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YlHh0SwUhP8U.npy", "labels": "/m/09ddx", "caption": "Birds chirp followed by some clicking then gunshots" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/Yk1QxQ4jJaEQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yk1QxQ4jJaEQ.npy", "labels": "/m/07r04,/m/07yv9,/m/09x0r,/t/dd00129", "caption": "An engine idling and a man speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/YwFiCblfZ-vg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YwFiCblfZ-vg.npy", "labels": "/m/07pqc89,/m/09x0r", "caption": "A man speaks with some mechanical humming and another man speaking faintly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part15/YGSHcgY6ATkQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YGSHcgY6ATkQ.npy", "labels": "/m/0316dw", "caption": "A male voice talking followed by typing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YS8k47ME-YT4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YS8k47ME-YT4.npy", "labels": "/m/06mb1,/m/0jb2l,/m/0ngt1", "caption": "Heavy rainfall with a brief muffled thunder from outside" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YnU-AI3Cmc3M.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YnU-AI3Cmc3M.npy", "labels": "/m/015p6,/m/0h0rv,/t/dd00129", "caption": "A pigeon cooing followed by bird wings flapping as wind blows into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YSNy_axSCoyw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YSNy_axSCoyw.npy", "labels": "/m/07qjznl", "caption": "The rhythmic and repeated ticktock of a clock" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/Ybpv_LneHmfU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ybpv_LneHmfU.npy", "labels": "/m/014yck,/m/07yv9,/m/0cmf2,/m/0k5j,/t/dd00129", "caption": "An engine running" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3Sml1wHcuxo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3Sml1wHcuxo.npy", "labels": "/m/01g50p,/m/0284vy3,/m/06d_3,/m/07jdr,/m/07rwm0c", "caption": "A railroad horn sounds repeatedly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YKJhGuhNHToA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YKJhGuhNHToA.npy", "labels": "/m/083vt", "caption": "Repeated scraping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YAagLJkfrFMk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YAagLJkfrFMk.npy", "labels": "/m/01jt3m", "caption": "A toilet flushing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part15/YG3YO2unWz7k.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YG3YO2unWz7k.npy", "labels": "/m/04_sv,/m/07yv9,/t/dd00128", "caption": "An engine chugging slowly followed by the engine revving" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YESjMIqrvRj4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YESjMIqrvRj4.npy", "labels": "/m/09t49,/t/dd00092", "caption": "Rain pitter-patters as thunder cracks and the wind blows" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/Yram-QPKSQYc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yram-QPKSQYc.npy", "labels": "/m/09ct_", "caption": "A helicopter blades running" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part27/Y_ezm-TpKj1w.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y_ezm-TpKj1w.npy", "labels": "/m/07q2z82,/m/09x0r,/m/0k4j", "caption": "Humming of a revving idling engine with people speaking in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part19/YMOxddxW5PXs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YMOxddxW5PXs.npy", "labels": "/m/09x0r,/m/0dxrf", "caption": "A man speaking with frying food and stirring sounds" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part9/Y8nUqSYC66mI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y8nUqSYC66mI.npy", "labels": "/m/0j6m2", "caption": "Water splashes and people scream and speak and laugh" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y14ekd4nkpwc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y14ekd4nkpwc.npy", "labels": "/t/dd00002", "caption": "An infant crying followed by a man laughing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4KObP7cREWw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4KObP7cREWw.npy", "labels": "/m/02mk9,/m/07yv9,/m/0k4j", "caption": "A car door slamming shut as a vehicle engine is running idle then revving" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/Yi2yhbckq3p0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yi2yhbckq3p0.npy", "labels": "/m/012f08,/m/04_sv,/m/07yv9,/m/0k4j", "caption": "Road traffic with engines followed by a shrill car alarm then whistles and several loud car horns blaring" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YrE6BJ0Bo4w4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YrE6BJ0Bo4w4.npy", "labels": "/m/02jz0l,/m/09x0r,/t/dd00125", "caption": "An adult female speaks, water runs from a faucet and splashes, and then the adult female speaks again" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/YzFzPOsOKog4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YzFzPOsOKog4.npy", "labels": "/m/01h3n,/m/03vt0,/m/0h2mp", "caption": "Buzzing sound with click and clack in background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/Ym_NCf-q4Gn0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ym_NCf-q4Gn0.npy", "labels": "/m/04_sv,/m/07qnq_y,/m/07yv9,/t/dd00128", "caption": "A motorcycle engine is idling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/Ye2rScj9UyMs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ye2rScj9UyMs.npy", "labels": "/m/015p6,/m/0h0rv,/t/dd00125", "caption": "Doves cooing quietly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YmUGmCSNETcg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YmUGmCSNETcg.npy", "labels": "/m/07ptfmf,/m/0dxrf", "caption": "Sizzling and a female speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part4/Y2ceUOv8A3FE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y2ceUOv8A3FE.npy", "labels": "/m/01g50p,/m/0284vy3,/m/06d_3,/m/07jdr", "caption": "A train horn blowing multiple times as a train runs on railroad tracks while a man and a young kid talk in the background alongside birds cooing in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YXamQAY_WXRY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YXamQAY_WXRY.npy", "labels": "/m/0j6m2", "caption": "Man speaking water moving in background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/Yq3SEOW2m4WY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yq3SEOW2m4WY.npy", "labels": "/m/01g50p,/m/0284vy3,/m/06d_3,/m/07jdr,/m/07rwm0c", "caption": "Railroad crossing signal followed by a train passing and blowing horn" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YQv1HXaT-28U.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YQv1HXaT-28U.npy", "labels": "/m/07qsvvw", "caption": "Something sprayed and popped with people laughing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YPkmpxrsidZM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YPkmpxrsidZM.npy", "labels": "/m/028ght,/m/09x0r", "caption": "A crowd is applauding, an adult female speaks, the crowd laughs, claps and whistles, and then another adult female begins to speak" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part24/YVE6Ku0-ucUM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YVE6Ku0-ucUM.npy", "labels": "/m/07qsvvw,/m/09x0r", "caption": "A man speaks followed by a popping noise and laughter" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/YgkWd1HugK2w.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YgkWd1HugK2w.npy", "labels": "/m/015p6,/m/0h0rv,/t/dd00129", "caption": "Pigeons coo and flap their wings" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YJQz40TkjymY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YJQz40TkjymY.npy", "labels": "/m/01m2v,/m/0316dw", "caption": "Typing on a keyboard is ongoing in a quiet environment" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/Yg5l3Bz6lWnc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yg5l3Bz6lWnc.npy", "labels": "/m/01h3n,/m/03vt0", "caption": "Wood lightly shuffling as insects buzz and birds chirp in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YU3CAjsm1sec.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YU3CAjsm1sec.npy", "labels": "/m/01yrx,/m/068hy,/m/07qrkrw,/m/0jbk", "caption": "Several cats meowing followed by a man singing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YDNtF_mGzQes.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YDNtF_mGzQes.npy", "labels": "/m/07r04,/m/07yv9,/m/09x0r", "caption": "A group of children talking as a man talks over an intercom while a large truck engine runs followed by compressed air releasing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/Yo7-X8DAToGc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yo7-X8DAToGc.npy", "labels": "/m/012f08,/m/07yv9,/m/0ltv,/t/dd00134", "caption": "Auto driving quickly past engine sound fading" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YEp72tyiL3as.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YEp72tyiL3as.npy", "labels": "/m/0ngt1", "caption": "A loud thunder cracking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YnLZeG9LaLgw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YnLZeG9LaLgw.npy", "labels": "/m/07yv9,/m/0k4j,/m/0ltv", "caption": "Humming of a loud powerful engine starting and speeding into the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/YpTJKJxaheI8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YpTJKJxaheI8.npy", "labels": "/m/07qjznl,/m/07qjznt", "caption": "A quiet ticking sound at regular intervals, interval shortens near the end, and a man coughs quietly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YSoO1HhaEc9Q.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YSoO1HhaEc9Q.npy", "labels": "/m/09x0r,/t/dd00018", "caption": "Mechanical noises followed by pigs oinking and a man talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YS0YE96w0YRk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YS0YE96w0YRk.npy", "labels": "/m/028ght", "caption": "A man speaks, and a crowd applauds" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part0/Y-CcGuq0yoKo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y-CcGuq0yoKo.npy", "labels": "/m/02qldy,/m/02zsn,/m/09x0r", "caption": "A woman speaking on a microphone as a kid yells in the distance with periodic audio static clicks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part19/YMvHpNzDpC6Q.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YMvHpNzDpC6Q.npy", "labels": "/m/012f08,/m/03q5_w,/m/07yv9,/m/09x0r,/m/0k4j", "caption": "Male speech and then a burp" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3wrdPAeqjVI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3wrdPAeqjVI.npy", "labels": "/m/083vt,/m/09x0r", "caption": "Man speaking then a faint clicking noise" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y6ZFU4PqXmoI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y6ZFU4PqXmoI.npy", "labels": "/m/019jd,/m/02rlv9,/m/07yv9,/m/09x0r", "caption": "A vehicle engine works and then a man talks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4KObP7cREWw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4KObP7cREWw.npy", "labels": "/m/02mk9,/m/07yv9,/m/0k4j", "caption": "Engine running and revving" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/Yrp3CQsWxVgE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yrp3CQsWxVgE.npy", "labels": "/m/07yv9,/m/0912c9,/m/0k4j,/t/dd00128", "caption": "A vehicle horn honking a melody" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part7/Y5t6tSW0yT40.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y5t6tSW0yT40.npy", "labels": "/m/07qlf79", "caption": "A sprayer sprays with low machine noise in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YC8kR19NvynA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YC8kR19NvynA.npy", "labels": "/m/02qldy,/m/05zppz,/m/09x0r", "caption": "A man speaking on a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/Yyau2WIRkxb8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yyau2WIRkxb8.npy", "labels": "/m/09ct_", "caption": "A whirring motor run uninterrupted" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YFfUqv0Vv3ME.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YFfUqv0Vv3ME.npy", "labels": "/m/03k3r,/m/09x0r,/m/0jbk", "caption": "A horse walks while an adult male speaks, an adult female speaks briefly, and roosters are crowing in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/YxIztYnMIWUA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YxIztYnMIWUA.npy", "labels": "/m/01hnzm,/m/07cx4,/m/07pp8cl", "caption": "A telephone rings repeatedly, with some buzzing in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/YglAeihz0NAM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YglAeihz0NAM.npy", "labels": "/m/09x0r,/m/0ytgt,/t/dd00129", "caption": "Wind blowing and waves crashing with people speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3ghVB-KaU_E.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3ghVB-KaU_E.npy", "labels": "/m/07rjwbb", "caption": "A man is speaking with hissing background noises" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/Yj1AiqT5oHZc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yj1AiqT5oHZc.npy", "labels": "/m/02fs_r,/m/09x0r,/t/dd00125", "caption": "A man speaks followed by a digital beep" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YlYhwCRX2wNc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YlYhwCRX2wNc.npy", "labels": "/m/04brg2,/m/09x0r", "caption": "A woman talking as water trickles followed by porcelain dishes clanking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YDc2WEiRk0rA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YDc2WEiRk0rA.npy", "labels": "/m/07qlf79", "caption": "Continuous spraying up and down" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YAFgGoY8Ihhg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YAFgGoY8Ihhg.npy", "labels": "/m/03j1ly,/m/03kmc9,/m/04qvtq", "caption": "Wind and then a short ambulance siren repeats several times" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y1OyEgzXCkYE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1OyEgzXCkYE.npy", "labels": "/m/02qldy,/m/05zppz,/m/09x0r", "caption": "A man speaking into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YHZ9O6sc7cLA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YHZ9O6sc7cLA.npy", "labels": "/m/05tny_,/m/07rc7d9,/m/0bt9lr", "caption": "Female speaking and a dog barking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y6ZwYgzcN6Is.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y6ZwYgzcN6Is.npy", "labels": "/m/09x0r,/m/0j6m2,/t/dd00129", "caption": "A female speech and laughing with running water" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YTQr9v-PQOc4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YTQr9v-PQOc4.npy", "labels": "/m/01hsr_", "caption": "A person sneezes and coughs" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part1/Y0On6-JiVwRs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y0On6-JiVwRs.npy", "labels": "/m/01yrx,/m/068hy,/m/09t49,/m/0jbk,/t/dd00128", "caption": "Cats meowing and then wind" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3rna9zo5ZOs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3rna9zo5ZOs.npy", "labels": "/m/02qldy,/m/05zppz,/m/09x0r", "caption": "A man is speaking with crowd noise in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YBvw2gv1fcZw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBvw2gv1fcZw.npy", "labels": "/m/03q5_w,/m/09x0r", "caption": "A click followed by loud burps and laughing from young girls" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y27HIamF8pKo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y27HIamF8pKo.npy", "labels": "/m/01g50p,/m/0284vy3,/m/06d_3,/m/07jdr,/m/07rwm0c", "caption": "A running train and then a train whistle" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y1L_OyngNZMA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1L_OyngNZMA.npy", "labels": "/m/01j3sz,/m/07p6fty,/m/09x0r", "caption": "A man speaking on a microphone followed by another man speaking on a microphone as a crowd of people laugh and cheer" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/Yh3UhoHIMfpw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yh3UhoHIMfpw.npy", "labels": "/m/02_41,/m/03m9d0z,/t/dd00092", "caption": "Some rustling with a very high toned beep" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/YA0E_UiD-fR4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YA0E_UiD-fR4.npy", "labels": "/m/02fs_r", "caption": "Engine working, beeping and a scraping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YHZ9O6sc7cLA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YHZ9O6sc7cLA.npy", "labels": "/m/05tny_,/m/07rc7d9,/m/0bt9lr", "caption": "A woman speaks followed by a dog barking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/Yc0V_HAul7rI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yc0V_HAul7rI.npy", "labels": "/m/01j3sz,/m/07rgt08,/m/09x0r", "caption": "A group of people laughing followed by a young man talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/YzF3xXn6NTyU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YzF3xXn6NTyU.npy", "labels": "/m/0j6m2", "caption": "A large volume of water is running, splashing and gurgling, a sneeze occurs, and two adult females speak" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/Yy-RSojxgkDo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yy-RSojxgkDo.npy", "labels": "/m/015p6,/m/068hy,/m/07pggtn", "caption": "A man speaks then a small bird chirps" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part27/Y_9mgOkzm-xg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y_9mgOkzm-xg.npy", "labels": "/m/09x0r,/m/0dxrf,/t/dd00125", "caption": "A man talking while wood clanks on a metal pan followed by gravel crunching as food and oil sizzle" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part24/YVQnmlf2OsUg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YVQnmlf2OsUg.npy", "labels": "/m/09ct_", "caption": "A toy helicopter flying" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3n05BjV7r7M.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3n05BjV7r7M.npy", "labels": "/m/02dgv,/m/02y_763", "caption": "A series of metal clanks and rattling as a small motor operates and hums" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YOUUckswAaNI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YOUUckswAaNI.npy", "labels": "/m/02dgv", "caption": "A man is speaking as birds are chirping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3wV3ST-c4PE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3wV3ST-c4PE.npy", "labels": "/m/07qjznl", "caption": "Tick took of a clock" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/YgkWd1HugK2w.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YgkWd1HugK2w.npy", "labels": "/m/015p6,/m/0h0rv,/t/dd00129", "caption": "Several pigeons cooing and flapping wings repeatedly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YOTLtzk0W4zg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YOTLtzk0W4zg.npy", "labels": "/m/07yv9,/m/09x0r,/m/0k4j,/t/dd00128,/t/dd00130", "caption": "An engine running and a male speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YCeRoaEcqUgM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YCeRoaEcqUgM.npy", "labels": "/m/019jd,/m/02rlv9,/m/07yv9", "caption": "A motorboat driving by as water splashes followed by wind blowing into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y1Og2TJ3bXW0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1Og2TJ3bXW0.npy", "labels": "/m/07yv9,/m/0cmf2,/m/0k5j,/t/dd00128", "caption": "An aircraft engine running then slowing down after a plastic click" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YWUpeplQr3A4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YWUpeplQr3A4.npy", "labels": "/m/01d380", "caption": "A loud shrill followed by a power tool drilling and a man screaming while liquid pours and splatters" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/Yg_P29ucKj78.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yg_P29ucKj78.npy", "labels": "/m/07yv9,/m/0k4j,/t/dd00134", "caption": "Race car shifting gears" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part38/YuhSDBwVrEdo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YuhSDBwVrEdo.npy", "labels": "/m/01w250", "caption": "The wind is blowing, and a person is whistling a tune" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/Ye6jSpvTvfJ0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ye6jSpvTvfJ0.npy", "labels": "/m/06mb1,/m/0cj0r", "caption": "Rain pouring heavily as gusts of wind blow and thunder roars in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YCM49C3RkzV8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YCM49C3RkzV8.npy", "labels": "/m/02qldy,/m/02zsn,/m/09x0r", "caption": "Female speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part9/Y7cHRSfbp7tc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y7cHRSfbp7tc.npy", "labels": "/m/02dgv,/m/07r4wb8,/m/09x0r", "caption": "A group of people talking and dinnerware clanking followed by quiet knocking on wood" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part0/Y-aYumc8KoXg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y-aYumc8KoXg.npy", "labels": "/m/07yv9,/m/0912c9,/m/0k4j", "caption": "Distant honking and humming of an engine as a car approached with a loud honk nearby" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YQoEal_hKz4Q.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YQoEal_hKz4Q.npy", "labels": "/m/032s66,/m/04zjc", "caption": "Rapid gunfire and then male speech on a radio and more gunfire" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YSePTNAN7s-w.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YSePTNAN7s-w.npy", "labels": "/m/01jt3m,/m/0838f", "caption": "A woman talking followed by a young girl talking as a toilet flushes" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/YeUecAF626A8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YeUecAF626A8.npy", "labels": "/m/07yv9,/m/09x0r,/m/0k4j,/m/0ltv", "caption": "An engine revving" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YbIV3bJZpkgA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YbIV3bJZpkgA.npy", "labels": "/m/07yv9,/m/09ct_", "caption": "A helicopter engine and propellers" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part7/Y5eSRL3PRHzo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y5eSRL3PRHzo.npy", "labels": "/m/028ght,/m/03qtwd", "caption": "A crowd applauds" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YWmDe2xbnSY4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YWmDe2xbnSY4.npy", "labels": "/m/07qsvvw", "caption": "Bursts with groans and grunts" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YBDpU2Qh77NE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBDpU2Qh77NE.npy", "labels": "/m/015p6,/m/020bb7,/m/07pggtn", "caption": "A bird whistling followed by a group of people softly talking then an electronic beep" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y7RMpCCkQks0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y7RMpCCkQks0.npy", "labels": "/m/07rjwbb", "caption": "Consistent ripping and tearing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/YxIztYnMIWUA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YxIztYnMIWUA.npy", "labels": "/m/01hnzm,/m/07cx4,/m/07pp8cl", "caption": "An old fashioned telephone ring occurs repeatedly, and buzzing is present in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4eyY1w2QyM0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4eyY1w2QyM0.npy", "labels": "/m/0j6m2", "caption": "Waves crash against a shore" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part1/Y0On6-JiVwRs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y0On6-JiVwRs.npy", "labels": "/m/01yrx,/m/068hy,/m/09t49,/m/0jbk,/t/dd00128", "caption": "A cat meowing as wind blows into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/Yd6gu2w19YQo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yd6gu2w19YQo.npy", "labels": "/m/01j3sz", "caption": "An baby laughing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YXJba7pTbpD0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YXJba7pTbpD0.npy", "labels": "/m/07qlf79", "caption": "Several varying hisses" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/Ycz0FSQDVBMw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ycz0FSQDVBMw.npy", "labels": "/m/06wzb,/m/07rjwbb", "caption": "Hissing and chugging with brief muffled speech" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YrE6BJ0Bo4w4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YrE6BJ0Bo4w4.npy", "labels": "/m/02jz0l,/m/09x0r,/t/dd00125", "caption": "A woman speaks, and faucet water runs" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YZNEZLlDVgrE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YZNEZLlDVgrE.npy", "labels": "/m/01h3n,/m/03vt0,/m/0h2mp", "caption": "Buzzing nearby insects with men speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/Yd1tL-9BILy8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yd1tL-9BILy8.npy", "labels": "/m/015p6,/m/020bb7,/m/07r_25d,/m/0h0rv", "caption": "Pigeons cooing followed by camera muffling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/Yz4MeV9IGVo0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yz4MeV9IGVo0.npy", "labels": "/m/01bjv,/m/07yv9,/m/09x0r", "caption": "Humming from loud engines with men speaking over the radio" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part15/YFi4-IqJo2xQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YFi4-IqJo2xQ.npy", "labels": "/m/02mk9,/m/07rqsjt,/m/07yv9,/m/0k4j", "caption": "A vehicle engine revving several times with a series of compressed air releasing and plastic pops" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YIKnx3hJv1bs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YIKnx3hJv1bs.npy", "labels": "/m/07qlf79", "caption": "Spraying and hissing with some light vibrations" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/YoOMtaqvQ3_M.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YoOMtaqvQ3_M.npy", "labels": "/m/07yv9,/m/09ct_,/m/0k5j", "caption": "Aircraft is in flight while the wind blows" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/Yr2KhpX_QgXA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yr2KhpX_QgXA.npy", "labels": "/m/02mk9,/m/02x984l,/m/09x0r", "caption": "Men talking followed by an engine starting" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YLP_DzNUkAKY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YLP_DzNUkAKY.npy", "labels": "/m/06wzb,/m/07rjwbb", "caption": "Humming of an engine with people speaking in the distance followed by hissing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YrJVXE6Axtrg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YrJVXE6Axtrg.npy", "labels": "/m/09x0r,/m/0llzx", "caption": "A man speaks and a machine runs with a continued speech" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YaZAXO2WZn84.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YaZAXO2WZn84.npy", "labels": "/m/06wzb,/m/07rjwbb", "caption": "Humming with some hissing and whistling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/Yazh_-OkQ-uI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yazh_-OkQ-uI.npy", "labels": "/m/07bgp,/m/07q0h5t,/m/09x0r", "caption": "A woman talks briefly as several goats bleat including one that has high pitched bleats. A crunch is followed by a man speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y7JWHbs3gu1w.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y7JWHbs3gu1w.npy", "labels": "/m/01g50p,/m/0284vy3,/m/06d_3,/m/07jdr,/m/07rwm0c", "caption": "A train running on railroad tracks followed by a train horn honking and railroad signal bells chiming" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/YhV4bDCBDCy0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YhV4bDCBDCy0.npy", "labels": "/m/07r04,/m/07yv9,/m/09x0r", "caption": "Humming of a large truck engine with blowing wind" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YBwnGxJD9xh8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBwnGxJD9xh8.npy", "labels": "/m/03fwl,/m/068hy,/m/07bgp,/m/0jbk", "caption": "Birds chirping and wind blowing in the background followed by a man talking then a goat baaing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YDt53UZgyznE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YDt53UZgyznE.npy", "labels": "/m/09x0r,/t/dd00002", "caption": "A kid crying followed by a man talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part24/YVjSEIRnLAh8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YVjSEIRnLAh8.npy", "labels": "/m/09x0r,/m/0dxrf", "caption": "A woman is talking as food is frying" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/YyLu4b01t53k.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YyLu4b01t53k.npy", "labels": "/m/012f08,/m/07pb8fc,/m/07yv9", "caption": "An idle vehicle engine running" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YU5ij0M7T-hk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YU5ij0M7T-hk.npy", "labels": "/m/02dgv,/m/09x0r", "caption": "Footsteps followed by creaking and a man speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/YiOCpICiu4LA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YiOCpICiu4LA.npy", "labels": "/m/01h3n,/m/03l9g,/m/03vt0,/m/0h2mp", "caption": "A man talking as birds chirp in the background followed by a loud popping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4eyY1w2QyM0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4eyY1w2QyM0.npy", "labels": "/m/0j6m2", "caption": "Ocean waves crashing and water splashing followed by a bird cawing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/YzF3xXn6NTyU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YzF3xXn6NTyU.npy", "labels": "/m/0j6m2", "caption": "Water falling and a woman talks, coughs, then talks again while a man speaks in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YkOYg4ZtKcAs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YkOYg4ZtKcAs.npy", "labels": "/m/01yrx,/m/068hy,/m/07qrkrw,/m/0jbk", "caption": "A cat meowing briefly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part24/YUV1kdjwpy6U.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YUV1kdjwpy6U.npy", "labels": "/m/01jwx6,/m/09x0r", "caption": "A loud motor begins to pick up speed, then cuts out and slowly stops" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YENTi8Sn4vdM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YENTi8Sn4vdM.npy", "labels": "/m/0j6m2", "caption": "A small child and woman speak with splashing water" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/Ypaf0nyjg1Js.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ypaf0nyjg1Js.npy", "labels": "/m/0dxrf", "caption": "Food and oil sizzling followed by a woman talking then plastic thumping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YBDpU2Qh77NE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBDpU2Qh77NE.npy", "labels": "/m/015p6,/m/020bb7,/m/07pggtn", "caption": "Birds chirping followed by whispering" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YLxu-3_h4kc4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YLxu-3_h4kc4.npy", "labels": "/m/03q5_w", "caption": "Loud burps and laughter" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YAxd__X2rixk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YAxd__X2rixk.npy", "labels": "/m/03k3r,/m/07rv9rh,/m/0jbk", "caption": "Clip clops of a horse running by" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/YoZaEHkfh5Eg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YoZaEHkfh5Eg.npy", "labels": "/m/07yv9,/m/0912c9,/m/0k4j", "caption": "Car horn and alarm blare simultaneously" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4pf-PIymDhU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4pf-PIymDhU.npy", "labels": "/m/01d380,/m/07k1x,/m/0_ksk", "caption": "A jackhammer operating" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YItS07xtdi4s.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YItS07xtdi4s.npy", "labels": "/m/07qsvvw,/m/09x0r", "caption": "Rockets igniting followed by an electronic beep then footsteps on concrete as idle vehicle engines run in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part7/Y5ORpSk5CIWc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y5ORpSk5CIWc.npy", "labels": "/m/09ct_", "caption": "A toy helicopter flying by followed by muffled plastic clacking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YCeRoaEcqUgM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YCeRoaEcqUgM.npy", "labels": "/m/019jd,/m/02rlv9,/m/07yv9", "caption": "A motorboat driving by as water splashes followed by wind blowing into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YQHfyKaOHSz4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YQHfyKaOHSz4.npy", "labels": "/m/07st88b,/m/09ld4", "caption": "An insect buzzing as wood clanks twice followed by a person gulping then another insect buzzing and a person gulping proceeded by a guitar strumming while birds chirp in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YaZAXO2WZn84.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YaZAXO2WZn84.npy", "labels": "/m/06wzb,/m/07rjwbb", "caption": "A train running on railroad tracks followed by a lawn mower engine running then a steam engine whistle blowing as a crowd of people are talking in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part1/Y-nQHwrRLfc0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y-nQHwrRLfc0.npy", "labels": "/m/02mk9,/m/07pb8fc,/t/dd00066", "caption": "Engine running steadily" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/Ye6jSpvTvfJ0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ye6jSpvTvfJ0.npy", "labels": "/m/06mb1,/m/0cj0r", "caption": "Thunder claps and rain falls hard, splashing on surfaces" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/YyVjivgsU2aA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YyVjivgsU2aA.npy", "labels": "/m/012f08,/m/07rknqz,/m/07yv9,/m/09x0r,/m/0h9mv,/m/0k4j,/m/0ltv", "caption": "An engine running followed by the engine revving and tires screeching" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/YhpDltmawxIM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YhpDltmawxIM.npy", "labels": "/m/0130jx,/m/02jz0l,/m/0838f", "caption": "A sink is filling with water" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/YwnqUgK_-fo4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YwnqUgK_-fo4.npy", "labels": "/m/07bgp,/m/09x0r,/m/0jbk", "caption": "A crowd of people talk then cheer and whistle as firecrackers pop in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YPRUfwpmYwJ8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YPRUfwpmYwJ8.npy", "labels": "/m/07qlf79,/m/09x0r", "caption": "A man speaks followed by bursts of hissing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YObWjGBJF_94.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YObWjGBJF_94.npy", "labels": "/m/02jz0l,/m/07ptzwd", "caption": "Music playing through a television speaker followed by a series of plastic clicking while white noise hisses" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YItS07xtdi4s.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YItS07xtdi4s.npy", "labels": "/m/07qsvvw,/m/09x0r", "caption": "Fire igniting as a motor runs followed by an electronic beep and vehicle engines running idle then car horns honking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part27/Y_C2HinL8VlM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y_C2HinL8VlM.npy", "labels": "/m/03j1ly,/m/03kmc9,/m/04qvtq", "caption": "The siren of an emergency vehicle sounds" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/YoiIi6H83Y38.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YoiIi6H83Y38.npy", "labels": "/m/04_sv,/m/07yv9,/m/09x0r", "caption": "A motorcycle engine starting up and revving as a man talks in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/YxBZnvfniA1c.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YxBZnvfniA1c.npy", "labels": "/m/09x0r,/m/0ytgt,/t/dd00125", "caption": "A man speaks, and a child speaks followed by laughter" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9BukzlPNqC8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9BukzlPNqC8.npy", "labels": "/m/01d380,/m/09x0r", "caption": "Drilling in operation with speech and thumping in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y2JV3emH50XU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y2JV3emH50XU.npy", "labels": "/m/07yv9,/m/0k4j,/m/0ltv", "caption": "A vehicle accelerating in the distance then driving by" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3XcIVh40pTI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3XcIVh40pTI.npy", "labels": "/m/01d3sd", "caption": "A few loud snores" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3xDZ-kdGE3o.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3xDZ-kdGE3o.npy", "labels": "/m/01jt3m,/m/0838f", "caption": "White noise followed by clanking and then a toilet flushing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part1/Y0Rpjl1AO-P0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y0Rpjl1AO-P0.npy", "labels": "/m/07yv9,/m/0k4j,/t/dd00134", "caption": "Car engine accelerates and shifts gears" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YNtQiduPRiRg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YNtQiduPRiRg.npy", "labels": "/m/01j3sz,/m/09x0r", "caption": "A man laughing then a girl laughing during a loud power tool motor running" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part9/Y8GHLfJ6y6zA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y8GHLfJ6y6zA.npy", "labels": "/m/01m2v,/m/0316dw,/m/09x0r", "caption": "A person speaks with some whistling and typing with faint booms" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9xoYx3lTJ9I.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9xoYx3lTJ9I.npy", "labels": "/m/019jd,/m/02rlv9,/m/03m9d0z,/t/dd00092", "caption": "Wind blows hard and a motor hums in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/Yg6CY7qvu81k.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yg6CY7qvu81k.npy", "labels": "/m/07p9k1k", "caption": "Drums and music playing with a man speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YEQVWhHmT_cE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YEQVWhHmT_cE.npy", "labels": "/m/02qldy,/m/05zppz,/m/09x0r", "caption": "A man speaks followed by glass breaking and people laughing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part0/Y-AheI8Epim4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y-AheI8Epim4.npy", "labels": "/m/07qsvvw,/m/09x0r", "caption": "Wind noise followed by a tapping noise while people are talking in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YbIV3bJZpkgA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YbIV3bJZpkgA.npy", "labels": "/m/07yv9,/m/09ct_", "caption": "A helicopter is in flight" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YrgrmLLhxoCQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YrgrmLLhxoCQ.npy", "labels": "/t/dd00112", "caption": "Repeated scraping on two different surfaces" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YOVQMFBeCHq0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YOVQMFBeCHq0.npy", "labels": "/m/012n7d,/m/03j1ly,/m/03kmc9", "caption": "An ambulance siren with rain" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YL6rnV0oNIII.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YL6rnV0oNIII.npy", "labels": "/m/07qjznl", "caption": "Laser followed by a gun shot" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/Yh0M4RS8p_mo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yh0M4RS8p_mo.npy", "labels": "/m/01j3sz,/m/0463cq4", "caption": "A maniacal laugh followed by a crying baby" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/Yn-JyOqYSLQM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yn-JyOqYSLQM.npy", "labels": "/m/07qlf79", "caption": "Metal clanking followed by plastic rattling as compressed air is spraying while a crowd of people talk in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YXPebkNzsnRI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YXPebkNzsnRI.npy", "labels": "/m/01w250,/m/09x0r", "caption": "Whistling followed by a child giggling and then Moe whistling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part9/Y8OTd45_6cvY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y8OTd45_6cvY.npy", "labels": "/m/07qlf79", "caption": "Footsteps running on a hard surface followed by liquid spraying then an animal growling as static plays in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/Ya_Rjlu50TfA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ya_Rjlu50TfA.npy", "labels": "/m/01d3sd,/m/07q0yl5,/m/09x0r", "caption": "Plastic tapping as a person is snoring" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YKJKHDKKW3XU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YKJKHDKKW3XU.npy", "labels": "/m/07swgks", "caption": "Water makes gurgling sound" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y6cS0FsUM-cQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y6cS0FsUM-cQ.npy", "labels": "/m/01yrx,/m/068hy,/m/07qrkrw,/m/07r81j2,/m/09x0r,/m/0jbk", "caption": "A person speaks and a cat growls" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YmaVYiednkSg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YmaVYiednkSg.npy", "labels": "/m/07qlf79,/m/09x0r", "caption": "A rumbling sound followed by a spray of liquid and a man speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YZUmZgPL0ges.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YZUmZgPL0ges.npy", "labels": "/m/0395lw", "caption": "Several church bells ringing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YBOB65Nd0pXo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBOB65Nd0pXo.npy", "labels": "/m/02l6bg,/m/07yv9,/m/09ct_", "caption": "The wind is blowing, an aircraft motor is running, and whirring and the beating of propellers are ongoing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YKJKHDKKW3XU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YKJKHDKKW3XU.npy", "labels": "/m/07swgks", "caption": "Gurgling and splashing water" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part19/YMSziND26UTA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YMSziND26UTA.npy", "labels": "/m/01h3n,/m/03vt0,/m/0h2mp", "caption": "Bees buzz as a man sings in the background followed by dogs howling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YCYUlLTKoa1Y.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YCYUlLTKoa1Y.npy", "labels": "/m/09x0r,/m/0llzx", "caption": "Humming followed by some rattling and a woman speaking then slow vibrations of a sewing machine" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y2ItTq2JShdU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y2ItTq2JShdU.npy", "labels": "/m/07rqsjt", "caption": "A train engine operating" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YCeRoaEcqUgM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YCeRoaEcqUgM.npy", "labels": "/m/019jd,/m/02rlv9,/m/07yv9", "caption": "A boat motor runs fast and water splashes at regular intervals, then it fades and the wind is blowing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YEzWEO2WD_MM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YEzWEO2WD_MM.npy", "labels": "/m/01d380", "caption": "High frequency humming followed by a smack" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part7/Y5QZ0NtdoKJ8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y5QZ0NtdoKJ8.npy", "labels": "/m/02fs_r,/m/07pp_mv,/m/09x0r", "caption": "Beeping sound with person talking in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part15/YGPj8h-WcjWs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YGPj8h-WcjWs.npy", "labels": "/m/01bjv,/m/07yv9,/m/09x0r", "caption": "Humming of a loud engine with a woman speaking over a loudspeaker" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3RultJjvTWI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3RultJjvTWI.npy", "labels": "/m/019jd,/m/034srq,/m/03m9d0z,/t/dd00092", "caption": "A young girl talks followed by another young girl laughing then a young man yelling as a river stream splashes and flows with a crowd of people talking in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YAR8-MVl_Mf8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YAR8-MVl_Mf8.npy", "labels": "/m/02dgv,/m/07rjzl8,/m/09x0r", "caption": "A man screaming followed by slamming against a metal object proceeded by a man talking cardboard tumbles on a hard surface as a truck engine runs idle in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YJTHMXLC9YRs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YJTHMXLC9YRs.npy", "labels": "/m/09ddx,/m/0jbk", "caption": "Wind blowing hard followed by breathing and faint quacks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YmWqH2xwjkYA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YmWqH2xwjkYA.npy", "labels": "/m/01j3sz,/m/09x0r", "caption": "An infant and a woman laughing followed by a person spitting then a woman talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YDrCm-HpX67k.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YDrCm-HpX67k.npy", "labels": "/m/083vt", "caption": "Birds are chirping, rustling and thumping are ongoing, a crow caws in the distance, and then four knocks on wood occur" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/YoOMtaqvQ3_M.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YoOMtaqvQ3_M.npy", "labels": "/m/07yv9,/m/09ct_,/m/0k5j", "caption": "A helicopter flying with wind heavily blowing into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part27/Y_C2HinL8VlM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y_C2HinL8VlM.npy", "labels": "/m/03j1ly,/m/03kmc9,/m/04qvtq", "caption": "Metal clanking and hammering in the distance followed by police sirens sounding" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part27/Y_iUX8CibElk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y_iUX8CibElk.npy", "labels": "/m/0ngt1", "caption": "A loud static plays continuously" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/YpO8kbg9IJnc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YpO8kbg9IJnc.npy", "labels": "/m/0130jx,/m/02jz0l,/m/0838f", "caption": "Some light clicks followed by a man speaking and water splashing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YEUZaxaWqhwg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YEUZaxaWqhwg.npy", "labels": "/m/07yv9,/m/0cmf2,/m/0k5j", "caption": "An aircraft engine running as a crowd of people talk in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part4/Y2ceUOv8A3FE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y2ceUOv8A3FE.npy", "labels": "/m/01g50p,/m/0284vy3,/m/06d_3,/m/07jdr", "caption": "A series of train horns honking as birds chirp and a man talks in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y7D7xgd4WJ50.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y7D7xgd4WJ50.npy", "labels": "/m/0395lw", "caption": "A high pitched bell rings rapidly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YZY4aGEniU_E.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YZY4aGEniU_E.npy", "labels": "/m/07p9k1k", "caption": "Food and oil sizzling followed by steam hissing as a man talks and light rock music plays in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YTaQKhIRwii4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YTaQKhIRwii4.npy", "labels": "/m/028ght", "caption": "Applause and some muffled speech" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/YhqPBcvex1VU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YhqPBcvex1VU.npy", "labels": "/m/09x0r,/t/dd00002", "caption": "A baby whining and crying" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3XuyGJqaXv8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3XuyGJqaXv8.npy", "labels": "/m/068hy,/m/07rc7d9,/m/09x0r,/m/0bt9lr,/m/0jbk", "caption": "A man speaks over a loudspeaker with a crowd talking in the distance and dogs barking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/Yj_NSuPnx5LA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yj_NSuPnx5LA.npy", "labels": "/m/07cx4", "caption": "Dialing on a phone using touch tone dialing followed by a loud thump noise" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3xDZ-kdGE3o.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3xDZ-kdGE3o.npy", "labels": "/m/01jt3m,/m/0838f", "caption": "Metal clacking followed by a door closing as water trickles then a toilet flushing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YatmDP_fmK_8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YatmDP_fmK_8.npy", "labels": "/m/014zdl,/m/07qsvvw", "caption": "A low loud hum gets lower followed by an explosion" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9hxFqltp3xw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9hxFqltp3xw.npy", "labels": "/m/07qlf79,/m/09x0r", "caption": "A woman speaks with some rattling and some spraying" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YDn3buZWMzwY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YDn3buZWMzwY.npy", "labels": "/m/01d3sd,/m/09x0r", "caption": "Snoring is ongoing, while an adult female laughs and an adult male speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YSoO1HhaEc9Q.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YSoO1HhaEc9Q.npy", "labels": "/m/09x0r,/t/dd00018", "caption": "Humming followed by faint cracking oinks and a man speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YP12nvSpKXcs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YP12nvSpKXcs.npy", "labels": "/m/01h3n,/m/03vt0,/m/0h2mp", "caption": "Insects buzzing followed by rattling and rustling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YLCwSUVuTyvg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YLCwSUVuTyvg.npy", "labels": "/m/02dgv", "caption": "Door opening and sliding" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YEfk5kdn9lR8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YEfk5kdn9lR8.npy", "labels": "/m/02dgv,/m/02y_763,/m/09x0r", "caption": "A child is speaking followed by a door moving" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/YfPqj3nnwQOI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YfPqj3nnwQOI.npy", "labels": "/m/0j6m2", "caption": "Waves coming against the shoreline" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YSmdj6JFB9MQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YSmdj6JFB9MQ.npy", "labels": "/m/01jt3m,/m/09x0r", "caption": "Female speech, a toilet flushing and then more speech" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part7/Y5YzNSjmZ3Wg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y5YzNSjmZ3Wg.npy", "labels": "/m/01h3n,/m/09x0r", "caption": "Male speech and a bug buzzing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YZTYAQBnU4GM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YZTYAQBnU4GM.npy", "labels": "/m/015p6,/m/068hy,/m/07pggtn", "caption": "Birds chirping repeatedly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YFc9pG54DDJM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YFc9pG54DDJM.npy", "labels": "/m/01jt3m,/m/0838f", "caption": "A toilet flushing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YbX2vDaHL26U.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YbX2vDaHL26U.npy", "labels": "/m/07rknqz,/m/07yv9,/m/0k4j,/m/0ltv", "caption": "An engine running and then tires squealing and a car accelerates" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YZUmZgPL0ges.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YZUmZgPL0ges.npy", "labels": "/m/0395lw", "caption": "Bells ringing repeatedly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/YpHNMcX-9FDs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YpHNMcX-9FDs.npy", "labels": "/m/068hy,/m/0bt9lr,/m/0jbk,/t/dd00136", "caption": "Puppies whining with some rustling and bird chirp" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YR91bUbtKrRs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YR91bUbtKrRs.npy", "labels": "/m/09x0r,/t/dd00002", "caption": "Two adult females speak in the foreground while muted speech occurs in the background, and an infant begins to cry" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YqF72bT878gw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YqF72bT878gw.npy", "labels": "/m/019jd,/m/02rlv9,/m/07yv9", "caption": "A motorboat engine running" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part19/YMe4npKmtchA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YMe4npKmtchA.npy", "labels": "/m/07pqc89,/m/0838f,/m/09x0r", "caption": "Bubbles gurgling and water spraying as a man speaks softly while crowd of people talk in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YQKHpSAAjakY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YQKHpSAAjakY.npy", "labels": "/m/04_sv,/m/07yv9,/m/09x0r,/t/dd00128", "caption": "An engine hums as it idles and a man speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part38/Yvigslb0kClE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yvigslb0kClE.npy", "labels": "/m/03fwl,/m/09x0r,/m/0jbk", "caption": "Goats bleating and a man speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y1a2XWJ8NA_Q.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1a2XWJ8NA_Q.npy", "labels": "/m/019jd,/m/02rlv9,/m/07yv9,/m/09x0r", "caption": "Distant, muffled murmuring together with an engine running continuously and light wind" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/Ym8wV38lf2jg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ym8wV38lf2jg.npy", "labels": "/m/03j1ly,/m/03kmc9,/m/04qvtq,/m/07yv9,/m/09x0r,/m/0k4j", "caption": "People are speaking while an engine is running, and an emergency vehicle sounds horn" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YtJhVH3VIrnE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YtJhVH3VIrnE.npy", "labels": "/m/02dgv", "caption": "Cracking and banging" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YLvhvAA11oxE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YLvhvAA11oxE.npy", "labels": "/m/07yv9,/m/09x0r,/m/0h9mv,/m/0ltv,/t/dd00128", "caption": "An engine is revving up, the driver is making it louder by giving it more gas" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/YcNARVD02-tw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YcNARVD02-tw.npy", "labels": "/m/02jz0l,/m/09x0r", "caption": "Male and female speech and then water running" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/YfPqj3nnwQOI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YfPqj3nnwQOI.npy", "labels": "/m/0j6m2", "caption": "A stream of water flowing as the wind blows" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y1PvMtRIlZNI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1PvMtRIlZNI.npy", "labels": "/m/07swgks", "caption": "Gurgling and splashing water" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YLCwSUVuTyvg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YLCwSUVuTyvg.npy", "labels": "/m/02dgv", "caption": "A series of doors sliding open as gusts of wind blows and glass clanks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/Ycr0GiZr0TNY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ycr0GiZr0TNY.npy", "labels": "/m/01j3sz,/t/dd00001", "caption": "Young children giggling and laughing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YRrmBGjJqlEo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YRrmBGjJqlEo.npy", "labels": "/m/0316dw", "caption": "Male speaking then typing computer keyboards" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/YjinJkonlrWc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YjinJkonlrWc.npy", "labels": "/m/09ct_,/m/09x0r", "caption": "An engine running and muffled speech" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/Yy-RSojxgkDo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yy-RSojxgkDo.npy", "labels": "/m/015p6,/m/068hy,/m/07pggtn", "caption": "An adult male speaks, a bird chirps harshly, and then the adult male and an adult female speak" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part27/YZsf2YvJfCKw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YZsf2YvJfCKw.npy", "labels": "/m/01jt3m", "caption": "A toilet flushing and water trickling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part38/YvEWmHtiznF8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YvEWmHtiznF8.npy", "labels": "/m/012f08,/m/01bjv,/m/07yv9,/m/09x0r", "caption": "An engine running and a male speech" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YkOYg4ZtKcAs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YkOYg4ZtKcAs.npy", "labels": "/m/01yrx,/m/068hy,/m/07qrkrw,/m/0jbk", "caption": "A cat is meowing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/Yq46VXJ6JN9M.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yq46VXJ6JN9M.npy", "labels": "/m/07qlf79", "caption": "Footsteps shuffling followed by compressed air spraying then plastic camera muffling as birds chirp in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YB4SZwi9Ce3o.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YB4SZwi9Ce3o.npy", "labels": "/m/07q2z82,/m/07yv9,/m/09x0r,/m/0k4j", "caption": "A man talking and plastic clicking as a vehicle engine accelerates" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/Yq1ivQ_2fddk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yq1ivQ_2fddk.npy", "labels": "/m/07qlf79,/m/09x0r,/t/dd00128", "caption": "A man talks outside while several other men join in the conversation" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/YdmUOSyPXkUw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YdmUOSyPXkUw.npy", "labels": "/m/06wzb,/m/07rjwbb", "caption": "Compressed air and steam releasing with a man faintly talking in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part19/YNDaVSIJaXVs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YNDaVSIJaXVs.npy", "labels": "/m/014yck,/m/07yv9,/m/0cmf2,/m/0k5j,/t/dd00128", "caption": "An aircraft engine operating as wind blows into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YkagkXkAVPNo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YkagkXkAVPNo.npy", "labels": "/m/07yv9,/m/0912c9,/m/09x0r,/m/0k4j", "caption": "Hum of a loud engine with several horns honking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part15/YGSHcgY6ATkQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YGSHcgY6ATkQ.npy", "labels": "/m/0316dw", "caption": "A man speaking followed by typing on a keyboard" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YD4s5aHrsBgs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YD4s5aHrsBgs.npy", "labels": "/m/01w250", "caption": "Music plays along with whistling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y0yETgW44MZU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y0yETgW44MZU.npy", "labels": "/m/01g50p,/m/0284vy3,/m/04zmvq,/m/06d_3,/m/07jdr,/m/07yv9,/t/dd00129", "caption": "A train horn honking as a train runs on railroad tracks and birds chirping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YHVz-FJBf_iM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YHVz-FJBf_iM.npy", "labels": "/m/01jt3m,/m/0838f", "caption": "Metal clanking occurs momentarily, then a flush occurs and water splashes and gurgles" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4abZbau8tZo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4abZbau8tZo.npy", "labels": "/m/07swgks,/m/09x0r", "caption": "Waves roll in and a man speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YJ0yeFeKvIt8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YJ0yeFeKvIt8.npy", "labels": "/m/09t49", "caption": "Wind blowing and leaves rustling followed by plastic clicking and wind blowing into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YqakN0JNbpcU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YqakN0JNbpcU.npy", "labels": "/m/01h3n,/m/03vt0,/m/09x0r", "caption": "Insects buzzing as a man speaks while birds chirp and wind blows into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part1/Y0_ogYGDGDco.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y0_ogYGDGDco.npy", "labels": "/m/019jd,/m/034srq,/m/03m9d0z,/m/056ks2,/m/05kq4,/t/dd00092", "caption": "Water is splashing, people are talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/Yq3SEOW2m4WY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yq3SEOW2m4WY.npy", "labels": "/m/01g50p,/m/0284vy3,/m/06d_3,/m/07jdr,/m/07rwm0c", "caption": "A train horn honks as a train speeds past" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YIKnx3hJv1bs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YIKnx3hJv1bs.npy", "labels": "/m/07qlf79", "caption": "The hiss of spraying" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YbAqgL5dCQOE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YbAqgL5dCQOE.npy", "labels": "/m/06mb1,/m/07r10fb,/t/dd00038", "caption": "Continuous rain falling on surface" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part27/Ya0yXS7PmVR0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ya0yXS7PmVR0.npy", "labels": "/m/07qlf79", "caption": "Praying with mechanical noise in background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part24/YVOXl8iR-HnI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YVOXl8iR-HnI.npy", "labels": "/m/014yck,/m/07yv9,/m/09x0r,/m/0cmf2,/m/0k5j", "caption": "A man talking as gusts of wind blow followed by an aircraft flying by" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YS8k47ME-YT4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YS8k47ME-YT4.npy", "labels": "/m/06mb1,/m/0jb2l,/m/0ngt1", "caption": "Thunder claps, and hard rain falls and splashes on surfaces" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part9/Y8DLcBdC5UrE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y8DLcBdC5UrE.npy", "labels": "/m/07swgks", "caption": "Wind followed by splashing of water" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YFJkvAMLmejY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YFJkvAMLmejY.npy", "labels": "/m/0912c9,/m/09x0r,/t/dd00125", "caption": "A young man whispering followed by a horn honking then a group of people laughing while someone claps" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part4/Y2msevPMQB4M.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y2msevPMQB4M.npy", "labels": "/m/01d380,/m/07k1x", "caption": "A power tool drill operating followed by compressed air releasing and steam hissing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YWLzzpzOKtnY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YWLzzpzOKtnY.npy", "labels": "/m/01h3n,/m/09x0r", "caption": "A man speaking as wind is blowing into a microphone and an insect buzzes while another man talks in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/Ye4ph6bIC5zc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ye4ph6bIC5zc.npy", "labels": "/m/012f08,/m/07yv9,/m/0k4j,/m/0ltv", "caption": "A radio playing in the background followed by a vehicle engine accelerating" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/Ycr0GiZr0TNY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ycr0GiZr0TNY.npy", "labels": "/m/01j3sz,/t/dd00001", "caption": "Children laughing with intermittent hissing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part9/Y8b9z7N25DmU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y8b9z7N25DmU.npy", "labels": "/m/01bjv,/m/07yv9,/m/09x0r,/t/dd00129", "caption": "Bus pulling up to a stop with distant voices in background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y40cuHrYfaqA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y40cuHrYfaqA.npy", "labels": "/m/068hy,/m/07rc7d9,/m/09x0r,/m/0bt9lr,/m/0jbk,/t/dd00136", "caption": "Dogs barking repeatedly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YARFFw0e_jig.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YARFFw0e_jig.npy", "labels": "/m/03q5_w", "caption": "A loud distorted belch followed by a series of burping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YPLHXGDnig4M.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YPLHXGDnig4M.npy", "labels": "/m/01yrx,/m/07qrkrw", "caption": "A man speaking then hissing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part27/Y_AcJVyToQUQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y_AcJVyToQUQ.npy", "labels": "/m/01j3sz,/m/09x0r", "caption": "Laughter and a female speaking and then a male vocalizing a sneezing sound" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YbIiiIo20PsY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YbIiiIo20PsY.npy", "labels": "/m/01h3n,/m/09x0r", "caption": "A man speaking as insects are buzzing and wind is blowing into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/Yoklu5ZJD_2U.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yoklu5ZJD_2U.npy", "labels": "/m/015p6,/m/068hy,/m/07pggtn", "caption": "Birds chirp as an object strikes a surface" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YKtTLsveexOg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YKtTLsveexOg.npy", "labels": "/m/0llzx", "caption": "A sewing machine running as a steam hisses followed by a machine motor sharply running in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9z2OwpftxUE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9z2OwpftxUE.npy", "labels": "/m/0ngt1", "caption": "Consistent muffled thunder" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/Yn-JyOqYSLQM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yn-JyOqYSLQM.npy", "labels": "/m/07qlf79", "caption": "Aluminum cans clanking followed by compressed air spraying as plastic rattles while a crowd of people talk in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part4/Y32565FEuksc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y32565FEuksc.npy", "labels": "/m/02qldy,/m/02zsn,/m/09x0r", "caption": "A woman speaks followed by the applause of a crowd" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/YxbLW9Wt1Jsg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YxbLW9Wt1Jsg.npy", "labels": "/m/0llzx", "caption": "Plastic bonking as metal shuffles and clanks while a motor engine hums in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y0fMXnvD38zI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y0fMXnvD38zI.npy", "labels": "/m/019jd,/m/034srq,/m/03m9d0z,/m/05kq4,/t/dd00092", "caption": "Continuous wind and surf" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/Ykdflh3akyH8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ykdflh3akyH8.npy", "labels": "/m/0ghcn6,/m/0jbk,/t/dd00136", "caption": "Several puppies yapping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4YMXgLFcR94.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4YMXgLFcR94.npy", "labels": "/m/02qldy,/m/05zppz,/m/09x0r", "caption": "Male speaking and then applause" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part9/Y8IdCiapDYCU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y8IdCiapDYCU.npy", "labels": "/m/068hy,/m/07rc7d9,/m/0bt9lr,/m/0jbk", "caption": "Laughing and a puppy barking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y1Og2TJ3bXW0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1Og2TJ3bXW0.npy", "labels": "/m/07yv9,/m/0cmf2,/m/0k5j,/t/dd00128", "caption": "A quiet whirring of an airplane" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YQ87LBiwJjTE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YQ87LBiwJjTE.npy", "labels": "/m/07p9k1k,/m/0dxrf", "caption": "A woman is speaking as food is frying and sizzling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YAMQei29haCw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YAMQei29haCw.npy", "labels": "/m/01d380", "caption": "A tool running and a male vocalizing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/Yq1ivQ_2fddk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yq1ivQ_2fddk.npy", "labels": "/m/07qlf79,/m/09x0r,/t/dd00128", "caption": "Hissing spray is ongoing and an adult male speaks in the foreground, while several adult males speak in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part15/YGMP8m09j5vk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YGMP8m09j5vk.npy", "labels": "/m/015p6,/m/020bb7,/m/07pggtn", "caption": "Birds chirping loudly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/YfsBR7e_X_0Y.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YfsBR7e_X_0Y.npy", "labels": "/m/09x0r,/m/0ytgt,/t/dd00125", "caption": "An infant yelling as a young boy talks while a hard surface is slapped several times" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YDc2WEiRk0rA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YDc2WEiRk0rA.npy", "labels": "/m/07qlf79", "caption": "Hissing spray is occurring, and liquid is pattering on a surface" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YOUUckswAaNI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YOUUckswAaNI.npy", "labels": "/m/02dgv", "caption": "Male speaking and birds chirping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/YwFiCblfZ-vg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YwFiCblfZ-vg.npy", "labels": "/m/07pqc89,/m/09x0r", "caption": "A man speaking followed by another man speaking in the background during audio static" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YBA-lFjpzad4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBA-lFjpzad4.npy", "labels": "/m/012f08,/m/04_sv,/m/07yv9,/m/09x0r,/t/dd00134", "caption": "Brief murmuring followed by a vehicle passing by" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YTdl9SmBbRnA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YTdl9SmBbRnA.npy", "labels": "/m/012f08,/m/01bjv,/m/07yv9,/m/09x0r", "caption": "A man talks while a motor vibrates nearby" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YHdPSebdDxe4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YHdPSebdDxe4.npy", "labels": "/m/03q5_w", "caption": "Male speech and then growling followed by male speech" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/YfPqj3nnwQOI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YfPqj3nnwQOI.npy", "labels": "/m/0j6m2", "caption": "Ocean waves crashing and water trickling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part27/YZsTZ7jqbd9M.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YZsTZ7jqbd9M.npy", "labels": "/m/01h3n,/m/09x0r", "caption": "A man talking during footsteps on leaves as birds chirp in the background." }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YsqsI2UyrcBQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YsqsI2UyrcBQ.npy", "labels": "/m/07q2z82,/m/07yv9,/m/0k4j", "caption": "A vehicle engine accelerating and revving" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YKOBkbROPv4c.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YKOBkbROPv4c.npy", "labels": "/m/07rknqz,/m/07yv9,/m/0h9mv,/m/0ltv", "caption": "An engine revving and then skidding tires" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/Yk1QxQ4jJaEQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yk1QxQ4jJaEQ.npy", "labels": "/m/07r04,/m/07yv9,/m/09x0r,/t/dd00129", "caption": "A man speaking as a truck engine runs idle" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part27/Ya3GzZKxUTy8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ya3GzZKxUTy8.npy", "labels": "/m/015p6,/m/09ddx,/m/0bt9lr,/m/0jbk", "caption": "A duck quacking followed by a dog whimpering then glass tapping as a film projector runs while birds chirp in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part9/Y8DQfjqPCTI8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y8DQfjqPCTI8.npy", "labels": "/m/01h3n,/m/03vt0,/m/0h2mp", "caption": "Bees buzz while two men talk followed by a sniffle" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YSNy_axSCoyw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YSNy_axSCoyw.npy", "labels": "/m/07qjznl", "caption": "A clock ticking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part19/YMBP4RcnwGZw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YMBP4RcnwGZw.npy", "labels": "/m/02zsn,/m/07qfr4h,/m/09x0r", "caption": "People speak with wind blowing and distant hums of traffic" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YAxd__X2rixk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YAxd__X2rixk.npy", "labels": "/m/03k3r,/m/07rv9rh,/m/0jbk", "caption": "A horse trotting" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part27/Y_z6pymOet7g.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y_z6pymOet7g.npy", "labels": "/m/01jt3m,/m/09x0r", "caption": "A man speaks followed by a toilet flush" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YbJMMp6PLKqM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YbJMMp6PLKqM.npy", "labels": "/m/0463cq4,/m/09x0r,/m/0ytgt,/t/dd00125", "caption": "A baby cries and a young child speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part27/YZsTZ7jqbd9M.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YZsTZ7jqbd9M.npy", "labels": "/m/01h3n,/m/09x0r", "caption": "An adult male speaks while birds chirp, slight rustling and brief buzzing occur, and emergency vehicle sirens are blaring in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part7/Y5YzNSjmZ3Wg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y5YzNSjmZ3Wg.npy", "labels": "/m/01h3n,/m/09x0r", "caption": "A nearby insect buzzes with nearby vibrations" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YnmLMLgWPmFM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YnmLMLgWPmFM.npy", "labels": "/m/09x0r,/m/0j6m2", "caption": "Humming of an engine with people speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/YgkWd1HugK2w.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YgkWd1HugK2w.npy", "labels": "/m/015p6,/m/0h0rv,/t/dd00129", "caption": "Pigeons coo and flap their wings" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YrPkCYq4Zjwk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YrPkCYq4Zjwk.npy", "labels": "/m/02fs_r", "caption": "A whoosh effect followed by a woman talking then a man talking proceeded by another man talking over a radio as guitar music plays in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YtB8TiiXwKmA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YtB8TiiXwKmA.npy", "labels": "/m/01d380,/m/07k1x,/m/0_ksk", "caption": "Vibrating and humming of a power tool" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YZTYAQBnU4GM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YZTYAQBnU4GM.npy", "labels": "/m/015p6,/m/068hy,/m/07pggtn", "caption": "Birds are chirping followed by a low vibrating noise" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/YhqPBcvex1VU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YhqPBcvex1VU.npy", "labels": "/m/09x0r,/t/dd00002", "caption": "A woman mumbling followed by an infant crying" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/YwoadpeAGHUQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YwoadpeAGHUQ.npy", "labels": "/m/012ndj,/m/03j1ly,/m/03kmc9", "caption": "An emergency siren blaring steadily" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YKVbmN9ZRg5Q.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YKVbmN9ZRg5Q.npy", "labels": "/m/01g50p,/m/0284vy3,/m/06d_3,/m/07jdr,/m/07rwm0c", "caption": "A passing train clacking with a long horn blowing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YIdBDl9Wr51A.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YIdBDl9Wr51A.npy", "labels": "/m/07rqsjt", "caption": "Man speaking, swords clash, monstrous voice speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/YpHYkWkZ4guE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YpHYkWkZ4guE.npy", "labels": "/m/06wzb,/m/07rjwbb", "caption": "Metal clanking and gears cranking as steam hisses" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/Ygbi6MxPf3hA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ygbi6MxPf3hA.npy", "labels": "/m/034srq,/m/03m9d0z,/m/05kq4,/t/dd00092", "caption": "Waves crashing, birds chirping lightly and a brief musical tone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YtdpiXW68adA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YtdpiXW68adA.npy", "labels": "/m/0463cq4,/m/09x0r", "caption": "A woman crying followed by a man talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/Yi6MQCm58zlY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yi6MQCm58zlY.npy", "labels": "/m/020bb7,/m/068hy,/m/0jbk", "caption": "Squealing and whimpering with some rustling followed by a man speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/YpHYkWkZ4guE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YpHYkWkZ4guE.npy", "labels": "/m/06wzb,/m/07rjwbb", "caption": "Steam hissing followed by a series of metal levers cranking then more steam hissing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part1/Y0UJtGcoPYa0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y0UJtGcoPYa0.npy", "labels": "/m/07jdr,/m/07yv9,/m/0912c9,/t/dd00128", "caption": "A motor engine running and buzzing as a train horn blows followed by a group of men groaning aloud" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part19/YMdlEswBfZMQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YMdlEswBfZMQ.npy", "labels": "/m/07rgt08,/m/09x0r,/m/0ytgt,/t/dd00125", "caption": "A group of children talking and laughing as a woman is speaking followed by a young boy speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part19/YMkbP_8zJwXU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YMkbP_8zJwXU.npy", "labels": "/m/015p6,/m/068hy,/m/09ddx,/t/dd00129", "caption": "Wind blows and a small bird chirps" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9E8BmPZ9mWc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9E8BmPZ9mWc.npy", "labels": "/m/07r04,/m/07yv9,/m/09x0r", "caption": "A truck revs up and moves, then men talk" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y1ed87LLY97k.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1ed87LLY97k.npy", "labels": "/m/07rjwbb", "caption": "Hissing with some faint bangs" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/Yx5AH2gW_8S4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yx5AH2gW_8S4.npy", "labels": "/m/0h0rv,/m/0jbk,/t/dd00125", "caption": "Pigeons are making coo and shrieking sounds" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YFDwK7T1JO_0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YFDwK7T1JO_0.npy", "labels": "/m/01d380,/m/07k1x,/m/09x0r,/t/dd00125", "caption": "A male voice and then drilling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YHdxfbpnd2-8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YHdxfbpnd2-8.npy", "labels": "/m/01w250", "caption": "A man talks and then whistles" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/YpHNMcX-9FDs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YpHNMcX-9FDs.npy", "labels": "/m/068hy,/m/0bt9lr,/m/0jbk,/t/dd00136", "caption": "Dogs are whimpering" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YYqYCDis3EUA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YYqYCDis3EUA.npy", "labels": "/m/01h3n,/m/03vt0,/m/0h2mp", "caption": "Birds chirping and bees buzzing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YmYQrjcYNrW0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YmYQrjcYNrW0.npy", "labels": "/m/01bjv,/m/07qv_d5,/m/07yv9", "caption": "A bus is tooting the horn" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/Yram-QPKSQYc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yram-QPKSQYc.npy", "labels": "/m/09ct_", "caption": "A helicopter flying" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YBrPFQDr99Gg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBrPFQDr99Gg.npy", "labels": "/m/02qldy,/m/05zppz,/m/09x0r", "caption": "A man is speaking, and a crowd applauds" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YqWYncqPSy9A.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YqWYncqPSy9A.npy", "labels": "/m/03vt0,/m/09f96,/m/0h2mp", "caption": "An adult female speaks, an insect buzzes, the adult female laughs, and then an adult male speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y2JV3emH50XU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y2JV3emH50XU.npy", "labels": "/m/07yv9,/m/0k4j,/m/0ltv", "caption": "A vehicle accelerating then driving by as gusts of wind blow and leaves rustle in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part9/Y8VOibo9Q_Dc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y8VOibo9Q_Dc.npy", "labels": "/m/09ddx,/m/09x0r,/m/0jbk", "caption": "Water splashing and birds chirping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YSePTNAN7s-w.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YSePTNAN7s-w.npy", "labels": "/m/01jt3m,/m/0838f", "caption": "A female speech and then a toilet flushing followed by a female speech." }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YRk-ujWKzPuc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YRk-ujWKzPuc.npy", "labels": "/m/06mb1,/t/dd00038", "caption": "Continuous rainfall" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/YzwoqJY03yHE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YzwoqJY03yHE.npy", "labels": "/m/03fwl,/m/068hy,/m/09x0r,/m/0jbk", "caption": "A woman talking followed by another woman talking as a goat is baaing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9ucb5HYO8ps.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9ucb5HYO8ps.npy", "labels": "/m/03q5_w,/m/09x0r", "caption": "Burping occurs, and several young adult females laugh and speak" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YmYQrjcYNrW0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YmYQrjcYNrW0.npy", "labels": "/m/01bjv,/m/07qv_d5,/m/07yv9", "caption": "A bus horn honking as wind is blowing into a microphone before a bus drives by" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part27/Y_iUX8CibElk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y_iUX8CibElk.npy", "labels": "/m/0ngt1", "caption": "Humming sounds from a distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4SZ7JXDCNps.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4SZ7JXDCNps.npy", "labels": "/m/07yv9,/m/0k4j,/m/0ltv", "caption": "A car engine revving" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YcK2kSVR1d2o.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YcK2kSVR1d2o.npy", "labels": "/m/07qsvvw,/m/0g6b5", "caption": "Fireworks pop and explode" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y6eX6bJOFftA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y6eX6bJOFftA.npy", "labels": "/m/02rlv9,/m/07yv9,/m/09x0r", "caption": "A man is vocalizing something while kids are talking in the background and music is being played, with a helicopter flying overhead" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YC4JwGJQ2dUA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YC4JwGJQ2dUA.npy", "labels": "/m/02qldy,/m/05zppz,/m/09x0r,/m/0brhx", "caption": "A man delivering a speech with some faint static buzzing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/Ydxow2DcTrwk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ydxow2DcTrwk.npy", "labels": "/m/0ngt1", "caption": "A man and a woman communicates with thunder and rain in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YWqXFAY4k79s.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YWqXFAY4k79s.npy", "labels": "/m/06mb1,/t/dd00038", "caption": "Several loud pops followed by one woman laughing and another speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part9/Y8ZH_PoK0clI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y8ZH_PoK0clI.npy", "labels": "/m/02dgv,/m/09x0r", "caption": "Rustling with footsteps and people briefly gasping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YF7QtqKtllK0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YF7QtqKtllK0.npy", "labels": "/m/01d3sd", "caption": "A person snores" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part24/YVZLZ08k3YeA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YVZLZ08k3YeA.npy", "labels": "/m/01d3sd,/m/09x0r", "caption": "A man speaks followed by loud snoring" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part4/Y2t82STv2GR8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y2t82STv2GR8.npy", "labels": "/m/0395lw", "caption": "Large church bells ringing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YJQz40TkjymY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YJQz40TkjymY.npy", "labels": "/m/01m2v,/m/0316dw", "caption": "Typing on a computer keyboard" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YFDwK7T1JO_0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YFDwK7T1JO_0.npy", "labels": "/m/01d380,/m/07k1x,/m/09x0r,/t/dd00125", "caption": "Two men communicating with each other followed by plastic clacking then a power tool drilling as wind softly blows into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part0/Y-DmjkgWa-rw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y-DmjkgWa-rw.npy", "labels": "/m/0395lw", "caption": "Church bells ringing during audio static" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YLbken4JCr94.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YLbken4JCr94.npy", "labels": "/m/06mb1,/m/0jb2l,/m/0ngt1", "caption": "Thunder roars in the distance as rain falls" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/Yy_OyLW9lBXU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yy_OyLW9lBXU.npy", "labels": "/m/09x0r,/t/dd00002", "caption": "An infant crying together with speech" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part19/YNDaVSIJaXVs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YNDaVSIJaXVs.npy", "labels": "/m/014yck,/m/07yv9,/m/0cmf2,/m/0k5j,/t/dd00128", "caption": "Aircraft engine and loud background roar" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YDzKjogSVOLM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YDzKjogSVOLM.npy", "labels": "/m/07qdb04,/m/09ddx,/m/09x0r,/m/0jbk", "caption": "Ducks quacking and birds chirping followed by a rooster crowing as a crowd of people talk" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/Yp9qRTh4BmSE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yp9qRTh4BmSE.npy", "labels": "/m/032s66,/m/04zjc", "caption": "A man speaks followed by another man screaming and rapid gunshots" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YPb6MqpdX5Jw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YPb6MqpdX5Jw.npy", "labels": "/m/0ngt1", "caption": "Rain falls and distant thunder roars with nearby faint clip-clops of a horse" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3qTL7QRk-tg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3qTL7QRk-tg.npy", "labels": "/m/07swgks,/m/0j6m2", "caption": "A group of male are singing while a river is flowing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part38/YuY4fe5DT1gI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YuY4fe5DT1gI.npy", "labels": "/m/01m2v,/m/0316dw", "caption": "A person is typing on a keyboard with some ruffling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YrbO727iF03I.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YrbO727iF03I.npy", "labels": "/m/03q5_w,/m/09x0r", "caption": "A person burping followed by a group of people talking and laughing with a man talking in the foreground" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YmYQrjcYNrW0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YmYQrjcYNrW0.npy", "labels": "/m/01bjv,/m/07qv_d5,/m/07yv9", "caption": "A vehicle horn is repeatedly tooting followed by a passing engine rumble" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/YjinJkonlrWc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YjinJkonlrWc.npy", "labels": "/m/09ct_,/m/09x0r", "caption": "An engine running and muffled speech" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part9/Y8ipe6b1LwHQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y8ipe6b1LwHQ.npy", "labels": "/m/023pjk,/m/04brg2", "caption": "Glass clinks, thumps occur, and then silverware clatters" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YQOmV7O9mFwg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YQOmV7O9mFwg.npy", "labels": "/m/01bjv,/m/07yv9,/m/09x0r", "caption": "Young people laughing and speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3ue0gJM0THk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3ue0gJM0THk.npy", "labels": "/m/02l6bg,/m/02mk9,/m/07pb8fc,/m/07q2z82,/t/dd00066", "caption": "Aircraft engine revs and creates propeller which" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YEzWEO2WD_MM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YEzWEO2WD_MM.npy", "labels": "/m/01d380", "caption": "A power tool drilling followed by plastic clanking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YSGaIvgwwWSE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YSGaIvgwwWSE.npy", "labels": "/m/06mb1,/m/0jb2l,/m/0ngt1", "caption": "Rain and thunder" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YrUq4w4EUSWA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YrUq4w4EUSWA.npy", "labels": "/m/01jt3m,/m/0838f", "caption": "Paper tearing followed by an electric motor buzzing before more paper tears than crinkles as bells chime proceeded by a toilet flushing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/Ysl_Pxpc7beo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ysl_Pxpc7beo.npy", "labels": "/m/07yv9,/m/0912c9,/t/dd00128", "caption": "A vehicle moving over pavement with loud horn honking noise" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9ZZHvwaH-CU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9ZZHvwaH-CU.npy", "labels": "/m/032s66", "caption": "Multiple gun shots woman screaming" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/Yk1QxQ4jJaEQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yk1QxQ4jJaEQ.npy", "labels": "/m/07r04,/m/07yv9,/m/09x0r,/t/dd00129", "caption": "A man talking as an idle truck engine runs" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part7/Y5ye0X5saadg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y5ye0X5saadg.npy", "labels": "/m/09ct_,/m/09x0r", "caption": "Helicopter blades spin with a humming engine, loud booms, and a man speaking over the radio" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/Yhzn_wGlzGpU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yhzn_wGlzGpU.npy", "labels": "/m/07yv9,/m/0k4j,/m/0ltv", "caption": "An aircraft accelerating as gusts of wind blow followed by fiber glass clanking while an emergency siren goes off in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YkEP-BwMarf8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YkEP-BwMarf8.npy", "labels": "/m/09x0r,/t/dd00112", "caption": "Plastic crinkling followed by a woman talking then cardboard shuffling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YEvZ3jOMYWxk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YEvZ3jOMYWxk.npy", "labels": "/m/02qldy,/m/02zsn,/m/09x0r", "caption": "An adult female is speaking in a quiet environment" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y5G6b_QWL3nY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y5G6b_QWL3nY.npy", "labels": "/m/07p9k1k,/m/0dxrf", "caption": "Female speech and sizzling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YPRUfwpmYwJ8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YPRUfwpmYwJ8.npy", "labels": "/m/07qlf79,/m/09x0r", "caption": "Compressed air spraying multiple times as a man is talking with faint metal clanging in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YK2kIOBeCfuo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YK2kIOBeCfuo.npy", "labels": "/m/028ght,/m/09x0r", "caption": "A person speaking and various laughter and clapping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YB3O476LeuXY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YB3O476LeuXY.npy", "labels": "/m/07pb8fc,/t/dd00130", "caption": "Humming and sputtering from an idling engine" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part15/YG0IsabU5hn4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YG0IsabU5hn4.npy", "labels": "/m/09t49,/t/dd00092", "caption": "Very strong wind is blowing, and leaves are rustling on the trees" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YS0YE96w0YRk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YS0YE96w0YRk.npy", "labels": "/m/028ght", "caption": "A man speaks and people laugh and clap" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part1/Y-oy0BkpMGAk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y-oy0BkpMGAk.npy", "labels": "/m/012f08,/m/07rknqz,/m/07yv9,/m/0k4j,/t/dd00134", "caption": "A vehicle engine revving and squealing tires" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part24/YW4GEwnXc9tQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YW4GEwnXc9tQ.npy", "labels": "/m/09ld4", "caption": "Music plays as a woman speaks while a frog croaks followed by girl and boy speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/YglAeihz0NAM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YglAeihz0NAM.npy", "labels": "/m/09x0r,/m/0ytgt,/t/dd00129", "caption": "Kids laughing then talking followed by a young man talking as wind blows into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YK2kIOBeCfuo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YK2kIOBeCfuo.npy", "labels": "/m/028ght,/m/09x0r", "caption": "An adult male speaks, and a crowd laughs and then cheers and applauds" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part38/YuhSDBwVrEdo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YuhSDBwVrEdo.npy", "labels": "/m/01w250", "caption": "A person whistling as wind blows lightly into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YKnXNy5Q6YS4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YKnXNy5Q6YS4.npy", "labels": "/m/01h3n,/m/03vt0,/m/09x0r", "caption": "Insects buzzing as a man is talking." }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/YwNiYSYJXssA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YwNiYSYJXssA.npy", "labels": "/m/03k3r,/m/09x0r,/m/0jbk", "caption": "A woman is speaking followed by a horse braying and speech from a crowd" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/Yw_Utn3CwAXE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yw_Utn3CwAXE.npy", "labels": "/m/01jt3m,/m/0838f", "caption": "A toilet flushes and a door creaks as it opens" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/YA61Mry8zBwE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YA61Mry8zBwE.npy", "labels": "/m/07rv9rh,/m/09x0r,/m/0jbk", "caption": "A man speaking over an intercom as a crowd of people applaud" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y0yxEvdnimGg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y0yxEvdnimGg.npy", "labels": "/m/068hy,/m/07rc7d9,/m/09x0r,/m/0bt9lr,/m/0jbk", "caption": "Several people talk as a few dogs bark, birds chirp and wind rustles" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YNeZerAPXR-A.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YNeZerAPXR-A.npy", "labels": "/m/01j3sz,/m/09x0r,/t/dd00125", "caption": "A woman shrieking and laughing, followed by a man laughing in the background, and a woman speaks a few words" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YrvtA7c1I4xo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YrvtA7c1I4xo.npy", "labels": "/m/07rqsjt", "caption": "A male speaking and shoes squeaking after a swoosh" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/Yj_NSuPnx5LA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yj_NSuPnx5LA.npy", "labels": "/m/07cx4", "caption": "A tapping noise followed by a person dialing the keys on a telephone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part19/YMvHpNzDpC6Q.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YMvHpNzDpC6Q.npy", "labels": "/m/012f08,/m/03q5_w,/m/07yv9,/m/09x0r,/m/0k4j", "caption": "A motor vehicle engine is running, two adult males speak, two burps occur, and person laughs" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/YcPiSd5nJLrI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YcPiSd5nJLrI.npy", "labels": "/m/014zdl,/m/07pxg6y,/m/07qsvvw", "caption": "Screaming and a big explosion and then screaming" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y1OyEgzXCkYE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1OyEgzXCkYE.npy", "labels": "/m/02qldy,/m/05zppz,/m/09x0r", "caption": "A male speaking over a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YXamQAY_WXRY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YXamQAY_WXRY.npy", "labels": "/m/0j6m2", "caption": "A man talking as water splashes and gurgles and a motor engine hums in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/Yq3SEOW2m4WY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yq3SEOW2m4WY.npy", "labels": "/m/01g50p,/m/0284vy3,/m/06d_3,/m/07jdr,/m/07rwm0c", "caption": "Soft clicking and electronic beeping is ongoing, while a large engine approaches, a train horn blows, and clattering occurs" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YECw5Yf7QoMo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YECw5Yf7QoMo.npy", "labels": "/m/02qldy,/m/05zppz,/m/09x0r", "caption": "A man delivers a speech while another man is speaking then audience claps" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part0/Y-EQByFLFqig.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y-EQByFLFqig.npy", "labels": "/m/06mb1,/m/0ngt1,/t/dd00038", "caption": "A man speaks with rain falling and thunder cracking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YDlWd7Wmdi1E.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YDlWd7Wmdi1E.npy", "labels": "/m/015p6,/m/07rc7d9,/m/09x0r,/m/0jbk", "caption": "A man is speaking as birds are squawking, and a dog barks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/Yk1QxQ4jJaEQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yk1QxQ4jJaEQ.npy", "labels": "/m/07r04,/m/07yv9,/m/09x0r,/t/dd00129", "caption": "A man speaking as well as an engine idling in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/Yi6MQCm58zlY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yi6MQCm58zlY.npy", "labels": "/m/020bb7,/m/068hy,/m/0jbk", "caption": "Squealing and rustling with a man speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part15/YG3YO2unWz7k.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YG3YO2unWz7k.npy", "labels": "/m/04_sv,/m/07yv9,/t/dd00128", "caption": "Clicking and sputtering then eventual revving of an idling engine" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YI_8KqxP5xOA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YI_8KqxP5xOA.npy", "labels": "/m/07qlf79", "caption": "Light, intermittent hissing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/YyL3gKa6YLoM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YyL3gKa6YLoM.npy", "labels": "/m/01d3sd,/m/09x0r", "caption": "A man talking as a person is snoring" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y0jGH7A_hpBM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y0jGH7A_hpBM.npy", "labels": "/m/02qldy,/m/05zppz,/m/09x0r", "caption": "A man narrating followed by another man speaking then speaking through a television speaker" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/Yorgwzt45ojE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yorgwzt45ojE.npy", "labels": "/m/015p6,/m/09x0r,/m/0h0rv,/t/dd00126", "caption": "A man talking as pigeons coo and bird wings flap" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YtwFypUcdgRc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YtwFypUcdgRc.npy", "labels": "/m/01bjv,/m/07yv9,/m/09x0r", "caption": "Wind blowing and people speaking with distant humming" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/Yos_2U4xqTqw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yos_2U4xqTqw.npy", "labels": "/m/014zdl,/m/07qsvvw,/m/07s2xch", "caption": "Heavy footsteps walking on a hard surface followed by a man grunting then two explosions" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YFKaJsvcyHTk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YFKaJsvcyHTk.npy", "labels": "/t/dd00002", "caption": "An infant crying" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YFXdoNvmrYxo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YFXdoNvmrYxo.npy", "labels": "/m/03vt0,/m/09x0r,/t/dd00129", "caption": "A girl talking followed by a man then a young boy talking as a bird chirps in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YL2dyilgQ8iM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YL2dyilgQ8iM.npy", "labels": "/m/09t49,/t/dd00092", "caption": "Footsteps walking on snow during camera muffling as wind blows into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3fomsZXG3aM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3fomsZXG3aM.npy", "labels": "/m/07q2z82,/m/07yv9,/t/dd00066", "caption": "An engine hums and then revs" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YTd2EEDdFlRY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YTd2EEDdFlRY.npy", "labels": "/m/07p9k1k", "caption": "A man talking as a woman talks in the distance while light music is playing followed by a guitar strumming and footsteps walking on gravel" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YCxaPpRJRkn0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YCxaPpRJRkn0.npy", "labels": "/m/01d3sd", "caption": "Footsteps shuffling on a hard surface followed by a person snoring" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YDNtF_mGzQes.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YDNtF_mGzQes.npy", "labels": "/m/07r04,/m/07yv9,/m/09x0r", "caption": "A man talking on loudspeakers along with an idling truck and a bustling crowd" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YC9NC7wJ7C3w.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YC9NC7wJ7C3w.npy", "labels": "/m/02qldy,/m/02zsn,/m/09x0r", "caption": "A woman speaking rapidly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part0/Y-NsC63dA01g.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y-NsC63dA01g.npy", "labels": "/m/01yrx,/m/068hy,/m/07qrkrw,/m/09x0r,/m/0jbk", "caption": "A woman talking as a cat meows" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YnLtNjMimLE0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YnLtNjMimLE0.npy", "labels": "/m/07pqc89,/m/0838f", "caption": "Running and splashing water" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YWU3qB7gf6ao.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YWU3qB7gf6ao.npy", "labels": "/m/02fs_r", "caption": "A short beep sounds and people talk far away" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YrbO727iF03I.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YrbO727iF03I.npy", "labels": "/m/03q5_w,/m/09x0r", "caption": "A loud belch followed by male human voices" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y6pssFJ0m-kU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y6pssFJ0m-kU.npy", "labels": "/m/015p6,/m/020bb7,/m/07pggtn", "caption": "Chirping of birds with wind blowing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part9/Y8ZH_PoK0clI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y8ZH_PoK0clI.npy", "labels": "/m/02dgv,/m/09x0r", "caption": "Door opening with woman faintly speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YK03ydb1uaoQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YK03ydb1uaoQ.npy", "labels": "/m/01d3sd,/t/dd00125", "caption": "Static sounds are vibrating along with snoring" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YXamQAY_WXRY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YXamQAY_WXRY.npy", "labels": "/m/0j6m2", "caption": "A man speaks as water splashes" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YHxZADVzNIqs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YHxZADVzNIqs.npy", "labels": "/m/015p6,/m/020bb7,/m/07pggtn", "caption": "Several birds chirp with trickling water followed by booms of drums" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y1wW0YJQ-Xa0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1wW0YJQ-Xa0.npy", "labels": "/m/07qlf79,/m/09x0r", "caption": "Someone coughs as a spray can be being used" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YmaVYiednkSg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YmaVYiednkSg.npy", "labels": "/m/07qlf79,/m/09x0r", "caption": "Low humming and vibrating with a spray and a man speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/Yn4VktYihtJU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yn4VktYihtJU.npy", "labels": "/m/07swgks,/m/09x0r", "caption": "A man yelling in the distance followed by two girls shouting as a motorboat engine runs and water sprays while wind blows into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YK_Vre_-4KqU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YK_Vre_-4KqU.npy", "labels": "/m/07yv9,/m/0k5j,/t/dd00129", "caption": "The loud idling of a machine" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YAj_VMUSNjNM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YAj_VMUSNjNM.npy", "labels": "/m/02mk9,/m/07q2z82,/m/07yv9,/m/0k4j", "caption": "Engine revving louder and louder than eases down" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YCvNAwby6Xos.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YCvNAwby6Xos.npy", "labels": "/m/09x0r,/m/0llzx,/t/dd00125", "caption": "A sewing machine operating several times followed by gears cranking as a man is talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/YpI_kPedctoo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YpI_kPedctoo.npy", "labels": "/m/04_sv,/m/07yv9,/m/09x0r", "caption": "Several motorcycle engines running and revving as a man talks in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y54eRRbCtPn8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y54eRRbCtPn8.npy", "labels": "/m/02qldy,/m/02zsn,/m/09x0r", "caption": "A woman is speaking briefly in a quiet environment" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/Yp_BB_rJaF7Q.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yp_BB_rJaF7Q.npy", "labels": "/m/09ld4", "caption": "A man talking as birds are chirping alongside dirt and gravel shuffling followed by an animal squeaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/YztSjcZNUY7A.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YztSjcZNUY7A.npy", "labels": "/m/09x0r,/t/dd00002", "caption": "A woman talks as a baby cries" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part19/YMj_BO-iK1G4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YMj_BO-iK1G4.npy", "labels": "/m/0llzx", "caption": "Vibrations from a sewing machine with clicking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YHUwXtfYRFwk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YHUwXtfYRFwk.npy", "labels": "/m/012f08,/m/01bjv,/m/07yv9,/m/0k4j", "caption": "A bus is traveling on the road" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YJp64Whpr3BA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YJp64Whpr3BA.npy", "labels": "/m/0llzx", "caption": "A sewing machine running briefly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part4/Y350OCezayrk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y350OCezayrk.npy", "labels": "/m/02mk9,/m/07yv9,/m/0k4j,/t/dd00066,/t/dd00130", "caption": "An engine of a vehicle is starting" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part1/Y0a9wVat2PWk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y0a9wVat2PWk.npy", "labels": "/m/0284vy3,/m/07jdr,/m/07yv9", "caption": "A train sounds horn and travels" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YTd2EEDdFlRY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YTd2EEDdFlRY.npy", "labels": "/m/07p9k1k", "caption": "A man speaks as music plays followed by footsteps" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/YyL3gKa6YLoM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YyL3gKa6YLoM.npy", "labels": "/m/01d3sd,/m/09x0r", "caption": "A man speaking followed by snoring" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YKJhGuhNHToA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YKJhGuhNHToA.npy", "labels": "/m/083vt", "caption": "Brief silence followed by wood shuffling on a stone surface" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YYk274Wr5iIE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YYk274Wr5iIE.npy", "labels": "/m/06mb1", "caption": "Wind and water splashing and trickling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y22L_3pBa1AI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y22L_3pBa1AI.npy", "labels": "/m/07yv9,/m/0k4j,/t/dd00134", "caption": "Vibrations from an engine as a car speeds past" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YK8-b0VtNOqA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YK8-b0VtNOqA.npy", "labels": "/m/03k3r,/m/09x0r,/m/0jbk", "caption": "Floor sweeping and a man then a woman talking in the background followed by horses neighing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YYQGW5AwDOIo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YYQGW5AwDOIo.npy", "labels": "/m/07yv9,/m/0k4j,/m/0ltv", "caption": "Motor vehicles are driving with loud engines and a person whistles" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YU5ij0M7T-hk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YU5ij0M7T-hk.npy", "labels": "/m/02dgv,/m/09x0r", "caption": "Footsteps and scuffing occur, after which a door grinds, squeaks and clicks, an adult male speaks, and the door grinds, squeaks and clicks shut with a thump" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/Ysl_Pxpc7beo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ysl_Pxpc7beo.npy", "labels": "/m/07yv9,/m/0912c9,/t/dd00128", "caption": "A car horn honks and echoes" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y8ycflE3dIHw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y8ycflE3dIHw.npy", "labels": "/m/01g50p,/m/0284vy3,/m/06d_3,/m/07jdr,/m/07rwm0c", "caption": "A train passes by followed by a horn" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YPVvi2SDOjVc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YPVvi2SDOjVc.npy", "labels": "/m/07yv9,/m/0912c9,/m/0k4j,/t/dd00128", "caption": "A vehicle horn honking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/YpaetCbEqp2w.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YpaetCbEqp2w.npy", "labels": "/m/0463cq4", "caption": "Small child crying followed by the child blowing their nose" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YBUAPM4D3-h8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBUAPM4D3-h8.npy", "labels": "/m/015p6,/m/020bb7,/m/07pggtn", "caption": "A woman and a child is communicating, and birds chirp" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part15/YG0IsabU5hn4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YG0IsabU5hn4.npy", "labels": "/m/09t49,/t/dd00092", "caption": "Strong wind is blowing while leaves are rustling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YECw5Yf7QoMo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YECw5Yf7QoMo.npy", "labels": "/m/02qldy,/m/05zppz,/m/09x0r", "caption": "A man speaks while another speaks on top as well followed by clapping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/YyVVLq4ao1Ck.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YyVVLq4ao1Ck.npy", "labels": "/m/015p6,/m/020bb7,/m/07pggtn", "caption": "Birds chirping with insects buzzing and outdoor ambiance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YqeSl7YZAfs4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YqeSl7YZAfs4.npy", "labels": "/m/0130jx,/m/02jz0l,/m/0838f", "caption": "Water flowing and splashing from a faucet with a man speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YrgrmLLhxoCQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YrgrmLLhxoCQ.npy", "labels": "/t/dd00112", "caption": "Dry scraping and scratching" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/YynHdcJ9Oqaw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YynHdcJ9Oqaw.npy", "labels": "/m/07rqsjt", "caption": "A series of synthesized laser effects" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/YxpZna_FwDhI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YxpZna_FwDhI.npy", "labels": "/m/09x0r,/m/0llzx", "caption": "A click occurs and then a woman speaks followed by a sewing machine stitching" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part9/Y8Zo30kV5aiI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y8Zo30kV5aiI.npy", "labels": "/m/012n7d,/m/03j1ly,/m/03kmc9", "caption": "Sirens ring as a vehicle passes" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YYqYCDis3EUA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YYqYCDis3EUA.npy", "labels": "/m/01h3n,/m/03vt0,/m/0h2mp", "caption": "The chirping of birds, interrupted by a rustling sound, and a buzzing fly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y1IoHRTUp86c.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1IoHRTUp86c.npy", "labels": "/m/07yv9,/m/0k5j,/t/dd00129", "caption": "A woman speaks briefly, and a muffled engine rumbles" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part24/YVjSEIRnLAh8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YVjSEIRnLAh8.npy", "labels": "/m/09x0r,/m/0dxrf", "caption": "Food sizzling with some knocking and banging followed by a woman speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YXQxIXaX_7M0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YXQxIXaX_7M0.npy", "labels": "/m/09t49,/m/09x0r", "caption": "Running water and distant speech" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YObWjGBJF_94.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YObWjGBJF_94.npy", "labels": "/m/02jz0l,/m/07ptzwd", "caption": "A series of plastic clicking as muffled rock music plays and audio static hisses in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part4/Y350OCezayrk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y350OCezayrk.npy", "labels": "/m/02mk9,/m/07yv9,/m/0k4j,/t/dd00066,/t/dd00130", "caption": "A motor vehicle engine starter grinds, and a mid-size engine starts up and idles smoothly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part0/Y-NrFeH-kBSM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y-NrFeH-kBSM.npy", "labels": "/m/032s66", "caption": "Clicks of weapons being loaded followed by a gunshot and a clink then a man speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4ftDFi4684Y.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4ftDFi4684Y.npy", "labels": "/m/07qjznl", "caption": "Footsteps shuffling followed by a wooden door softly opening then a clock ticking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y1L_OyngNZMA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1L_OyngNZMA.npy", "labels": "/m/01j3sz,/m/07p6fty,/m/09x0r", "caption": "Two men talking on a microphone as a crowd of people laugh and applaud" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YCxaPpRJRkn0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YCxaPpRJRkn0.npy", "labels": "/m/01d3sd", "caption": "Male snoring loudly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/YeYbFtxZmKL4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YeYbFtxZmKL4.npy", "labels": "/m/03k3r,/m/09x0r,/m/0jbk", "caption": "Horses trotting while wood clanks several times as a woman talks and birds chirp in the background alongside wind blowing into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9vZDsGjyh5M.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9vZDsGjyh5M.npy", "labels": "/m/07r04,/m/07yv9,/m/0k4j", "caption": "Engine idling consistently" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/Ym_U506sf9p4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ym_U506sf9p4.npy", "labels": "/m/07p9k1k,/m/07ptfmf,/m/0dxrf", "caption": "A woman talking followed by plastic thumping then metal clanking as food and oil sizzles" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y14izd_i3ryE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y14izd_i3ryE.npy", "labels": "/m/07rv9rh,/m/09x0r,/m/0jbk", "caption": "A man talking as another man speaks through a megaphone as wind blows into a microphone and a vehicle engine runs" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part0/Y-CcGuq0yoKo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y-CcGuq0yoKo.npy", "labels": "/m/02qldy,/m/02zsn,/m/09x0r", "caption": "A female voice speaking on a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YIhvXtS9-IxM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YIhvXtS9-IxM.npy", "labels": "/m/07yv9,/m/09ct_", "caption": "A helicopter is flying" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YcFHFVGOtp6g.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YcFHFVGOtp6g.npy", "labels": "/m/09ld4,/m/09x0r", "caption": "Gravely sound with women voice in background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YtmLAXm1WlnE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YtmLAXm1WlnE.npy", "labels": "/m/01h3n,/m/03vt0,/m/0h2mp", "caption": "A woman speaks with nearby buzzing of insects" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part38/Yv59uHr-B1no.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yv59uHr-B1no.npy", "labels": "/m/09ld4", "caption": "Chirps and croaks of different frogs near and far" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YEUZaxaWqhwg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YEUZaxaWqhwg.npy", "labels": "/m/07yv9,/m/0cmf2,/m/0k5j", "caption": "An aircraft is moving with low speech of people talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YOUUckswAaNI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YOUUckswAaNI.npy", "labels": "/m/02dgv", "caption": "Males speaking and birds chirping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/Yp9qRTh4BmSE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yp9qRTh4BmSE.npy", "labels": "/m/032s66,/m/04zjc", "caption": "A man shouts followed by rapid gunfire" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/YhDMHIDJdfDA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YhDMHIDJdfDA.npy", "labels": "/m/01d3sd,/t/dd00125", "caption": "Continuous snoring" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part0/Y-aYumc8KoXg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y-aYumc8KoXg.npy", "labels": "/m/07yv9,/m/0912c9,/m/0k4j", "caption": "A vehicle is driving, and a horn is honking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YOTLtzk0W4zg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YOTLtzk0W4zg.npy", "labels": "/m/07yv9,/m/09x0r,/m/0k4j,/t/dd00128,/t/dd00130", "caption": "A man talks as a vehicle engine runs idle" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YPTyFYxXdut4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YPTyFYxXdut4.npy", "labels": "/m/07pqc89,/m/0838f,/m/09x0r", "caption": "Female speech and water trickling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/YpPLisQ_QXxw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YpPLisQ_QXxw.npy", "labels": "/m/07yv9,/m/0912c9,/m/0k4j", "caption": "A car horn blows amid road noise" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YR91bUbtKrRs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YR91bUbtKrRs.npy", "labels": "/m/09x0r,/t/dd00002", "caption": "Two woman speaking then a baby crying" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9BukzlPNqC8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9BukzlPNqC8.npy", "labels": "/m/01d380,/m/09x0r", "caption": "Soft drilling noise" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YBz9Y5nZK3eo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBz9Y5nZK3eo.npy", "labels": "/m/01m2v,/m/0316dw", "caption": "Typing on a computer keyboard for a few seconds" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/Yk4XyfaWVLEY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yk4XyfaWVLEY.npy", "labels": "/m/01bjv,/m/07yv9,/m/09x0r", "caption": "A bus engine running as leaves rustle and a kid talks in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YENTi8Sn4vdM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YENTi8Sn4vdM.npy", "labels": "/m/0j6m2", "caption": "A woman and a young boy talking as water splashes and a group of kids yell in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/YpHYkWkZ4guE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YpHYkWkZ4guE.npy", "labels": "/m/06wzb,/m/07rjwbb", "caption": "Scraping and hissing with some light knocks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YAj_VMUSNjNM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YAj_VMUSNjNM.npy", "labels": "/m/02mk9,/m/07q2z82,/m/07yv9,/m/0k4j", "caption": "An engine revs several times" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/Yn4VktYihtJU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yn4VktYihtJU.npy", "labels": "/m/07swgks,/m/09x0r", "caption": "Strong gusts of wind are followed by cheers and shouts from several people plus the chatter of girl" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/YhxbmDeNSO6Q.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YhxbmDeNSO6Q.npy", "labels": "/m/09x0r,/m/0llzx", "caption": "Vibrations from a sewing machine followed by clicks and a man speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/Yc6YJgZ3qzOw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yc6YJgZ3qzOw.npy", "labels": "/m/09ct_", "caption": "A small motor is running and whirring is present, then the motor stops and a whoosh occurs" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3hzy-FL24no.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3hzy-FL24no.npy", "labels": "/m/0j6m2", "caption": "A small motor is buzzing and water is running, splashing and gurgling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YsVYTOURVsQ0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YsVYTOURVsQ0.npy", "labels": "/m/07pqc89,/m/09x0r", "caption": "Water trickling with man speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/Ylh801oHGtD4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ylh801oHGtD4.npy", "labels": "/m/01d380,/m/09x0r", "caption": "Male speech and then a door shutting" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YLBe33dw9ezg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YLBe33dw9ezg.npy", "labels": "/m/09ct_,/m/09x0r", "caption": "Buzzing sound moving nearer and further" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YP4qd8uodw_M.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YP4qd8uodw_M.npy", "labels": "/m/02fs_r,/m/09x0r", "caption": "Muffled man speech with tapping and clicks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YD9GHUPGWsV0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YD9GHUPGWsV0.npy", "labels": "/m/07bgp,/m/07q0h5t,/m/09x0r", "caption": "Female speaking and a sheep bleating" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YQv1HXaT-28U.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YQv1HXaT-28U.npy", "labels": "/m/07qsvvw", "caption": "Liquid spraying and splattering on a hard surface as kids laugh in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YNwoBDrTlbTI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YNwoBDrTlbTI.npy", "labels": "/t/dd00018", "caption": "A small animal vocalizing and squeaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YFc9pG54DDJM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YFc9pG54DDJM.npy", "labels": "/m/01jt3m,/m/0838f", "caption": "A toilet flushes and water drains" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/YwbPmnxCLoRQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YwbPmnxCLoRQ.npy", "labels": "/m/0395lw", "caption": "Church bells tolling followed by a smaller bell ringing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YcK2kSVR1d2o.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YcK2kSVR1d2o.npy", "labels": "/m/07qsvvw,/m/0g6b5", "caption": "Burst and popping sounds followed by a loud explosion" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YLvMA1Wcgu3w.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YLvMA1Wcgu3w.npy", "labels": "/m/09ld4", "caption": "A man talking followed by plastic clunking and rattling as frogs croak and crickets chirp" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YBUAPM4D3-h8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBUAPM4D3-h8.npy", "labels": "/m/015p6,/m/020bb7,/m/07pggtn", "caption": "A girl speaks with some rustling of grass and a distant bird chirping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YWUpeplQr3A4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YWUpeplQr3A4.npy", "labels": "/m/01d380", "caption": "A person screeching followed by a man screaming as a power tool drills and liquid sprays and gurgles" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/Yp_BB_rJaF7Q.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yp_BB_rJaF7Q.npy", "labels": "/m/09ld4", "caption": "A man speaks with distant birds chirping and a small loud chirp" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/Ys_EWjoiVfzo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ys_EWjoiVfzo.npy", "labels": "/m/0llzx", "caption": "Some rustling with humming and consistent clicks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YXplKBvZaHXA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YXplKBvZaHXA.npy", "labels": "/m/04_sv,/m/07yv9,/m/09x0r,/t/dd00129", "caption": "Revving of a motorcycle with a man speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4s2rRnu2PZo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4s2rRnu2PZo.npy", "labels": "/m/07rqsjt", "caption": "Music plays continuously along with swooshing followed by a man speaking quickly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YSL3wB5sDcdw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YSL3wB5sDcdw.npy", "labels": "/m/09t49,/m/0d31p", "caption": "A machine running and minor rustling of leaves" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4s2rRnu2PZo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4s2rRnu2PZo.npy", "labels": "/m/07rqsjt", "caption": "Loud metal/rock music plays, with gunshots heard in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YOr7umk40TZA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YOr7umk40TZA.npy", "labels": "/m/01jwx6", "caption": "Vibrations from a sewing machine" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YECw5Yf7QoMo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YECw5Yf7QoMo.npy", "labels": "/m/02qldy,/m/05zppz,/m/09x0r", "caption": "An adult male speaks in the foreground while and another adult male speaks in the background, and a crowd applauds" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YmSF_FqBtRPs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YmSF_FqBtRPs.npy", "labels": "/m/01hnzm,/m/07cx4", "caption": "A telephone rings with bell sounds" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part7/Y5OM3tJh51pE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y5OM3tJh51pE.npy", "labels": "/m/02qldy,/m/02zsn,/m/09x0r", "caption": "A woman gives a speech" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YnmLMLgWPmFM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YnmLMLgWPmFM.npy", "labels": "/m/09x0r,/m/0j6m2", "caption": "An engine idling continuously" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part19/YMkbP_8zJwXU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YMkbP_8zJwXU.npy", "labels": "/m/015p6,/m/068hy,/m/09ddx,/t/dd00129", "caption": "A bird chirping as water trickles and wind blows into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y1HCuBnPLMqQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1HCuBnPLMqQ.npy", "labels": "/m/07pqc89", "caption": "Trickling water sounds with breathing in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YL2dyilgQ8iM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YL2dyilgQ8iM.npy", "labels": "/m/09t49,/t/dd00092", "caption": "Muffled rustling noise over wind blowing over a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part1/Y0a9wVat2PWk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y0a9wVat2PWk.npy", "labels": "/m/0284vy3,/m/07jdr,/m/07yv9", "caption": "A muffled train running on railroad tracks followed by a train horn honking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part27/Y_BSmz3SEW1w.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y_BSmz3SEW1w.npy", "labels": "/m/015p6,/m/0h0rv,/t/dd00125,/t/dd00129", "caption": "Rustling pigeons coo" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YtdpiXW68adA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YtdpiXW68adA.npy", "labels": "/m/0463cq4,/m/09x0r", "caption": "A woman cries and speaks and a second woman speaks in return" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/Ycz0FSQDVBMw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ycz0FSQDVBMw.npy", "labels": "/m/06wzb,/m/07rjwbb", "caption": "Hissing with some cracking and rustling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/YzEM94PH29VQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YzEM94PH29VQ.npy", "labels": "/m/09x0r,/t/dd00002", "caption": "An infant crying as a group of women and children yell in the background as a woman talks in the foreground" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YDNtF_mGzQes.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YDNtF_mGzQes.npy", "labels": "/m/07r04,/m/07yv9,/m/09x0r", "caption": "A crowd of children talking as a man speaks over an intercom as a large truck engine runs idle followed by pressurized air releasing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YBOB65Nd0pXo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBOB65Nd0pXo.npy", "labels": "/m/02l6bg,/m/07yv9,/m/09ct_", "caption": "A helicopter engine operating while wind blows heavily into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YOt0bN_hz2ec.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YOt0bN_hz2ec.npy", "labels": "/m/0195fx,/m/01g50p,/m/0284vy3,/m/06d_3,/m/07jdr,/m/07rwm0c", "caption": "Train blows horn twice as it speeds down the tracks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YQt0_xTadAT0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YQt0_xTadAT0.npy", "labels": "/m/09ld4", "caption": "Two instances of bird wings flapping while frogs are croaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YHkbCUN4V3TU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YHkbCUN4V3TU.npy", "labels": "/m/09x0r,/m/0ytgt,/t/dd00125", "caption": "A baby whines and laughs and a woman speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YTSdAJWJ-tW0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YTSdAJWJ-tW0.npy", "labels": "/m/012f08,/m/07yv9,/m/0k4j,/t/dd00134", "caption": "People are speaking as a vehicle goes by" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y6eX6bJOFftA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y6eX6bJOFftA.npy", "labels": "/m/02rlv9,/m/07yv9,/m/09x0r", "caption": "Ducks quack and men speak with distant humming" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/Ycr0GiZr0TNY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ycr0GiZr0TNY.npy", "labels": "/m/01j3sz,/t/dd00001", "caption": "Babies laugh with a spray noise" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y7WkB6pflr6o.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y7WkB6pflr6o.npy", "labels": "/m/02qldy,/m/02zsn,/m/09x0r", "caption": "A woman delivering a speech" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part0/Y-R69Fa-mCaY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y-R69Fa-mCaY.npy", "labels": "/m/01j4z9,/m/083vt", "caption": "Sound of cutting with a chainsaw with a little pause and again followed by the same sound" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part9/Y8ipe6b1LwHQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y8ipe6b1LwHQ.npy", "labels": "/m/023pjk,/m/04brg2", "caption": "A glass link occurs, a thump, and then clattering" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4sb9jN0SgTM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4sb9jN0SgTM.npy", "labels": "/m/02mk9,/m/07pb8fc,/m/07q2z82,/m/07yv9,/m/09x0r,/m/0k4j,/t/dd00066", "caption": "A car revving loudly followed by a man talking close by" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YBn4lc01q9vE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBn4lc01q9vE.npy", "labels": "/m/0130jx,/m/02jz0l,/m/03dnzn,/m/0838f", "caption": "Water is running and hitting a surface and women speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/YwoadpeAGHUQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YwoadpeAGHUQ.npy", "labels": "/m/012ndj,/m/03j1ly,/m/03kmc9", "caption": "An emergency siren wailing as a truck engine runs idle followed by wind blowing into a microphone then water spraying as a man yells" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part7/Y6Nvu6EcpdE8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y6Nvu6EcpdE8.npy", "labels": "/m/07pb8fc,/m/07yv9,/m/09x0r,/t/dd00130", "caption": "Wind blowing with a man speaking followed by a click and light hum" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/YxUWSHYoslPQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YxUWSHYoslPQ.npy", "labels": "/m/04brg2,/m/09x0r", "caption": "A man speaks with some rattling and banging with a high frequency ringing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YI_vN_BFUr0Y.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YI_vN_BFUr0Y.npy", "labels": "/m/01g50p,/m/0284vy3,/m/04zmvq,/m/06d_3,/m/07jdr,/m/07yv9", "caption": "Railroad tracks clickety-clack as train horn blasts" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/YxbLW9Wt1Jsg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YxbLW9Wt1Jsg.npy", "labels": "/m/0llzx", "caption": "Some rustling with short bursts of vibrations from a sewing machine" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YLCwSUVuTyvg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YLCwSUVuTyvg.npy", "labels": "/m/02dgv", "caption": "Opening and closing a door" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part19/YMSziND26UTA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YMSziND26UTA.npy", "labels": "/m/01h3n,/m/03vt0,/m/0h2mp", "caption": "Many bees are buzzing, music is playing in the background, and roosters crow, one nearby and one in the far distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YRk-ujWKzPuc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YRk-ujWKzPuc.npy", "labels": "/m/06mb1,/t/dd00038", "caption": "Hard rain is falling and splashing on a surface" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/YhJtOGmN_KVw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YhJtOGmN_KVw.npy", "labels": "/m/09x0r,/t/dd00112,/t/dd00125", "caption": "A man speaking and plastic crumpling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YDjKGzOe_COc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YDjKGzOe_COc.npy", "labels": "/m/02qldy,/m/02zsn,/m/09x0r", "caption": "A female child speaks in a quiet environment" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y1a2XWJ8NA_Q.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1a2XWJ8NA_Q.npy", "labels": "/m/019jd,/m/02rlv9,/m/07yv9,/m/09x0r", "caption": "A motorboat engine running as two women are talking and wind is blowing into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part19/YMtK8L8gXRrI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YMtK8L8gXRrI.npy", "labels": "/m/01jt3m", "caption": "A toilet flushing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3hzy-FL24no.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3hzy-FL24no.npy", "labels": "/m/0j6m2", "caption": "Water running quickly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3rna9zo5ZOs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3rna9zo5ZOs.npy", "labels": "/m/02qldy,/m/05zppz,/m/09x0r", "caption": "Male speaking with many people cheering in background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y1FNJbN-eHY4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1FNJbN-eHY4.npy", "labels": "/m/03q5_w,/m/09x0r", "caption": "Someone burps and then laughs" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y0qbHT34qTZE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y0qbHT34qTZE.npy", "labels": "/m/032s66,/m/06q74,/m/09x0r", "caption": "Male yelling and multiple gunshots" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YC5kmOK_l4jc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YC5kmOK_l4jc.npy", "labels": "/m/09x0r,/m/0ytgt,/t/dd00001", "caption": "A baby laughs each time as another older child speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YHVz-FJBf_iM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YHVz-FJBf_iM.npy", "labels": "/m/01jt3m,/m/0838f", "caption": "A man talking during camera muffling followed by water gurgling in a drain then a toilet flushing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YZ1Cyj4N05lk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YZ1Cyj4N05lk.npy", "labels": "/m/01w250", "caption": "A man whistling followed by a man yelling as plastic rustles and clanks in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YbAqgL5dCQOE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YbAqgL5dCQOE.npy", "labels": "/m/06mb1,/m/07r10fb,/t/dd00038", "caption": "Rain falling with distant hums of traffic" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YAWGnTI0e2Fs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YAWGnTI0e2Fs.npy", "labels": "/m/09ct_", "caption": "A toy helicopter flying then powering down before starting up" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/YgwQMkQmBITE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YgwQMkQmBITE.npy", "labels": "/m/083vt,/m/09x0r,/t/dd00125", "caption": "A man talking followed by several lights scrapping on a wooden surface as wood clanks in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YTd2EEDdFlRY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YTd2EEDdFlRY.npy", "labels": "/m/07p9k1k", "caption": "A man is speaking as music plays followed by musical instrument sounds" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YtNxfdAd14qE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YtNxfdAd14qE.npy", "labels": "/m/07p9k1k", "caption": "A machine makes buzzing sound with low television noise in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/Yjid4t-FzUn0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yjid4t-FzUn0.npy", "labels": "/m/03fwl,/m/07s04w4,/m/09x0r", "caption": "A man is speaking in high tone while a goat is bleating one time" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/YfGGYeXR_LS8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YfGGYeXR_LS8.npy", "labels": "/m/01w250,/m/09x0r", "caption": "A man is speaking with whistling and rain background noise" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YR_g4RpU9mO0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YR_g4RpU9mO0.npy", "labels": "/m/019jd,/m/02rlv9,/m/07yv9", "caption": "A motorboat engine running idle then accelerating as water trickles then splashes" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YLCwSUVuTyvg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YLCwSUVuTyvg.npy", "labels": "/m/02dgv", "caption": "Glass doors rattling and sliding shut followed by a plastic clack" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YOt0bN_hz2ec.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YOt0bN_hz2ec.npy", "labels": "/m/0195fx,/m/01g50p,/m/0284vy3,/m/06d_3,/m/07jdr,/m/07rwm0c", "caption": "A honk followed by loud gusts of wind as a train passes by" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YlgwpIImXCWA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YlgwpIImXCWA.npy", "labels": "/m/083vt,/m/09x0r,/t/dd00125", "caption": "A man talking followed by wood sawing then paper shuffling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YXi6V0LGvqoo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YXi6V0LGvqoo.npy", "labels": "/m/01z5f,/m/068hy,/m/07rc7d9,/m/0bt9lr,/m/0jbk", "caption": "Dogs bark and whine and growl" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YK-7Y8yhcUiw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YK-7Y8yhcUiw.npy", "labels": "/m/01d3sd,/m/068hy,/m/0bt9lr,/m/0jbk", "caption": "Loud nearby snoring" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part19/YMjSegUnQXr4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YMjSegUnQXr4.npy", "labels": "/m/015p6,/m/0h0rv,/t/dd00125", "caption": "Pigeons cooing and bird wings flapping during light scrapping on a metal surface while a construction machine operates in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part4/Y2j8pxiFvElM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y2j8pxiFvElM.npy", "labels": "/m/01yrx,/m/068hy,/m/07qrkrw,/m/0jbk", "caption": "A pet cat meows two times" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YtaYKM1OSTwE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YtaYKM1OSTwE.npy", "labels": "/m/03fwl,/m/07bgp,/m/0ch8v,/m/0jbk", "caption": "Several goats baaing as grass shuffles followed by a person chuckling in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/YdJYO3RbBabE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YdJYO3RbBabE.npy", "labels": "/m/02fs_r", "caption": "An electronic beep followed by a man talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YDrCm-HpX67k.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YDrCm-HpX67k.npy", "labels": "/m/083vt", "caption": "Wood shuffling and clanking followed by knocking on wood and leaves rustling as wind blows into a microphone and a crow caws in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YEBCH7TPgiPc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YEBCH7TPgiPc.npy", "labels": "/m/07q2z82,/m/07yv9,/m/0k4j", "caption": "An engine revving as it idles" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/YxpZna_FwDhI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YxpZna_FwDhI.npy", "labels": "/m/09x0r,/m/0llzx", "caption": "A click is followed by a woman speaking and then a sewing machine stitching" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part1/Y0AsXkZkqelg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y0AsXkZkqelg.npy", "labels": "/m/028ght", "caption": "An idle vehicle engine running normally before stuttering" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part15/YFlk-X0gwjF4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YFlk-X0gwjF4.npy", "labels": "/m/020bb7,/m/09x0r,/t/dd00129", "caption": "A man talking followed by several footsteps walk on grass and leaves rustling while birds chirp in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YNtQiduPRiRg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YNtQiduPRiRg.npy", "labels": "/m/01j3sz,/m/09x0r", "caption": "A man and a young girl laughing as a power tool sands a surface" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/Yy_OyLW9lBXU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yy_OyLW9lBXU.npy", "labels": "/m/09x0r,/t/dd00002", "caption": "A group of infants crying as a man and a woman talk" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/Yd6gu2w19YQo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yd6gu2w19YQo.npy", "labels": "/m/01j3sz", "caption": "An infant laughing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y6ukYSXzfEgQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y6ukYSXzfEgQ.npy", "labels": "/m/02jz0l,/m/0838f", "caption": "A bird calls in the distance occasionally, a hollow clanking sound is followed by rushing water, a double thump, and a trickling sound" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part7/Y6OlHuvJR_Dk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y6OlHuvJR_Dk.npy", "labels": "/m/07yv9,/m/09ct_", "caption": "Loud wind with a faint mechanical whirring sound" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y1L_OyngNZMA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1L_OyngNZMA.npy", "labels": "/m/01j3sz,/m/07p6fty,/m/09x0r", "caption": "A man speaks into an echoing, a crowd laughs and cheers" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/Yd1tL-9BILy8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yd1tL-9BILy8.npy", "labels": "/m/015p6,/m/020bb7,/m/07r_25d,/m/0h0rv", "caption": "Pigeons cooing followed by footsteps shuffling on gravel" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YlfAFQ0-wDJU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YlfAFQ0-wDJU.npy", "labels": "/m/034srq,/m/03m9d0z", "caption": "Ocean waves crashing as wind blows heavily into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YBoe3MeEpn_c.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBoe3MeEpn_c.npy", "labels": "/m/04brg2,/m/09x0r,/t/dd00125", "caption": "A metal pan clacking followed by compressed air spraying then an aerosol can tapping a hard surface while a man talks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YSePTNAN7s-w.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YSePTNAN7s-w.npy", "labels": "/m/01jt3m,/m/0838f", "caption": "A young woman speaks loudly with a toilet flushing sound" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part24/YVMsbrcHPBfk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YVMsbrcHPBfk.npy", "labels": "/m/03fwl", "caption": "A goat baaing normally before and after a goat screaming" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YRfGapDlAYoQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YRfGapDlAYoQ.npy", "labels": "/m/01w250", "caption": "A person whistles a tune with people talking low in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y1WTSW96XP6E.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1WTSW96XP6E.npy", "labels": "/m/04_sv,/m/07yv9,/m/09x0r", "caption": "A man is speaking followed by a tap and motorcycle turning on" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/YfGGYeXR_LS8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YfGGYeXR_LS8.npy", "labels": "/m/01w250,/m/09x0r", "caption": "Whistling is ongoing while an adult male speaks, and water is pattering in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part19/YNJEPbGVBJIQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YNJEPbGVBJIQ.npy", "labels": "/m/012f08,/m/04_sv,/m/07yv9,/m/09x0r,/m/0btp2,/t/dd00128", "caption": "A man talking followed by a vehicle horn honking then a motorbike accelerating and driving by" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YAI1OweEW8C0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YAI1OweEW8C0.npy", "labels": "/m/06mb1,/m/07r10fb,/m/0jb2l,/m/0ngt1", "caption": "Wind blowing into a microphone followed by thunder roaring in the distance while a stream of water trickles in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y7MLERaOgK_Y.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y7MLERaOgK_Y.npy", "labels": "/m/0llzx", "caption": "A young girl singing as a sewing machine operates" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9dLLsZVRSZI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9dLLsZVRSZI.npy", "labels": "/m/07r04,/m/07yv9,/t/dd00129", "caption": "A truck is idling, and a horn honks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YcFoXRmGgIME.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YcFoXRmGgIME.npy", "labels": "/m/01g50p,/m/0284vy3,/m/04zmvq,/m/06d_3,/m/07jdr,/m/07yv9", "caption": "High pitches squealing and a horn blowing with constant humming of an engine" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/YzoctgurhvHE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YzoctgurhvHE.npy", "labels": "/m/012f08,/m/02dgv,/m/04gxbd,/m/07yv9", "caption": "A man speaks with some clicking as wind blows and a distant motor hums" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YPRUfwpmYwJ8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YPRUfwpmYwJ8.npy", "labels": "/m/07qlf79,/m/09x0r", "caption": "A man talking as compressed air is spraying with wood clanking in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/Yc6YJgZ3qzOw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yc6YJgZ3qzOw.npy", "labels": "/m/09ct_", "caption": "A toy helicopter flying followed by wind blowing into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y4CAMv5nlr-0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4CAMv5nlr-0.npy", "labels": "/m/02qldy,/m/05zppz,/m/09x0r", "caption": "A man gives a speech followed by applause" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part4/Y2msevPMQB4M.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y2msevPMQB4M.npy", "labels": "/m/01d380,/m/07k1x", "caption": "A power tool vibrating and humming" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YRfGapDlAYoQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YRfGapDlAYoQ.npy", "labels": "/m/01w250", "caption": "Musical whistling with wind blowing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/YcN-oYKd-M4E.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YcN-oYKd-M4E.npy", "labels": "/m/07bgp,/m/0ch8v,/m/0jbk", "caption": "Sheep bleat near and far" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YlHh0SwUhP8U.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YlHh0SwUhP8U.npy", "labels": "/m/09ddx", "caption": "Birds chirping as a gun cocks followed by a gunshot and a man chuckling while metal clanks then another gunshot alongside ducks quacking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YHqnSyliKTKA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YHqnSyliKTKA.npy", "labels": "/m/03k3r,/m/07q5rw0,/m/07rv9rh,/m/09x0r,/m/0jbk", "caption": "A crowd of people talking followed by a horse neighing as a lawnmower engine runs in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YHUwXtfYRFwk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YHUwXtfYRFwk.npy", "labels": "/m/012f08,/m/01bjv,/m/07yv9,/m/0k4j", "caption": "A bus engine running as cars drive by and a car horn honks in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4YodC6RnplI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4YodC6RnplI.npy", "labels": "/m/01d3sd", "caption": "Snoring is ongoing, while an adult female laugh in the foreground and an adult male speaks briefly in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YFA11v4SmdBc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YFA11v4SmdBc.npy", "labels": "/m/01w250,/m/09x0r", "caption": "Man speaks followed by whistling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YZ1Cyj4N05lk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YZ1Cyj4N05lk.npy", "labels": "/m/01w250", "caption": "Musical whistling followed by a man speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YTgxst7Ft9js.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YTgxst7Ft9js.npy", "labels": "/m/02p01q,/m/07pdjhy", "caption": "Sanding and filing then a man speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/Yq4YFJA5pFXc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yq4YFJA5pFXc.npy", "labels": "/m/09ct_,/t/dd00129", "caption": "A helicopter engine whines as it starts" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YBn4lc01q9vE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBn4lc01q9vE.npy", "labels": "/m/0130jx,/m/02jz0l,/m/03dnzn,/m/0838f", "caption": "Water splashing followed by a woman speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/YA2mcp0N__7U.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YA2mcp0N__7U.npy", "labels": "/m/07qlf79,/m/09x0r", "caption": "A crowd of people talking as a person repeatedly coughs" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YR_g4RpU9mO0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YR_g4RpU9mO0.npy", "labels": "/m/019jd,/m/02rlv9,/m/07yv9", "caption": "A motorboat engine running idle then accelerating as water trickles followed by water spraying" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YHqnSyliKTKA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YHqnSyliKTKA.npy", "labels": "/m/03k3r,/m/07q5rw0,/m/07rv9rh,/m/09x0r,/m/0jbk", "caption": "'An engine with people speaking and a horse neighing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/YxUWSHYoslPQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YxUWSHYoslPQ.npy", "labels": "/m/04brg2,/m/09x0r", "caption": "A man is getting a glass and setting in down on a hard surface" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/Yy3-M1sonh3M.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yy3-M1sonh3M.npy", "labels": "/m/01jt3m", "caption": "Tapping noises followed by a toilet flushing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/YyfYNPWs7mWY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YyfYNPWs7mWY.npy", "labels": "/m/02dgv,/m/05zppz,/m/09x0r", "caption": "A man talking as a door closes shut followed by a door slowly creaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part0/Y-BUWGM7qeUM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y-BUWGM7qeUM.npy", "labels": "/m/06mb1", "caption": "Rain heavily pouring as wind blows into a microphone and streams of water trickle on a solid surface" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YCchRf2jq6fc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YCchRf2jq6fc.npy", "labels": "/m/02qldy,/m/02zsn,/m/09x0r", "caption": "An adult female speaks in a quiet environment" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/YzF3xXn6NTyU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YzF3xXn6NTyU.npy", "labels": "/m/0j6m2", "caption": "A woman speaking then coughing as a river stream flows followed by a series of plastic clacking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/YhDMHIDJdfDA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YhDMHIDJdfDA.npy", "labels": "/m/01d3sd,/t/dd00125", "caption": "A series of snores followed by subdued laughter and another snore" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YZYWCwfCkBp4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YZYWCwfCkBp4.npy", "labels": "/m/01b82r,/m/07pdjhy,/m/083vt", "caption": "Rustling and sanding on wood with distant music playing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part38/YuJzAf4PaExI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YuJzAf4PaExI.npy", "labels": "/m/07yv9,/m/09x0r,/m/0k5j", "caption": "Humming from a plane with wind whooshing by" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part0/Y-SkjbQVgJ0M.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y-SkjbQVgJ0M.npy", "labels": "/m/07yv9,/m/09x0r,/m/0k4j,/t/dd00134", "caption": "A man speaking followed by a car driving by" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/YilspW7JRjAg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YilspW7JRjAg.npy", "labels": "/m/012f08,/m/02mk9,/m/07yv9,/m/0k4j", "caption": "An engine revs repeatedly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4pv3w--cRrA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4pv3w--cRrA.npy", "labels": "/m/09t49", "caption": "Vibrations and clicking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/YdYZSKX7vuRI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YdYZSKX7vuRI.npy", "labels": "/m/01d3sd,/m/09x0r", "caption": "A person snoring loudly followed by a man speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YDzKjogSVOLM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YDzKjogSVOLM.npy", "labels": "/m/07qdb04,/m/09ddx,/m/09x0r,/m/0jbk", "caption": "Ducks quack and people speak in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/Yram-QPKSQYc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yram-QPKSQYc.npy", "labels": "/m/09ct_", "caption": "Helicopter blades spinning then fading away" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YHg6HxylRGDo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YHg6HxylRGDo.npy", "labels": "/m/012n7d,/m/03j1ly,/m/03kmc9", "caption": "The blaring siren of an ambulance and a vehicle revving up loudly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/YwbPmnxCLoRQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YwbPmnxCLoRQ.npy", "labels": "/m/0395lw", "caption": "Several bells ring" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YLP_DzNUkAKY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YLP_DzNUkAKY.npy", "labels": "/m/06wzb,/m/07rjwbb", "caption": "Clicking and humming with people speaking followed by a hydraulic hiss" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YCYUlLTKoa1Y.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YCYUlLTKoa1Y.npy", "labels": "/m/09x0r,/m/0llzx", "caption": "A woman speaks as a machine whirs and creaks in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YbJMMp6PLKqM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YbJMMp6PLKqM.npy", "labels": "/m/0463cq4,/m/09x0r,/m/0ytgt,/t/dd00125", "caption": "A baby cries and a small child speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/Ya_Rjlu50TfA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ya_Rjlu50TfA.npy", "labels": "/m/01d3sd,/m/07q0yl5,/m/09x0r", "caption": "A series of sharp, squeaky snoring noises" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/YggN4-K5AgoM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YggN4-K5AgoM.npy", "labels": "/m/01jt3m,/m/0838f", "caption": "A toilet flushes and water splashes around noisily" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/YxQDq3A4Zfbo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YxQDq3A4Zfbo.npy", "labels": "/m/019jd,/m/034srq,/m/03m9d0z,/m/05kq4,/m/0hsrw,/t/dd00092", "caption": "Water splashing and trickling as wind blows into a microphone followed by a man talking in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YARFFw0e_jig.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YARFFw0e_jig.npy", "labels": "/m/03q5_w", "caption": "Several distorted belches followed by non-distorted burps" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YU3CAjsm1sec.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YU3CAjsm1sec.npy", "labels": "/m/01yrx,/m/068hy,/m/07qrkrw,/m/0jbk", "caption": "Several cats meowing followed by a man singing in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y27HIamF8pKo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y27HIamF8pKo.npy", "labels": "/m/01g50p,/m/0284vy3,/m/06d_3,/m/07jdr,/m/07rwm0c", "caption": "Train is moving followed by a train horn" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part7/Y5eSRL3PRHzo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y5eSRL3PRHzo.npy", "labels": "/m/028ght,/m/03qtwd", "caption": "An audience clapping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/YjOYvIISk--4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YjOYvIISk--4.npy", "labels": "/m/0130jx,/m/02jz0l,/m/0838f", "caption": "A man speaking followed by a faucet turning on and off while pouring water twice proceeded by water draining down a pipe" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YCbe2B6ohBpw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YCbe2B6ohBpw.npy", "labels": "/m/015p6,/m/068hy,/m/09ddx,/m/0ch8v,/m/0dbvp,/m/0jbk", "caption": "Ducks are quacking, and water splashes softly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YL8dA-2Lu2hY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YL8dA-2Lu2hY.npy", "labels": "/m/01w250", "caption": "A continuation of intermittent whistling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YrPkCYq4Zjwk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YrPkCYq4Zjwk.npy", "labels": "/m/02fs_r", "caption": "A loud whoosh with computer female voice, a beep then male speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/Yeu5bq0A3XVQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yeu5bq0A3XVQ.npy", "labels": "/m/03q5_w,/m/09x0r", "caption": "A man gasping for air then talking followed by mumbling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part24/YV8A0VRGdgwM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YV8A0VRGdgwM.npy", "labels": "/m/03fwl,/m/07q0h5t,/m/0ch8v,/m/0jbk", "caption": "Some clicks followed by a person speaking and a goat bleating" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part7/Y5xC4hkAWiao.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y5xC4hkAWiao.npy", "labels": "/m/012f08,/m/02mk9,/m/07yv9", "caption": "A motor vehicle engine is idling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/YhJtOGmN_KVw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YhJtOGmN_KVw.npy", "labels": "/m/09x0r,/t/dd00112,/t/dd00125", "caption": "Plastic crinkling and paper sliding as a man talks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YQ87LBiwJjTE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YQ87LBiwJjTE.npy", "labels": "/m/07p9k1k,/m/0dxrf", "caption": "Music in the background as a woman speaks and food fries" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YYQGW5AwDOIo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YYQGW5AwDOIo.npy", "labels": "/m/07yv9,/m/0k4j,/m/0ltv", "caption": "Vehicles driving by then accelerating and revving as a crowd of people talk" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/YgQMTOKsCIyk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YgQMTOKsCIyk.npy", "labels": "/m/015p6,/m/07qwf61,/m/09ddx,/m/09x0r", "caption": "A group of birds chirping and ducks quacking followed by a man speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YFf8bCCJfVX4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YFf8bCCJfVX4.npy", "labels": "/m/032s66", "caption": "A small gun being shot repeatedly." }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/Yn74IYuCe_ms.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yn74IYuCe_ms.npy", "labels": "/m/09x0r,/m/0j6m2", "caption": "A stream burbles while a man speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/Yrp3CQsWxVgE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yrp3CQsWxVgE.npy", "labels": "/m/07yv9,/m/0912c9,/m/0k4j,/t/dd00128", "caption": "White noise followed by a musical horn honking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YmVjub3o_IxE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YmVjub3o_IxE.npy", "labels": "/m/02jz0l,/m/09x0r,/t/dd00125", "caption": "Light mechanical sounds while male speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YnuZEAuAl8hQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YnuZEAuAl8hQ.npy", "labels": "/m/015p6,/m/09ddx,/m/0ch8v", "caption": "A chicken clucking while crickets chirp in the background as gusts of wind blows" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3kBlVLkN0zo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3kBlVLkN0zo.npy", "labels": "/m/03fwl,/m/09x0r,/m/0ch8v,/m/0jbk", "caption": "Wind is blowing and birds are chirping, a metal bell clangs quietly once, and multiple animals bleat while two men speak in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/YxnVqvc7N7Po.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YxnVqvc7N7Po.npy", "labels": "/m/07cx4,/m/09x0r", "caption": "A female voice and then a male voice followed by the female voice again" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part19/YMSziND26UTA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YMSziND26UTA.npy", "labels": "/m/01h3n,/m/03vt0,/m/0h2mp", "caption": "Insects buzzing while wind is blowing on a microphone as music faintly plays followed by a rooster crowing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part27/Y_9mgOkzm-xg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y_9mgOkzm-xg.npy", "labels": "/m/09x0r,/m/0dxrf,/t/dd00125", "caption": "Food and oil sizzling as a man is speaking followed by wooden clanking then gravel scraping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/Ydkiwn2FdDVw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ydkiwn2FdDVw.npy", "labels": "/m/09ddx,/m/09x0r", "caption": "A woman speaks with distant quacks of a duck" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y2JutOgAnqWA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y2JutOgAnqWA.npy", "labels": "/m/01d380,/m/07k1x,/m/0_ksk", "caption": "A machine motor running alongside gears cranking followed by a power tool humming then drilling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YESjMIqrvRj4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YESjMIqrvRj4.npy", "labels": "/m/09t49,/t/dd00092", "caption": "Bird wings flapping then a bird chirping while rain falls followed by thunder" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y2KEfkDO6hlA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y2KEfkDO6hlA.npy", "labels": "/m/012f08,/m/07yv9,/m/0k4j,/t/dd00134", "caption": "Humming of an accelerating engine with wind passing and rustling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/Yt3VFlDiEKgY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yt3VFlDiEKgY.npy", "labels": "/m/03vt0,/m/09f96,/m/0h2mp", "caption": "A fly is buzzing around a man speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YFJkvAMLmejY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YFJkvAMLmejY.npy", "labels": "/m/0912c9,/m/09x0r,/t/dd00125", "caption": "People whisper and then a horn sounds and people laugh" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YFKaJsvcyHTk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YFKaJsvcyHTk.npy", "labels": "/t/dd00002", "caption": "A baby grunts and begins crying" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YAgh2EKINlSw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YAgh2EKINlSw.npy", "labels": "/m/06mb1,/t/dd00038", "caption": "Wind, rain and people talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part1/Y096oTVzc5Gs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y096oTVzc5Gs.npy", "labels": "/m/09x0r,/m/0bt9lr,/m/0jbk,/t/dd00136", "caption": "An adult female speaks and an animal growls playfully" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/YfmEft49sPfE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YfmEft49sPfE.npy", "labels": "/m/05zppz,/m/09t49,/m/09x0r", "caption": "A man is speaking as wind is blowing through the leaves" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YTwR8BA6buMI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YTwR8BA6buMI.npy", "labels": "/m/07qjznl", "caption": "A piano playing as a clock ticks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/YhV4bDCBDCy0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YhV4bDCBDCy0.npy", "labels": "/m/07r04,/m/07yv9,/m/09x0r", "caption": "Humming of a large engine with wind blowing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YBlbGXalLNVU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBlbGXalLNVU.npy", "labels": "/m/07pqc89", "caption": "Surf comes ashore as a man speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YnaPgJvWTIY4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YnaPgJvWTIY4.npy", "labels": "/m/04_sv,/m/07yv9,/t/dd00066,/t/dd00128", "caption": "A motorcycle engine running idle then revving its engine" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/Yx5AH2gW_8S4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yx5AH2gW_8S4.npy", "labels": "/m/0h0rv,/m/0jbk,/t/dd00125", "caption": "Pigeons cooing with some rattling and screeching" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YOt0bN_hz2ec.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YOt0bN_hz2ec.npy", "labels": "/m/0195fx,/m/01g50p,/m/0284vy3,/m/06d_3,/m/07jdr,/m/07rwm0c", "caption": "A train horn honks with a train racing by" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YbmEF-c-M174.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YbmEF-c-M174.npy", "labels": "/m/015p6,/m/09ddx,/m/09x0r", "caption": "A duck quacks as footsteps thump on wood while a bird chirps followed by a man talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part19/YNJEPbGVBJIQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YNJEPbGVBJIQ.npy", "labels": "/m/012f08,/m/04_sv,/m/07yv9,/m/09x0r,/m/0btp2,/t/dd00128", "caption": "A man speaks followed by a vehicle revving" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part27/Y_z6pymOet7g.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y_z6pymOet7g.npy", "labels": "/m/01jt3m,/m/09x0r", "caption": "A man speaks followed by a toilet flushing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YB4SZwi9Ce3o.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YB4SZwi9Ce3o.npy", "labels": "/m/07q2z82,/m/07yv9,/m/09x0r,/m/0k4j", "caption": "A man talks as a vehicle is accelerating" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YKvrcRMfFzOE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YKvrcRMfFzOE.npy", "labels": "/m/07yv9,/m/09ct_,/m/0k5j", "caption": "A helicopter is in flight with loud blades moving fast" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part0/Y-mhFGevxLUg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y-mhFGevxLUg.npy", "labels": "/m/07rqsjt,/m/09x0r", "caption": "A man speaks with low speech in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part38/Yu84FiZ_omhA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yu84FiZ_omhA.npy", "labels": "/m/015p6,/m/07pggtn,/m/0jbk", "caption": "Loud high humming and croaking sound" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/YhFCmq9pCBbM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YhFCmq9pCBbM.npy", "labels": "/m/09x0r,/t/dd00112", "caption": "A young girl talking as plastic crinkles and plastic thumping against a glass surface" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/Yyrxa6_P2I80.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yyrxa6_P2I80.npy", "labels": "/m/015p6,/m/0h0rv,/t/dd00129", "caption": "A group of birds chirp and pigeons coo" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YsJrFyjfrL-g.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YsJrFyjfrL-g.npy", "labels": "/m/0llzx", "caption": "A sewing machine operating during several metal clacks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/YwFiCblfZ-vg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YwFiCblfZ-vg.npy", "labels": "/m/07pqc89,/m/09x0r", "caption": "A man speaking softly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YmW1EpJYcy_E.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YmW1EpJYcy_E.npy", "labels": "/m/04_sv,/m/07yv9,/t/dd00128", "caption": "A motorcycle revving by quickly twice" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/Yir1XTdyt4IY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yir1XTdyt4IY.npy", "labels": "/m/014zdl,/m/07qsvvw,/m/09x0r", "caption": "Air hissing followed by a popping explosion then warning signals and a man laughing and talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/Ypgq2KPX5_SA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ypgq2KPX5_SA.npy", "labels": "/t/dd00112", "caption": "Crumpling occurs followed by a thud and then crinkling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part15/YGIOApFAWDOc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YGIOApFAWDOc.npy", "labels": "/m/015p6,/m/020bb7,/m/07pggtn", "caption": "Birds chirping and tweeting" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9E8BmPZ9mWc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9E8BmPZ9mWc.npy", "labels": "/m/07r04,/m/07yv9,/m/09x0r", "caption": "A truck engine running as a group of men are talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YAgaiowyYt88.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YAgaiowyYt88.npy", "labels": "/m/02dgv", "caption": "A loud bang followed by silence" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part7/Y6CDl4CqOgMg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y6CDl4CqOgMg.npy", "labels": "/m/068hy,/m/0bt9lr,/m/0jbk,/t/dd00136", "caption": "Dog panting followed by footsteps" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part0/Y-DmjkgWa-rw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y-DmjkgWa-rw.npy", "labels": "/m/0395lw", "caption": "A bell ringing repeatedly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YCbe2B6ohBpw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YCbe2B6ohBpw.npy", "labels": "/m/015p6,/m/068hy,/m/09ddx,/m/0ch8v,/m/0dbvp,/m/0jbk", "caption": "Continuous quacking and rustling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/Yeu5bq0A3XVQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yeu5bq0A3XVQ.npy", "labels": "/m/03q5_w,/m/09x0r", "caption": "A male voice talks after doing some burps" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YAUmY0YRAFQE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YAUmY0YRAFQE.npy", "labels": "/m/04qvtq,/m/07yv9,/m/0k4j,/t/dd00134", "caption": "Ringing of a siren of a passing vehicle" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YR8bHTHnF8j4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YR8bHTHnF8j4.npy", "labels": "/m/07yv9,/m/09ct_,/m/0k5j", "caption": "A helicopter engine running idle" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YQOmV7O9mFwg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YQOmV7O9mFwg.npy", "labels": "/m/01bjv,/m/07yv9,/m/09x0r", "caption": "Laughing followed by a child talking and more laughing with many children talking in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YmVjub3o_IxE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YmVjub3o_IxE.npy", "labels": "/m/02jz0l,/m/09x0r,/t/dd00125", "caption": "Constant squeaking occurs while a man speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YCchRf2jq6fc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YCchRf2jq6fc.npy", "labels": "/m/02qldy,/m/02zsn,/m/09x0r", "caption": "A young woman is talking." }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YBDpU2Qh77NE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBDpU2Qh77NE.npy", "labels": "/m/015p6,/m/020bb7,/m/07pggtn", "caption": "A bird making vocalizations from a distance followed by several people whispering nearby" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3RultJjvTWI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3RultJjvTWI.npy", "labels": "/m/019jd,/m/034srq,/m/03m9d0z,/t/dd00092", "caption": "'A group of young adults laughing followed by a man shouting as a stream of water splashes and flows while wind blows" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YK8-b0VtNOqA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YK8-b0VtNOqA.npy", "labels": "/m/03k3r,/m/09x0r,/m/0jbk", "caption": "Horses snorting and neighing as a man talks followed by a door creaking shut before woman talks in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/YxbLW9Wt1Jsg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YxbLW9Wt1Jsg.npy", "labels": "/m/0llzx", "caption": "A sewing machine is in use as well as knocking and bleeping noises" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YPTyFYxXdut4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YPTyFYxXdut4.npy", "labels": "/m/07pqc89,/m/0838f,/m/09x0r", "caption": "A woman speaks as water splashes" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part27/Y_BSmz3SEW1w.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y_BSmz3SEW1w.npy", "labels": "/m/015p6,/m/0h0rv,/t/dd00125,/t/dd00129", "caption": "Birds cooing and rustling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YCYUlLTKoa1Y.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YCYUlLTKoa1Y.npy", "labels": "/m/09x0r,/m/0llzx", "caption": "Humming followed by a woman speaking with slow ticks of a sewing machine" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/Yx5AH2gW_8S4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yx5AH2gW_8S4.npy", "labels": "/m/0h0rv,/m/0jbk,/t/dd00125", "caption": "Pigeons cooing as wood clanks and an animal hisses" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YAtkD-3GjXMw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YAtkD-3GjXMw.npy", "labels": "/m/032s66,/m/04zjc", "caption": "Music plays as a man is singing followed by muffled rapid gunshots firing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9XqkKuTqEOM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9XqkKuTqEOM.npy", "labels": "/m/02dgv", "caption": "Some rustling and scratching with a short click" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y6TO9PEGpZcQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y6TO9PEGpZcQ.npy", "labels": "/m/012n7d,/m/012ndj,/m/03j1ly,/m/03kmc9", "caption": "An emergency siren wailing followed by a large truck engine running idle" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YDAN1t9ukkg0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YDAN1t9ukkg0.npy", "labels": "/m/01m2v,/m/0316dw", "caption": "A person types on a keyboard" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/YeJCaRgf1M20.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YeJCaRgf1M20.npy", "labels": "/m/07qjznl", "caption": "A bell chiming as birds chirp followed by plastic clanking and shuffling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YWUpeplQr3A4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YWUpeplQr3A4.npy", "labels": "/m/01d380", "caption": "A man shrilling followed by a power tool drilling and a man screaming as liquid splatters" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YXZTt1xdK8uQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YXZTt1xdK8uQ.npy", "labels": "/m/07swgks", "caption": "A vehicle engine running as water is splashing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part24/YUXGzbBGbqAA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YUXGzbBGbqAA.npy", "labels": "/m/07ryjzk,/m/0dxrf", "caption": "Footsteps shuffling and fabric slapping a hard surface" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YlTJLvSvjUZk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YlTJLvSvjUZk.npy", "labels": "/m/01w250", "caption": "A girl talking and shouting with whistling in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YmWqH2xwjkYA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YmWqH2xwjkYA.npy", "labels": "/m/01j3sz,/m/09x0r", "caption": "A baby laughs and a woman speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/Yf2fSxfvmkZQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yf2fSxfvmkZQ.npy", "labels": "/m/01d380,/m/09x0r", "caption": "Brief speech followed by rustling and then vibrating" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/YpWQeV08kYR0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YpWQeV08kYR0.npy", "labels": "/m/012n7d,/m/03j1ly,/m/03kmc9,/m/07yv9,/t/dd00128", "caption": "Emergency sirens going off as a vehicle drives by" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/YynHdcJ9Oqaw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YynHdcJ9Oqaw.npy", "labels": "/m/07rqsjt", "caption": "A series of synthesized laser effects" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YlVr-PxhZo8s.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YlVr-PxhZo8s.npy", "labels": "/m/07pb8fc,/m/07yv9,/t/dd00126", "caption": "Camera muffling and wind blowing into a microphone as a vehicle engine runs while idle" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/Yorgwzt45ojE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yorgwzt45ojE.npy", "labels": "/m/015p6,/m/09x0r,/m/0h0rv,/t/dd00126", "caption": "A man speaking and wings flapping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YJHhEjsAkZoc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YJHhEjsAkZoc.npy", "labels": "/m/01g50p,/m/0284vy3,/m/06d_3,/m/07jdr,/m/07rwm0c", "caption": "A train horn blows and fades, then metal clacking occurs" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y2ItTq2JShdU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y2ItTq2JShdU.npy", "labels": "/m/07rqsjt", "caption": "A train engine running" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/Yh5_1pnkl_SY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yh5_1pnkl_SY.npy", "labels": "/m/02jz0l,/m/0838f", "caption": "Water pouring continuously" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YZ_smJ66Tb3c.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YZ_smJ66Tb3c.npy", "labels": "/m/015p6,/m/020bb7,/m/07r_25d,/m/0h0rv", "caption": "A man talking as pigeons are cooing and birds are chirping with bird wings flapping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y1OyEgzXCkYE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1OyEgzXCkYE.npy", "labels": "/m/02qldy,/m/05zppz,/m/09x0r", "caption": "A man is speaking on a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YkF1KWybdRpM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YkF1KWybdRpM.npy", "labels": "/m/014yck,/m/07yv9,/m/0cmf2,/m/0k5j", "caption": "A loud airplane engine passes by and starts to diminish in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4s2rRnu2PZo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4s2rRnu2PZo.npy", "labels": "/m/07rqsjt", "caption": "Music and gunfire with male speech" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/Ybgbnu5YKTDg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ybgbnu5YKTDg.npy", "labels": "/m/032s66", "caption": "A man is speaking followed by gunfire" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part1/Y0_K6OKtoBBU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y0_K6OKtoBBU.npy", "labels": "/m/01yrx,/m/068hy,/m/07qrkrw,/m/0jbk", "caption": "A cat is meowing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9dLLsZVRSZI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9dLLsZVRSZI.npy", "labels": "/m/07r04,/m/07yv9,/t/dd00129", "caption": "Engine idling continuously followed by honking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9HVgYs8OOLc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9HVgYs8OOLc.npy", "labels": "/m/015p6,/m/09x0r,/m/0h0rv,/t/dd00125", "caption": "A man speaking followed by pigeons cooing and flapping wings then a kid speaking and someone claps loudly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y4CAMv5nlr-0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4CAMv5nlr-0.npy", "labels": "/m/02qldy,/m/05zppz,/m/09x0r", "caption": "In an echoing space, an older man speaks loudly, followed by enthusiastic applause" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YCh0LMmhBUg4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YCh0LMmhBUg4.npy", "labels": "/m/03m9d0z,/m/06q74,/m/07yv9,/m/09x0r,/t/dd00129", "caption": "A man speaks with some distant hum and a child speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YItS07xtdi4s.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YItS07xtdi4s.npy", "labels": "/m/07qsvvw,/m/09x0r", "caption": "Rockets igniting followed by footsteps on concrete as multiple vehicle engines run while idle" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/Yos_2U4xqTqw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yos_2U4xqTqw.npy", "labels": "/m/014zdl,/m/07qsvvw,/m/07s2xch", "caption": "Loud footsteps followed by a scream and explosions" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part19/YMPLZUg89y5U.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YMPLZUg89y5U.npy", "labels": "/m/07r04,/m/07yv9,/m/09x0r", "caption": "Men speak with humming of an engine and some rustling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3hzy-FL24no.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3hzy-FL24no.npy", "labels": "/m/0j6m2", "caption": "A stream of water flowing and trickling as a small motor hum in the background followed by camera muffling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part38/YuJzAf4PaExI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YuJzAf4PaExI.npy", "labels": "/m/07yv9,/m/09x0r,/m/0k5j", "caption": "An engine idling consistently" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/Yc6YJgZ3qzOw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yc6YJgZ3qzOw.npy", "labels": "/m/09ct_", "caption": "A toy helicopter flying followed by wind blowing into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9PN4gyxpH2M.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9PN4gyxpH2M.npy", "labels": "/m/09x0r,/t/dd00112", "caption": "A man and a woman talking as paper crinkles" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part24/YV8A0VRGdgwM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YV8A0VRGdgwM.npy", "labels": "/m/03fwl,/m/07q0h5t,/m/0ch8v,/m/0jbk", "caption": "Rustling followed by baaing and then more rustling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YnD1K1Zo0qrM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YnD1K1Zo0qrM.npy", "labels": "/m/032s66,/m/04zjc", "caption": "Several rapid gunshots with a distant aircraft passing by with a booming engine" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y11SEBDuoqSk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y11SEBDuoqSk.npy", "labels": "/m/07yv9,/m/0cmf2,/m/0k5j", "caption": "An engine chugging loudly together with gunfire" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YBLMWD6fxhpo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBLMWD6fxhpo.npy", "labels": "/t/dd00018", "caption": "A grunt from a person followed by footsteps and oinks from a pig with a single squeal" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part4/Y2UNuMbxz9ds.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y2UNuMbxz9ds.npy", "labels": "/m/012f08,/m/07yv9,/m/0k4j,/t/dd00134", "caption": "A vehicle engine is revving up" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YrvtA7c1I4xo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YrvtA7c1I4xo.npy", "labels": "/m/07rqsjt", "caption": "A whooshing effect followed by a man talking as basketballs bounce and shoes squeak on a hard surface while a crowd of people yell in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4pf-PIymDhU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4pf-PIymDhU.npy", "labels": "/m/01d380,/m/07k1x,/m/0_ksk", "caption": "A jackhammer drilling and vibrating continuously" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/YggN4-K5AgoM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YggN4-K5AgoM.npy", "labels": "/m/01jt3m,/m/0838f", "caption": "A toilet flushing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YDrCm-HpX67k.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YDrCm-HpX67k.npy", "labels": "/m/083vt", "caption": "Opening and closing followed by tapping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/Yf8WPf5F22xI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yf8WPf5F22xI.npy", "labels": "/m/01hsr_", "caption": "A person sneezes and then speaks with clock ticking in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part27/Y_C2HinL8VlM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y_C2HinL8VlM.npy", "labels": "/m/03j1ly,/m/03kmc9,/m/04qvtq", "caption": "Low rumbling sounds followed by a police siren going off" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YJHhEjsAkZoc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YJHhEjsAkZoc.npy", "labels": "/m/01g50p,/m/0284vy3,/m/06d_3,/m/07jdr,/m/07rwm0c", "caption": "A train honks horn and passes by" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YQ87LBiwJjTE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YQ87LBiwJjTE.npy", "labels": "/m/07p9k1k,/m/0dxrf", "caption": "An adult female speaks, sizzling is ongoing, water runs and metal clanks, and music plays in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3iLGu2Omgrw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3iLGu2Omgrw.npy", "labels": "/m/02qldy,/m/05zppz,/m/09x0r", "caption": "A man speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/YxpZna_FwDhI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YxpZna_FwDhI.npy", "labels": "/m/09x0r,/m/0llzx", "caption": "Brief clanking followed by a woman speaking and sewing machine working" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YYk274Wr5iIE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YYk274Wr5iIE.npy", "labels": "/m/06mb1", "caption": "Water splashing as rain falls and trickles on a wet surface followed by thunder while wind blows into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part19/YMj_BO-iK1G4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YMj_BO-iK1G4.npy", "labels": "/m/0llzx", "caption": "A sewing machines a sewing then suddenly stopping with some squeezing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y52IxrdTxGs4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y52IxrdTxGs4.npy", "labels": "/m/07qsvvw,/m/09x0r", "caption": "An explosion and heart beating as instrumental music plays followed by a man talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/YzFzPOsOKog4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YzFzPOsOKog4.npy", "labels": "/m/01h3n,/m/03vt0,/m/0h2mp", "caption": "Rustling, bees buzzing and then birds chirping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/Yy-RSojxgkDo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yy-RSojxgkDo.npy", "labels": "/m/015p6,/m/068hy,/m/07pggtn", "caption": "A male speech and a bird chirping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YkXjzsroVTtw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YkXjzsroVTtw.npy", "labels": "/m/020bb7,/m/07pggtn,/m/09x0r", "caption": "Birds are chirping in the background, while an adult male speaks and footfalls occur" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part19/YN_s9F4CI_98.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YN_s9F4CI_98.npy", "labels": "/m/015p6,/m/020bb7,/m/07r_25d,/m/0h0rv", "caption": "Pigeons cooing followed by bird wings flapping as crickets chirp in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y7JWHbs3gu1w.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y7JWHbs3gu1w.npy", "labels": "/m/01g50p,/m/0284vy3,/m/06d_3,/m/07jdr,/m/07rwm0c", "caption": "A hum of a train engine passing with a blowing horn" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YDrCm-HpX67k.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YDrCm-HpX67k.npy", "labels": "/m/083vt", "caption": "Fabric rustling followed by wood clanking then knocking on a hollow wooden surface as dirt and gravel pour out while crows caw in the background and wind blows into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/Ybpv_LneHmfU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ybpv_LneHmfU.npy", "labels": "/m/014yck,/m/07yv9,/m/0cmf2,/m/0k5j,/t/dd00129", "caption": "An aircraft engine sharply running" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/YwBs02amFGXs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YwBs02amFGXs.npy", "labels": "/m/015p6,/m/0h0rv,/t/dd00125,/t/dd00129", "caption": "Pigeons coo and flap their wings and a distant rooster crows" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YBlbGXalLNVU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBlbGXalLNVU.npy", "labels": "/m/07pqc89", "caption": "Water splashes and wind blows as men speak" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y7bO0AJI-ihs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y7bO0AJI-ihs.npy", "labels": "/m/03k3r,/m/07rv9rh,/m/0jbk", "caption": "Clip-clop of horse with an engine idling in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YlfAFQ0-wDJU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YlfAFQ0-wDJU.npy", "labels": "/m/034srq,/m/03m9d0z", "caption": "Wind and surf with water splashing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/Yj0KvrVE_Oww.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yj0KvrVE_Oww.npy", "labels": "/m/0912c9,/m/09x0r,/t/dd00125", "caption": "Men talking over a background humming noise then an alarm blares" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/YzEM94PH29VQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YzEM94PH29VQ.npy", "labels": "/m/09x0r,/t/dd00002", "caption": "A baby crying and various speeches" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YCbe2B6ohBpw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YCbe2B6ohBpw.npy", "labels": "/m/015p6,/m/068hy,/m/09ddx,/m/0ch8v,/m/0dbvp,/m/0jbk", "caption": "Ducks quaking and water lightly splashing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4bUL_ttiOdw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4bUL_ttiOdw.npy", "labels": "/t/dd00002", "caption": "A baby crying repeatedly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9zstu_IfAm4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9zstu_IfAm4.npy", "labels": "/m/07r04,/m/07yv9,/m/09x0r", "caption": "A truck driving by as a truck horn honks while a crowd of people talk in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/YhV4bDCBDCy0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YhV4bDCBDCy0.npy", "labels": "/m/07r04,/m/07yv9,/m/09x0r", "caption": "An engine running and revving lightly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/YhiJB_95IWiE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YhiJB_95IWiE.npy", "labels": "/m/02p01q,/m/07pdjhy", "caption": "A male speaking and scraping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/YpHYkWkZ4guE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YpHYkWkZ4guE.npy", "labels": "/m/06wzb,/m/07rjwbb", "caption": "Hissing is ongoing, while metal clattering and clanking occur" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YRdC8cviN6Bs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YRdC8cviN6Bs.npy", "labels": "/m/06mb1,/t/dd00038", "caption": "Rain falling followed by fabric rustling and footsteps shuffling then a vehicle door opening and closing as plastic crinkles" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YJC2ZrXzCX4Y.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YJC2ZrXzCX4Y.npy", "labels": "/m/01d3sd,/m/09x0r", "caption": "A man snoring with children speaking in the distance and a woman speaking nearby" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YqPYwp1K4sZE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YqPYwp1K4sZE.npy", "labels": "/m/09x0r,/t/dd00112,/t/dd00125", "caption": "A woman speaking with crumpling and crinkling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YLF6x7B0Ppvo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YLF6x7B0Ppvo.npy", "labels": "/m/07yv9,/m/0k4j,/m/0ltv", "caption": "A mid-size motor vehicle engine is running fast and accelerating, gears change, and acceleration continues" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y7WkB6pflr6o.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y7WkB6pflr6o.npy", "labels": "/m/02qldy,/m/02zsn,/m/09x0r", "caption": "A woman speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YQoEal_hKz4Q.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YQoEal_hKz4Q.npy", "labels": "/m/032s66,/m/04zjc", "caption": "Rapid gunfire with speaking over a radio" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/Yz1ax0QPpd14.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yz1ax0QPpd14.npy", "labels": "/m/015p6,/m/09ddx", "caption": "Several birds are singing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part24/YUjje3lSabsg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YUjje3lSabsg.npy", "labels": "/m/01d3sd", "caption": "A person is snoring" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/YcN-oYKd-M4E.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YcN-oYKd-M4E.npy", "labels": "/m/07bgp,/m/0ch8v,/m/0jbk", "caption": "Sheep bleat and distant birds chirp" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YI_8KqxP5xOA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YI_8KqxP5xOA.npy", "labels": "/m/07qlf79", "caption": "A sprayer is used to spray" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part7/Y5K1mISHwggI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y5K1mISHwggI.npy", "labels": "/m/02mk9,/m/07yv9,/m/09x0r", "caption": "Men are speaking with an engine sound in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YIFRmbxWK8u0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YIFRmbxWK8u0.npy", "labels": "/m/07qjznl", "caption": "A clock ticking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part27/Y_xylo5_IiaM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y_xylo5_IiaM.npy", "labels": "/m/09x0r,/m/0ytgt,/t/dd00125", "caption": "A woman speaks then a small child speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/Yz4MeV9IGVo0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yz4MeV9IGVo0.npy", "labels": "/m/01bjv,/m/07yv9,/m/09x0r", "caption": "A large truck engine running idle as a man speaks over a radio followed by a large truck accelerating while wind blows into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y473wBEwC35M.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y473wBEwC35M.npy", "labels": "/m/02qldy,/m/05zppz,/m/09x0r", "caption": "A man speaking as a vehicle horn honks and a man speaks in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y7bO0AJI-ihs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y7bO0AJI-ihs.npy", "labels": "/m/03k3r,/m/07rv9rh,/m/0jbk", "caption": "Clip clops of horses on a hard surface" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YJdFmMw0zyKA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YJdFmMw0zyKA.npy", "labels": "/m/01j3sz,/m/09x0r", "caption": "A girl speaks followed by barking then a splash and laughter" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YDjKGzOe_COc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YDjKGzOe_COc.npy", "labels": "/m/02qldy,/m/02zsn,/m/09x0r", "caption": "A girl giving a speech" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YrPkCYq4Zjwk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YrPkCYq4Zjwk.npy", "labels": "/m/02fs_r", "caption": "A loud whoosh followed by a woman speaking then digital beeps and men speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YD96OO7nYYsg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YD96OO7nYYsg.npy", "labels": "/m/07q2z82,/m/07yv9,/m/0k4j", "caption": "A muffled vehicle engine running as police sirens wail in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YSNIaYhri76w.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YSNIaYhri76w.npy", "labels": "/m/05tny_,/m/07rc7d9,/m/09x0r,/m/0bt9lr,/m/0ghcn6,/m/0jbk,/t/dd00129", "caption": "A dog barking as footsteps walking on foliage and a man talking while a pig squeals" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YkVYNXZd0MMY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YkVYNXZd0MMY.npy", "labels": "/m/01jwx6,/m/02mk9,/m/07yv9,/m/0k4j", "caption": "An engine is vibrating" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part27/Y_w2pA1VeB40.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y_w2pA1VeB40.npy", "labels": "/m/01j3sz", "caption": "Several people laughing followed by a popping farting sound" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/YpO8kbg9IJnc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YpO8kbg9IJnc.npy", "labels": "/m/0130jx,/m/02jz0l,/m/0838f", "caption": "A man talking followed by a faucet running" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/YhqPBcvex1VU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YhqPBcvex1VU.npy", "labels": "/m/09x0r,/t/dd00002", "caption": "An infant crying as a woman mumbles" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part24/YUmNrhFKpWIY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YUmNrhFKpWIY.npy", "labels": "/m/07q2z82,/m/07yv9,/m/0k4j", "caption": "A car engine revs and then shuts off" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part27/Y_duNX6Vyd6g.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y_duNX6Vyd6g.npy", "labels": "/m/019jd,/m/02rlv9,/m/07yv9", "caption": "A speedboat races across water with room sounds" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YWCYfCfW9NA0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YWCYfCfW9NA0.npy", "labels": "/m/07yv9,/m/09ct_,/t/dd00129", "caption": "Whirring and whooshing of a low helicopter" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YEbpOXac13yo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YEbpOXac13yo.npy", "labels": "/m/01bjv,/m/07yv9,/m/09x0r", "caption": "A bus accelerates followed by people communicating" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YAj_VMUSNjNM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YAj_VMUSNjNM.npy", "labels": "/m/02mk9,/m/07q2z82,/m/07yv9,/m/0k4j", "caption": "A vehicle engine revving and accelerating" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4Ujigme2IxY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4Ujigme2IxY.npy", "labels": "/m/01jwx6", "caption": "An engine humming and brakes squealing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part7/Y5K1mISHwggI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y5K1mISHwggI.npy", "labels": "/m/02mk9,/m/07yv9,/m/09x0r", "caption": "A person speaks, traffic passes by" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y1a2XWJ8NA_Q.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1a2XWJ8NA_Q.npy", "labels": "/m/019jd,/m/02rlv9,/m/07yv9,/m/09x0r", "caption": "A boat engine sounds, wind blows by, people speak" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y1_z6NcidGzM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1_z6NcidGzM.npy", "labels": "/m/07swgks,/m/09x0r,/m/0j6m2", "caption": "Two quick whistle sounds with water splashing and mixed with kids playing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/YcPiSd5nJLrI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YcPiSd5nJLrI.npy", "labels": "/m/014zdl,/m/07pxg6y,/m/07qsvvw", "caption": "A group of people screaming followed by missiles launching and loud popping explosions then a slowed down explosion" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part19/YNJEPbGVBJIQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YNJEPbGVBJIQ.npy", "labels": "/m/012f08,/m/04_sv,/m/07yv9,/m/09x0r,/m/0btp2,/t/dd00128", "caption": "Humming engines with distant horns and revving motorcycles with a man speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part38/YvaujJ7msKfc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YvaujJ7msKfc.npy", "labels": "/m/012n7d,/m/03j1ly,/m/03kmc9", "caption": "Humming with distant traffic passing and a distant siren ringing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y1Og2TJ3bXW0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1Og2TJ3bXW0.npy", "labels": "/m/07yv9,/m/0cmf2,/m/0k5j,/t/dd00128", "caption": "An aircraft engine humming followed by plastic clanking then an aircraft engine slowing down" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4pf-PIymDhU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4pf-PIymDhU.npy", "labels": "/m/01d380,/m/07k1x,/m/0_ksk", "caption": "Vibrations and clanking from a drill" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YKOBkbROPv4c.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YKOBkbROPv4c.npy", "labels": "/m/07rknqz,/m/07yv9,/m/0h9mv,/m/0ltv", "caption": "Humming of an engine with squealing tires" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/Yi6MQCm58zlY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yi6MQCm58zlY.npy", "labels": "/m/020bb7,/m/068hy,/m/0jbk", "caption": "A critter squealing as a man is talking and leaves are rustling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/YpTJKJxaheI8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YpTJKJxaheI8.npy", "labels": "/m/07qjznl,/m/07qjznt", "caption": "A clock ticking for several seconds followed by faint coughing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y59VP93Tzjmg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y59VP93Tzjmg.npy", "labels": "/m/01g50p,/m/0284vy3,/m/06d_3,/m/07jdr", "caption": "A train horn repeatedly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part0/Y-mhFGevxLUg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y-mhFGevxLUg.npy", "labels": "/m/07rqsjt,/m/09x0r", "caption": "A man speaking with murmuring in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part9/Y8ZH_PoK0clI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y8ZH_PoK0clI.npy", "labels": "/m/02dgv,/m/09x0r", "caption": "Footsteps then a woman speaks followed by a door clanging" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YlrKGCtSsAkA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YlrKGCtSsAkA.npy", "labels": "/m/09ct_", "caption": "High frequency humming followed by wind blowing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y1Uh74_rZ72k.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1Uh74_rZ72k.npy", "labels": "/m/07swgks", "caption": "Wind blowing with passing distant traffic and some rumbling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YqeSl7YZAfs4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YqeSl7YZAfs4.npy", "labels": "/m/0130jx,/m/02jz0l,/m/0838f", "caption": "A man is talking as tap water is running" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part9/Y8ipe6b1LwHQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y8ipe6b1LwHQ.npy", "labels": "/m/023pjk,/m/04brg2", "caption": "Dishes and silverware rattle and click from movement" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/Yr2KhpX_QgXA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yr2KhpX_QgXA.npy", "labels": "/m/02mk9,/m/02x984l,/m/09x0r", "caption": "An motor blowing air faintly before becoming more audible as a man talks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/Ylh801oHGtD4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ylh801oHGtD4.npy", "labels": "/m/01d380,/m/09x0r", "caption": "A man talking as an electronic device hums followed by a door closing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/YyVjivgsU2aA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YyVjivgsU2aA.npy", "labels": "/m/012f08,/m/07rknqz,/m/07yv9,/m/09x0r,/m/0h9mv,/m/0k4j,/m/0ltv", "caption": "A vehicle engine running idle as a man is talking then accelerating with tires skidding and squeaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/YgbtcDoh0q3c.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YgbtcDoh0q3c.npy", "labels": "/m/01j3sz,/m/07s04w4,/m/09x0r", "caption": "Metal clacking followed by a man talking then a metal bang as footsteps shuffle on dirt and a group of men laugh" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YnaPgJvWTIY4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YnaPgJvWTIY4.npy", "labels": "/m/04_sv,/m/07yv9,/t/dd00066,/t/dd00128", "caption": "A motorbike running idle then revving" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part15/YGOD8Bt5LfDE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YGOD8Bt5LfDE.npy", "labels": "/m/07jdr,/m/09x0r,/m/0ytgt", "caption": "A toy train running as a young boy talks followed by plastic clanking then a child laughing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YEY4p0_NJVQs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YEY4p0_NJVQs.npy", "labels": "/m/02qldy,/m/02zsn,/m/09x0r", "caption": "An adult female is speaking in a quiet environment" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YmSF_FqBtRPs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YmSF_FqBtRPs.npy", "labels": "/m/01hnzm,/m/07cx4", "caption": "A ring tone begins with a high pitched bell followed by a traditional telephone ring" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YtmLAXm1WlnE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YtmLAXm1WlnE.npy", "labels": "/m/01h3n,/m/03vt0,/m/0h2mp", "caption": "Buzzing and female speech" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YlYhwCRX2wNc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YlYhwCRX2wNc.npy", "labels": "/m/04brg2,/m/09x0r", "caption": "Water is running and splashing while an adult female speaks and dishes clink" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YNtQiduPRiRg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YNtQiduPRiRg.npy", "labels": "/m/01j3sz,/m/09x0r", "caption": "A buzzing and laughter" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YBz9Y5nZK3eo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBz9Y5nZK3eo.npy", "labels": "/m/01m2v,/m/0316dw", "caption": "Rapid typing on a keyboard" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YtB8TiiXwKmA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YtB8TiiXwKmA.npy", "labels": "/m/01d380,/m/07k1x,/m/0_ksk", "caption": "A small drill is operating and whirring, with grinding and clattering" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YOMGHnJV0l2U.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YOMGHnJV0l2U.npy", "labels": "/m/02p01q,/m/07pdjhy,/m/083vt", "caption": "Scraping and banging" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YkXjzsroVTtw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YkXjzsroVTtw.npy", "labels": "/m/020bb7,/m/07pggtn,/m/09x0r", "caption": "Birds chirp and sing in the background, while an adult male speaks and crunching footfalls occur" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YmW1EpJYcy_E.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YmW1EpJYcy_E.npy", "labels": "/m/04_sv,/m/07yv9,/t/dd00128", "caption": "A motorcycle running close and then far away" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/YxqtrbqDlz28.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YxqtrbqDlz28.npy", "labels": "/m/01hsr_", "caption": "A sneeze and sniffle" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YZ7yDwpdGelM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YZ7yDwpdGelM.npy", "labels": "/m/07pqc89,/m/09x0r", "caption": "A man speaks and water trickles" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y466ucPGoNSQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y466ucPGoNSQ.npy", "labels": "/m/01yrx,/m/068hy,/m/07qrkrw,/m/09x0r,/m/0jbk", "caption": "A cat meowing repeatedly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y0ury8KHQdL4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y0ury8KHQdL4.npy", "labels": "/m/01m2v,/m/0316dw,/m/09x0r", "caption": "An adult male is speaking and typing on a keyboard" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YBXxlqaDvdaA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBXxlqaDvdaA.npy", "labels": "/m/05kq4,/m/07yv9,/m/09x0r,/m/0hsrw,/m/0j6m2", "caption": "A man talking as water splashes and wind heavily blowing into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YHdxfbpnd2-8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YHdxfbpnd2-8.npy", "labels": "/m/01w250", "caption": "A man talking then whistling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YL_CNz9Vrtkw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YL_CNz9Vrtkw.npy", "labels": "/m/028ght,/m/09x0r", "caption": "Male speech and then applause" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4Ujigme2IxY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4Ujigme2IxY.npy", "labels": "/m/01jwx6", "caption": "An emergency siren with horn honking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YljrL7Cb-jr8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YljrL7Cb-jr8.npy", "labels": "/m/07qlf79", "caption": "Continuous spray" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3qTL7QRk-tg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3qTL7QRk-tg.npy", "labels": "/m/07swgks,/m/0j6m2", "caption": "Water running, men singing, and clanging of metal" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part38/Yvsy1IpYmrSY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yvsy1IpYmrSY.npy", "labels": "/m/0h9mv", "caption": "Race car engines revving through gears" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YEQVWhHmT_cE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YEQVWhHmT_cE.npy", "labels": "/m/02qldy,/m/05zppz,/m/09x0r", "caption": "A male speaking and the glass shattering followed by a laughter" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/YwNiYSYJXssA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YwNiYSYJXssA.npy", "labels": "/m/03k3r,/m/09x0r,/m/0jbk", "caption": "People are speaking followed by crowd noise" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y1N_DtRpdAp8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1N_DtRpdAp8.npy", "labels": "/m/01jwx6", "caption": "Loud clicking machine noises that revs up and down" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/Yk4XyfaWVLEY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yk4XyfaWVLEY.npy", "labels": "/m/01bjv,/m/07yv9,/m/09x0r", "caption": "A vehicle engine idles and birds chirp in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YlTfNLKEy1RU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YlTfNLKEy1RU.npy", "labels": "/m/01d3sd,/m/0bt9lr,/m/0jbk", "caption": "Continuous light snoring" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part15/YFi4-IqJo2xQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YFi4-IqJo2xQ.npy", "labels": "/m/02mk9,/m/07rqsjt,/m/07yv9,/m/0k4j", "caption": "An engine revving with whooshing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YTSdAJWJ-tW0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YTSdAJWJ-tW0.npy", "labels": "/m/012f08,/m/07yv9,/m/0k4j,/t/dd00134", "caption": "A man talking in the background as vehicles drive by" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YHqndxoujCYI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YHqndxoujCYI.npy", "labels": "/m/07qjznl,/m/09x0r", "caption": "A bell chiming as a man is speaking in the background followed by a muffled bell chiming" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YBXxlqaDvdaA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBXxlqaDvdaA.npy", "labels": "/m/05kq4,/m/07yv9,/m/09x0r,/m/0hsrw,/m/0j6m2", "caption": "Male speech and wind blowing hard over microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YITlqMkR5alY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YITlqMkR5alY.npy", "labels": "/m/03fwl,/m/09x0r,/m/0ch8v,/m/0jbk", "caption": "Background rustling followed by a goat screaming" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YHUwXtfYRFwk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YHUwXtfYRFwk.npy", "labels": "/m/012f08,/m/01bjv,/m/07yv9,/m/0k4j", "caption": "City ambiance with multiple cars driving by and a large vehicle engine revving then accelerating" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y54eRRbCtPn8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y54eRRbCtPn8.npy", "labels": "/m/02qldy,/m/02zsn,/m/09x0r", "caption": "Woman speaking in a quiet environment" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y2KR0C5ysO8o.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y2KR0C5ysO8o.npy", "labels": "/m/02mk9,/m/07pb8fc,/m/07q2z82,/m/07yv9,/m/09x0r,/t/dd00066", "caption": "An engine revving continuously" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part27/Y_AcJVyToQUQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y_AcJVyToQUQ.npy", "labels": "/m/01j3sz,/m/09x0r", "caption": "A baby laughing and the female speech and male shouting" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part24/YVZLZ08k3YeA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YVZLZ08k3YeA.npy", "labels": "/m/01d3sd,/m/09x0r", "caption": "Someone snores and a man speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y7XXSOzDQ2z0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y7XXSOzDQ2z0.npy", "labels": "/m/07yv9,/m/0h9mv,/m/0k4j,/m/0ltv", "caption": "A mid-size motor vehicle engine is idling and clacking somewhat, followed by mid-size motor vehicles accelerating quickly with a brief tire squeal" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y466ucPGoNSQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y466ucPGoNSQ.npy", "labels": "/m/01yrx,/m/068hy,/m/07qrkrw,/m/09x0r,/m/0jbk", "caption": "A speech and then a cat vocalizing repeatedly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YZ7yDwpdGelM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YZ7yDwpdGelM.npy", "labels": "/m/07pqc89,/m/09x0r", "caption": "A man speaking followed by sawing then plastic crinkling as water trickles" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/Yc3nlaAkv9bA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yc3nlaAkv9bA.npy", "labels": "/m/03fwl,/m/068hy,/m/09x0r,/m/0ch8v,/m/0jbk", "caption": "Male speech and a goat bleating" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YR_g4RpU9mO0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YR_g4RpU9mO0.npy", "labels": "/m/019jd,/m/02rlv9,/m/07yv9", "caption": "A motor boat idling then taking off" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YT9_ep-3BZDY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YT9_ep-3BZDY.npy", "labels": "/m/09x0r,/t/dd00112,/t/dd00125", "caption": "A woman speaks with some rustling and crinkling of plastic" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YROootH-mtEI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YROootH-mtEI.npy", "labels": "/m/0j6m2", "caption": "Water moving down a stream swiftly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9_YfTz8cnFY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9_YfTz8cnFY.npy", "labels": "/m/06hck5,/m/06wzb,/m/07rjwbb", "caption": "People are speaking in the background, a hiss occurs, then a steam whistle blows" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/YwrQDkX0NbTA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YwrQDkX0NbTA.npy", "labels": "/m/019jd,/m/02rlv9,/m/07yv9", "caption": "A motorboat accelerating and water splashing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/YiOCpICiu4LA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YiOCpICiu4LA.npy", "labels": "/m/01h3n,/m/03l9g,/m/03vt0,/m/0h2mp", "caption": "Birds chirp in the background while an adult male speaks and many bees buzz" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YSGaIvgwwWSE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YSGaIvgwwWSE.npy", "labels": "/m/06mb1,/m/0jb2l,/m/0ngt1", "caption": "It is thundering and raining" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/Ye9MWXS34o48.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ye9MWXS34o48.npy", "labels": "/m/01hsr_", "caption": "A person breathing heavily then sneezing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YWUpeplQr3A4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YWUpeplQr3A4.npy", "labels": "/m/01d380", "caption": "A man screams while a drill runs" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YS_3aeOvniZc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YS_3aeOvniZc.npy", "labels": "/m/07yv9,/m/0k4j,/m/0ltv", "caption": "A motor runs as tires screech twice" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part4/Y32565FEuksc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y32565FEuksc.npy", "labels": "/m/02qldy,/m/02zsn,/m/09x0r", "caption": "A woman speaks and a crowd applauds" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y1QNLMF-Kl_s.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1QNLMF-Kl_s.npy", "labels": "/m/02qldy,/m/02zsn,/m/09x0r", "caption": "A woman is speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YlX3k5p2I_g0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YlX3k5p2I_g0.npy", "labels": "/m/014yck,/m/02mk9,/m/07yv9,/m/09x0r,/m/0cmf2,/m/0k5j", "caption": "A man talking followed by another man shouting then an aircraft engine starting up as vehicles drive by in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part0/Y--0w1YA1Hm4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y--0w1YA1Hm4.npy", "labels": "/m/01bjv,/m/07yv9,/m/09x0r", "caption": "A vehicle driving as a man and woman are talking and laughing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y1vCYiVvZ7VE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1vCYiVvZ7VE.npy", "labels": "/m/02qldy,/m/02zsn,/m/09x0r", "caption": "An adult female speaks in a quiet environment" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YmJ6ZO3xEcgw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YmJ6ZO3xEcgw.npy", "labels": "/m/01hsr_", "caption": "A woman repeatedly sneezing and coughing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YPMMkPq5jJXY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YPMMkPq5jJXY.npy", "labels": "/m/03q5_w,/m/09x0r", "caption": "A person burps followed by laughter" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YDlWd7Wmdi1E.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YDlWd7Wmdi1E.npy", "labels": "/m/015p6,/m/07rc7d9,/m/09x0r,/m/0jbk", "caption": "A man talks while several animals make noises in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YPvWI4p74UOs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YPvWI4p74UOs.npy", "labels": "/m/019jd,/m/02rlv9,/m/07yv9,/m/09x0r", "caption": "Laughing and birds chirping with wind and an engine running" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4sb9jN0SgTM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4sb9jN0SgTM.npy", "labels": "/m/02mk9,/m/07pb8fc,/m/07q2z82,/m/07yv9,/m/09x0r,/m/0k4j,/t/dd00066", "caption": "A motor vehicle engine accelerates, and a man speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YOpiWMltpj44.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YOpiWMltpj44.npy", "labels": "/m/015p6,/m/09ddx,/m/0dbvp", "caption": "Several ducks quack with some distant humming" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YPZBUdlKwX04.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YPZBUdlKwX04.npy", "labels": "/m/09x0r,/m/0j2kx,/m/0j6m2", "caption": "A plastic clack followed by a man talking as a stream of water rushes and a crowd of people talk in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part4/Y2bq2lc3DLwM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y2bq2lc3DLwM.npy", "labels": "/m/07yv9,/m/09x0r,/m/0k4j,/t/dd00134", "caption": "A man gives a talk while engines were in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YHg6HxylRGDo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YHg6HxylRGDo.npy", "labels": "/m/012n7d,/m/03j1ly,/m/03kmc9", "caption": "An emergency vehicle sounds sirens as a vehicle accelerates" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YCM49C3RkzV8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YCM49C3RkzV8.npy", "labels": "/m/02qldy,/m/02zsn,/m/09x0r", "caption": "A woman delivers a speech" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YqPYwp1K4sZE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YqPYwp1K4sZE.npy", "labels": "/m/09x0r,/t/dd00112,/t/dd00125", "caption": "A young girl speaking with some crinkling plastic" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3wrdPAeqjVI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3wrdPAeqjVI.npy", "labels": "/m/083vt,/m/09x0r", "caption": "A man talking followed by a camera muffling and footsteps shuffling then wood lightly clanking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YYH4qi8Ul6v0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YYH4qi8Ul6v0.npy", "labels": "/m/09x0r,/t/dd00002", "caption": "Men humming and talking with baby crying in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YBDpU2Qh77NE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBDpU2Qh77NE.npy", "labels": "/m/015p6,/m/020bb7,/m/07pggtn", "caption": "Birds chirp followed by people communicating" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part19/YMkbP_8zJwXU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YMkbP_8zJwXU.npy", "labels": "/m/015p6,/m/068hy,/m/09ddx,/t/dd00129", "caption": "A bird chirping as water lightly trickles and wind blows into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YAf4a-9rcnP0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YAf4a-9rcnP0.npy", "labels": "/m/07qsvvw", "caption": "A loud burst followed by rustling and then spraying" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y6ZwYgzcN6Is.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y6ZwYgzcN6Is.npy", "labels": "/m/09x0r,/m/0j6m2,/t/dd00129", "caption": "Ocean waves crashing as a woman laughs and yells as a group of boys and girls scream and laugh in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/Yyau2WIRkxb8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yyau2WIRkxb8.npy", "labels": "/m/09ct_", "caption": "A toy helicopter flying" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/Yjj2RyNDj7no.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yjj2RyNDj7no.npy", "labels": "/m/01h3n,/m/03vt0,/m/0h2mp", "caption": "Bees buzz while birds call followed by man speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y1Uh74_rZ72k.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1Uh74_rZ72k.npy", "labels": "/m/07swgks", "caption": "Distant thumping with some lights wind" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/Yt1hj7se76wQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yt1hj7se76wQ.npy", "labels": "/m/0316dw,/m/07qn4z3,/m/0c2wf", "caption": "Typing on a typewriter is ongoing with clicking and clacking, a bell rings, and a clack occurs with the carriage return" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YBZCEDkx37rI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBZCEDkx37rI.npy", "labels": "/m/02mk9,/m/07pb8fc,/t/dd00066,/t/dd00130", "caption": "A muffled vehicle engine revving then running idle as cloth rustles" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/YpHYkWkZ4guE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YpHYkWkZ4guE.npy", "labels": "/m/06wzb,/m/07rjwbb", "caption": "Steam followed by knocking sounds" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/YjYPU6aSDo88.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YjYPU6aSDo88.npy", "labels": "/m/014yck,/m/07yv9,/m/09x0r,/m/0k5j", "caption": "An aircraft engine running in the distance as wind blows into a microphone followed by a man talking in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y6dLkgq9EKPE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y6dLkgq9EKPE.npy", "labels": "/m/01bjv,/m/07yv9,/m/09x0r", "caption": "An engine whines in the background as a man talks followed by a smack then a high pitched whistle before a woman speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YJnSwRonB9wI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YJnSwRonB9wI.npy", "labels": "/m/019jd,/m/02rlv9,/m/034srq,/m/05kq4", "caption": "A muffled motorboat engine running as a group of people are laughing and screaming while water splashes and sprays" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part38/YvEWmHtiznF8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YvEWmHtiznF8.npy", "labels": "/m/012f08,/m/01bjv,/m/07yv9,/m/09x0r", "caption": "A bus engine running idle as a man is talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part7/Y6NBPiArs2-w.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y6NBPiArs2-w.npy", "labels": "/m/032s66", "caption": "Footsteps followed by rapid gunshots and people speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y7_smJ8VbfSU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y7_smJ8VbfSU.npy", "labels": "/m/02qldy,/m/02zsn,/m/09x0r", "caption": "A woman is speaking with people communicating in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/Yg6CY7qvu81k.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yg6CY7qvu81k.npy", "labels": "/m/07p9k1k", "caption": "Music followed by male speech and distant sizzling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/Yeu5bq0A3XVQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yeu5bq0A3XVQ.npy", "labels": "/m/03q5_w,/m/09x0r", "caption": "A loud exhale followed by a man speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YSNy_axSCoyw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YSNy_axSCoyw.npy", "labels": "/m/07qjznl", "caption": "Mechanical sound with clock tick-tocking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part15/YGGgQR7aIofY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YGGgQR7aIofY.npy", "labels": "/m/012f08,/m/01bjv,/m/07yv9", "caption": "A horn sounds as wind blows followed by motor vehicle engine noise" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YK-7Y8yhcUiw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YK-7Y8yhcUiw.npy", "labels": "/m/01d3sd,/m/068hy,/m/0bt9lr,/m/0jbk", "caption": "A dog snoring loudly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3RultJjvTWI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3RultJjvTWI.npy", "labels": "/m/019jd,/m/034srq,/m/03m9d0z,/t/dd00092", "caption": "Water splashing with speech and brief laughter" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YXrJcmftCY04.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YXrJcmftCY04.npy", "labels": "/m/028ght", "caption": "A crowd of people applauding and cheering" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YS0SQyFXbqF8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YS0SQyFXbqF8.npy", "labels": "/m/09ld4", "caption": "A child talking then laughing with a man as an animal gurgles followed by a man talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YbQNX7vDalQw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YbQNX7vDalQw.npy", "labels": "/m/07p9k1k", "caption": "A man speaks followed by heavy sizzling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/Yj1AiqT5oHZc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yj1AiqT5oHZc.npy", "labels": "/m/02fs_r,/m/09x0r,/t/dd00125", "caption": "Beep then male speaking multiple times" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YC8kR19NvynA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YC8kR19NvynA.npy", "labels": "/m/02qldy,/m/05zppz,/m/09x0r", "caption": "A man speaking continuously" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3ndid3jni7M.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3ndid3jni7M.npy", "labels": "/m/01g50p,/m/0284vy3,/m/06d_3,/m/07jdr,/m/07rwm0c", "caption": "A main horn honks, a train passes by" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y6ZFU4PqXmoI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y6ZFU4PqXmoI.npy", "labels": "/m/019jd,/m/02rlv9,/m/07yv9,/m/09x0r", "caption": "Humming and vibrating followed by rustling and splashes with a man speaking briefly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y5G6b_QWL3nY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y5G6b_QWL3nY.npy", "labels": "/m/07p9k1k,/m/0dxrf", "caption": "A woman is speaking while food is frying and sizzling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YbLZFtoWXYTA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YbLZFtoWXYTA.npy", "labels": "/m/02jz0l", "caption": "Liquid is trickling, splashing and gurgling while filling a container" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/YoiIi6H83Y38.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YoiIi6H83Y38.npy", "labels": "/m/04_sv,/m/07yv9,/m/09x0r", "caption": "A motorbike engine starting up then revving as a man talks in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/Yg_P29ucKj78.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yg_P29ucKj78.npy", "labels": "/m/07yv9,/m/0k4j,/t/dd00134", "caption": "Racecar motor revving engine with downshifting" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YndxkSQKxaak.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YndxkSQKxaak.npy", "labels": "/m/04_sv,/m/07yv9,/m/09x0r", "caption": "An engine running and male speech" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/Yzq00Oe1ecpE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yzq00Oe1ecpE.npy", "labels": "/m/012f08,/m/01bjv,/m/07yv9", "caption": "A vehicle running and then speeding up" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part19/YNJEPbGVBJIQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YNJEPbGVBJIQ.npy", "labels": "/m/012f08,/m/04_sv,/m/07yv9,/m/09x0r,/m/0btp2,/t/dd00128", "caption": "Male speech and an engine revving and a honk in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YAWGnTI0e2Fs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YAWGnTI0e2Fs.npy", "labels": "/m/09ct_", "caption": "Helicopter propellers spinning" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YT32kii824pA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YT32kii824pA.npy", "labels": "/m/083vt", "caption": "A man speaking as metal clanks and gears crank followed by pots and pans falling onto a hard surface" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/Yw_Utn3CwAXE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yw_Utn3CwAXE.npy", "labels": "/m/01jt3m,/m/0838f", "caption": "A toilet flushing followed by plastic clacking and a door slowly creaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YZ-SIyOChVh8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YZ-SIyOChVh8.npy", "labels": "/m/06mb1,/m/0jb2l,/m/0ngt1", "caption": "Thunder is booming, and rain is falling and pattering on a surface" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y1WTSW96XP6E.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1WTSW96XP6E.npy", "labels": "/m/04_sv,/m/07yv9,/m/09x0r", "caption": "A male speech followed by an engine starting" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YtdpiXW68adA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YtdpiXW68adA.npy", "labels": "/m/0463cq4,/m/09x0r", "caption": "A woman sobbing and speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YtTB0BK39JI8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YtTB0BK39JI8.npy", "labels": "/m/0395lw", "caption": "A series of bell chime as wood shuffles and a clock ticks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YDzKjogSVOLM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YDzKjogSVOLM.npy", "labels": "/m/07qdb04,/m/09ddx,/m/09x0r,/m/0jbk", "caption": "Ducks quacking and birds tweeting as a crowd of people talk while a rooster crows in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/Yl5KdHAWwJCw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yl5KdHAWwJCw.npy", "labels": "/m/07qjznl", "caption": "Ticking of a clock" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/Yh5_1pnkl_SY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yh5_1pnkl_SY.npy", "labels": "/m/02jz0l,/m/0838f", "caption": "Middle aged man speaks foreign language while water is trickling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part0/Y-EaZ7EJJUl0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y-EaZ7EJJUl0.npy", "labels": "/m/023pjk,/m/04brg2", "caption": "Man speaking and clinking dishes" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YsbW7XwwUtSU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YsbW7XwwUtSU.npy", "labels": "/m/07qjznl,/m/07qjznt", "caption": "A clock ticking with a series of bell chimes" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YlJayhiVzl_E.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YlJayhiVzl_E.npy", "labels": "/m/019jd,/m/02rlv9,/m/03m9d0z,/t/dd00092", "caption": "Water trickling as a motorboat engine runs and wind blows on a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/Yn-JyOqYSLQM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yn-JyOqYSLQM.npy", "labels": "/m/07qlf79", "caption": "Metal clanking followed by plastic rattling and air spraying with a group of people talking faintly in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YPMMdAKZxI_I.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YPMMdAKZxI_I.npy", "labels": "/m/03q5_w,/m/09x0r", "caption": "Burping and laughing by girls with distant speaking of a television" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/YfBYDJWChe5c.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YfBYDJWChe5c.npy", "labels": "/m/01d3sd", "caption": "A person snoring" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part27/Y_9mgOkzm-xg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y_9mgOkzm-xg.npy", "labels": "/m/09x0r,/m/0dxrf,/t/dd00125", "caption": "A man speaks as food sizzles followed by some cracks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YAgaiowyYt88.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YAgaiowyYt88.npy", "labels": "/m/02dgv", "caption": "Loud banging followed by silence" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y1GgEpRZDWN0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1GgEpRZDWN0.npy", "labels": "/m/01h8n0,/m/02zsn,/m/09x0r", "caption": "A man and woman speak" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part0/Y-FW109cbv0g.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y-FW109cbv0g.npy", "labels": "/m/01hsr_,/m/09x0r", "caption": "A man laughs and talks with another man sneezing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YPTyFYxXdut4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YPTyFYxXdut4.npy", "labels": "/m/07pqc89,/m/0838f,/m/09x0r", "caption": "A woman speaking as water softly splashes and trickles while wind lightly blows into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part4/Y2msevPMQB4M.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y2msevPMQB4M.npy", "labels": "/m/01d380,/m/07k1x", "caption": "A power tool is being used to cut" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9E8BmPZ9mWc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9E8BmPZ9mWc.npy", "labels": "/m/07r04,/m/07yv9,/m/09x0r", "caption": "An engine chugging followed by distant speech" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YDlWd7Wmdi1E.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YDlWd7Wmdi1E.npy", "labels": "/m/015p6,/m/07rc7d9,/m/09x0r,/m/0jbk", "caption": "A man speaking followed by dogs barking alongside chimps screaming and birds chirping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YlmPMhs-9IYE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YlmPMhs-9IYE.npy", "labels": "/m/07yv9,/m/09x0r,/m/0k4j,/m/0ltv", "caption": "Revving of an engine with people cheering while someone speaks through a speaker" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YDrCm-HpX67k.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YDrCm-HpX67k.npy", "labels": "/m/083vt", "caption": "Cracking with some rustling as distant birds chirp" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/Yy_OyLW9lBXU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yy_OyLW9lBXU.npy", "labels": "/m/09x0r,/t/dd00002", "caption": "A baby cries and people speak" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/Yii3Geza3hAU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yii3Geza3hAU.npy", "labels": "/m/0llzx", "caption": "Vibrations from a sewing machine in bursts" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YsqWyxUObwkw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YsqWyxUObwkw.npy", "labels": "/m/019jd,/m/02rlv9,/m/07yv9", "caption": "A boat engine starts up and idles" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YniwgMbB6tpQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YniwgMbB6tpQ.npy", "labels": "/m/01d3sd", "caption": "High-pitched snoring occurs in a rhythmic pattern" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/YhGWarNR6xmg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YhGWarNR6xmg.npy", "labels": "/m/06wzb,/m/07rjwbb", "caption": "A roaring hiss is ongoing, and a brief low hum occurs" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YtdpiXW68adA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YtdpiXW68adA.npy", "labels": "/m/0463cq4,/m/09x0r", "caption": "A young girl speaks and cries" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YqeSl7YZAfs4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YqeSl7YZAfs4.npy", "labels": "/m/0130jx,/m/02jz0l,/m/0838f", "caption": "Faucet running and a man speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9vZDsGjyh5M.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9vZDsGjyh5M.npy", "labels": "/m/07r04,/m/07yv9,/m/0k4j", "caption": "Vehicle motor running" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YWHRnyGXcdy8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YWHRnyGXcdy8.npy", "labels": "/t/dd00002", "caption": "A baby continuously crying" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YCeRoaEcqUgM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YCeRoaEcqUgM.npy", "labels": "/m/019jd,/m/02rlv9,/m/07yv9", "caption": "A speedboat is traveling across water followed by strong wind noise" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YAUJPx81qKtY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YAUJPx81qKtY.npy", "labels": "/m/01h3n,/m/03vt0,/m/0h2mp", "caption": "An adult male speaks, birds chirp in the background, and many insects are buzzing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YIdBDl9Wr51A.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YIdBDl9Wr51A.npy", "labels": "/m/07rqsjt", "caption": "Synthesized laser effects and explosions as a man talks followed by a deeper voiced man talking then woman laughing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YIvfaKPDWC00.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YIvfaKPDWC00.npy", "labels": "/m/012f08,/m/012ndj,/m/03j1ly,/m/03kmc9,/m/07yv9", "caption": "Sirens ring and a vehicle speeds closer" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YTtRtURWVYBE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YTtRtURWVYBE.npy", "labels": "/m/0395lw", "caption": "Bells ringing a tune" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part24/YUXGzbBGbqAA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YUXGzbBGbqAA.npy", "labels": "/m/07ryjzk,/m/0dxrf", "caption": "Slapping noises while a person breathes heavily" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YCO6-i8NLbeo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YCO6-i8NLbeo.npy", "labels": "/m/03fwl,/m/09x0r,/m/0jbk", "caption": "A man talking followed by a goat baaing then a metal gate sliding shut as ducks quack and wind blows into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/Yi2yhbckq3p0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yi2yhbckq3p0.npy", "labels": "/m/012f08,/m/04_sv,/m/07yv9,/m/0k4j", "caption": "A motorcycle engine running as several vehicle horns honk while a car alarm rings in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YEfk5kdn9lR8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YEfk5kdn9lR8.npy", "labels": "/m/02dgv,/m/02y_763,/m/09x0r", "caption": "A female child speaks, clattering and banging occur and the child screams, an adult male speaks in the background, and then more clattering and banging occur" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part0/Y-EQByFLFqig.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y-EQByFLFqig.npy", "labels": "/m/06mb1,/m/0ngt1,/t/dd00038", "caption": "A man speaks as rain pitter-patters and thunder rumbles" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y6i5eQOpFk_U.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y6i5eQOpFk_U.npy", "labels": "/m/0130jx,/m/02jz0l,/m/0838f", "caption": "Water is running, splashing and gurgling, thumps occur, an adult male speaks, and people are talking in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y1WTSW96XP6E.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1WTSW96XP6E.npy", "labels": "/m/04_sv,/m/07yv9,/m/09x0r", "caption": "A man speaks followed by several clicks then an engine struggling to start" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YIJ6pm5Kns8A.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YIJ6pm5Kns8A.npy", "labels": "/m/03q5_w,/m/09x0r", "caption": "Woman speaks, girl speaks, clapping, croaking noise interrupts, followed by laughter" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YatmDP_fmK_8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YatmDP_fmK_8.npy", "labels": "/m/014zdl,/m/07qsvvw", "caption": "A loud, long explosion" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YLvhvAA11oxE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YLvhvAA11oxE.npy", "labels": "/m/07yv9,/m/09x0r,/m/0h9mv,/m/0ltv,/t/dd00128", "caption": "A vehicle engine repeatedly revving as tires skid while a man talks over an intercom and wind blows into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part27/Y_BSmz3SEW1w.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y_BSmz3SEW1w.npy", "labels": "/m/015p6,/m/0h0rv,/t/dd00125,/t/dd00129", "caption": "Pigeons coo and rustle" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y7QN3lwOzfdg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y7QN3lwOzfdg.npy", "labels": "/m/07cx4,/m/09x0r", "caption": "A man and woman are having a conversation on the telephone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YXWw7ZM1c_QA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YXWw7ZM1c_QA.npy", "labels": "/m/07qjznl,/m/09x0r", "caption": "A woman is speaking as surface is scratched followed by ticktock sounds" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/Yjf4iyQPJSvk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yjf4iyQPJSvk.npy", "labels": "/m/07pqc89,/m/0838f,/m/0j2kx,/t/dd00129", "caption": "Water is trickling while wind is blowing in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/Yi1u_2eZYYlE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yi1u_2eZYYlE.npy", "labels": "/m/07pb8fc,/m/07r04,/m/07yv9", "caption": "Brief vibrations from a truck" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/YcNARVD02-tw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YcNARVD02-tw.npy", "labels": "/m/02jz0l,/m/09x0r", "caption": "Two people talking then water running" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/Yn4VktYihtJU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yn4VktYihtJU.npy", "labels": "/m/07swgks,/m/09x0r", "caption": "High wind with people yelling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/YwVi5w_NU6CM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YwVi5w_NU6CM.npy", "labels": "/m/012f08,/m/012ndj,/m/03j1ly,/m/03kmc9,/m/07r04,/m/07yv9", "caption": "A fire truck siren blasts" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YSCow4mpBsGY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YSCow4mpBsGY.npy", "labels": "/m/01d3sd", "caption": "A person is snoring" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/YgwQMkQmBITE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YgwQMkQmBITE.npy", "labels": "/m/083vt,/m/09x0r,/t/dd00125", "caption": "A man is talking with thumping noises in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/Ybpv_LneHmfU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ybpv_LneHmfU.npy", "labels": "/m/014yck,/m/07yv9,/m/0cmf2,/m/0k5j,/t/dd00129", "caption": "A high pitched airplane engine idles" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YZYWCwfCkBp4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YZYWCwfCkBp4.npy", "labels": "/m/01b82r,/m/07pdjhy,/m/083vt", "caption": "Sawing wood with music playing in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YJBWJQCS4SvA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YJBWJQCS4SvA.npy", "labels": "/m/034srq,/m/03m9d0z,/m/05kq4,/t/dd00092", "caption": "Wind noise on microphone with waves splashing in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YmWqH2xwjkYA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YmWqH2xwjkYA.npy", "labels": "/m/01j3sz,/m/09x0r", "caption": "A baby and a woman laugh" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YPTyFYxXdut4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YPTyFYxXdut4.npy", "labels": "/m/07pqc89,/m/0838f,/m/09x0r", "caption": "Water is trickling while a woman is speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YLs2vrr9TamU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YLs2vrr9TamU.npy", "labels": "/m/083vt", "caption": "A machine is chopping wood" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/YoZaEHkfh5Eg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YoZaEHkfh5Eg.npy", "labels": "/m/07yv9,/m/0912c9,/m/0k4j", "caption": "A vehicle horn honking during a series of electronic beeps" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YrUq4w4EUSWA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YrUq4w4EUSWA.npy", "labels": "/m/01jt3m,/m/0838f", "caption": "An electronic motor buzzing and paper tearing followed by a bell chiming and a plastic click then a toilet flushing as paper crinkles in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YXi6V0LGvqoo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YXi6V0LGvqoo.npy", "labels": "/m/01z5f,/m/068hy,/m/07rc7d9,/m/0bt9lr,/m/0jbk", "caption": "Dog whimpering and barking together with rustling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9_YfTz8cnFY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9_YfTz8cnFY.npy", "labels": "/m/06hck5,/m/06wzb,/m/07rjwbb", "caption": "A long train whistle and a train chugging" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/YwbPmnxCLoRQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YwbPmnxCLoRQ.npy", "labels": "/m/0395lw", "caption": "Several bells ringing rapidly and then a single bell" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YSQHYl2Kp5ww.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YSQHYl2Kp5ww.npy", "labels": "/m/07ptfmf,/m/0dxrf", "caption": "Music is ongoing while two adult males speak, and sizzling and crackling occur along with random metal scraping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y1nUOGZgSzZo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1nUOGZgSzZo.npy", "labels": "/m/07swgks,/m/09x0r,/m/0j6m2", "caption": "Plastic thumping as a man laughs and a kid talk in the distance as wind blows into a microphone and water is splashing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YD4s5aHrsBgs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YD4s5aHrsBgs.npy", "labels": "/m/01w250", "caption": "A person whistles to music" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YKtinboYbmHQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YKtinboYbmHQ.npy", "labels": "/m/07rknqz,/m/07yv9,/m/0h9mv,/m/0k4j", "caption": "Tires squeal and an engine hums as a vehicle approaches" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YlTfNLKEy1RU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YlTfNLKEy1RU.npy", "labels": "/m/01d3sd,/m/0bt9lr,/m/0jbk", "caption": "Repetitive faint snoring" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/YxnVqvc7N7Po.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YxnVqvc7N7Po.npy", "labels": "/m/07cx4,/m/09x0r", "caption": "A woman speaking over a phone and a man speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y1_z6NcidGzM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1_z6NcidGzM.npy", "labels": "/m/07swgks,/m/09x0r,/m/0j6m2", "caption": "Various speech and a whistle blown and water splashing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part38/YvfNKduToki4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YvfNKduToki4.npy", "labels": "/m/07r04,/m/07yv9,/m/09x0r", "caption": "A truck engine running as a man yells in the distance followed by steam hissing as vehicles drive by in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YkF1KWybdRpM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YkF1KWybdRpM.npy", "labels": "/m/014yck,/m/07yv9,/m/0cmf2,/m/0k5j", "caption": "Aircraft engine roars as it approaches and then recedes" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/Ys_EWjoiVfzo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ys_EWjoiVfzo.npy", "labels": "/m/0llzx", "caption": "A sewing machine operating several times between metal clicking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/Yg5l3Bz6lWnc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yg5l3Bz6lWnc.npy", "labels": "/m/01h3n,/m/03vt0", "caption": "Insects buzzing as wood lightly shuffles and birds chirp in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/YpCQEWAFGEjc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YpCQEWAFGEjc.npy", "labels": "/m/06wzb,/m/07rjwbb", "caption": "A steam engine running on railroad tracks as steam releases and hisses while group of people talk in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/YpWQeV08kYR0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YpWQeV08kYR0.npy", "labels": "/m/012n7d,/m/03j1ly,/m/03kmc9,/m/07yv9,/t/dd00128", "caption": "An ambulance sounds the siren" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part27/YZsf2YvJfCKw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YZsf2YvJfCKw.npy", "labels": "/m/01jt3m", "caption": "Water trickling followed by a toilet flushing then liquid draining through a pipe" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YI_vN_BFUr0Y.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YI_vN_BFUr0Y.npy", "labels": "/m/01g50p,/m/0284vy3,/m/04zmvq,/m/06d_3,/m/07jdr,/m/07yv9", "caption": "A train horn blowing several times as a train runs on railroad tracks and a railroad crossing signal rings in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YJfaj4P3us9M.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YJfaj4P3us9M.npy", "labels": "/m/02c8p,/m/07cx4", "caption": "A phone dial tone playing followed by a plastic switch flipping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/YwBs02amFGXs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YwBs02amFGXs.npy", "labels": "/m/015p6,/m/0h0rv,/t/dd00125,/t/dd00129", "caption": "A rooster crowing and birds cooing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YEcihYbSlyck.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YEcihYbSlyck.npy", "labels": "/m/01bjv,/m/07yv9,/m/09x0r", "caption": "The wind is blowing, a large motor vehicle engine idles, an electronic signal beep, a vehicle horn blows, and faint speech is present in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4UPOUGVMlEs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4UPOUGVMlEs.npy", "labels": "/t/dd00018", "caption": "Rustling and breathing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YR8bHTHnF8j4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YR8bHTHnF8j4.npy", "labels": "/m/07yv9,/m/09ct_,/m/0k5j", "caption": "Helicopter rotors slowing down" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YPVvi2SDOjVc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YPVvi2SDOjVc.npy", "labels": "/m/07yv9,/m/0912c9,/m/0k4j,/t/dd00128", "caption": "A vehicle is running followed by the horn honking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YEYTz1LPDHsc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YEYTz1LPDHsc.npy", "labels": "/m/02dgv", "caption": "Birds chirping followed by a car door unlocking and opening" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/YoiIi6H83Y38.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YoiIi6H83Y38.npy", "labels": "/m/04_sv,/m/07yv9,/m/09x0r", "caption": "A motor vehicle engine is starting and accelerating" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YrtgVoZCcBw8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YrtgVoZCcBw8.npy", "labels": "/m/03fwl,/m/09x0r,/m/0jbk", "caption": "Goats are bleating with other natural outdoor noises" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y8ycflE3dIHw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y8ycflE3dIHw.npy", "labels": "/m/01g50p,/m/0284vy3,/m/06d_3,/m/07jdr,/m/07rwm0c", "caption": "A train passes and then a horn honks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part38/Yv59uHr-B1no.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yv59uHr-B1no.npy", "labels": "/m/09ld4", "caption": "Frogs call out to each other over the chirp of insects" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YYNDKuNINDOY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YYNDKuNINDOY.npy", "labels": "/m/012ndj,/m/03j1ly,/m/03kmc9", "caption": "A wailing siren fades, a motor sputters, then the siren resumes accompanied by blaring horns" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4abZbau8tZo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4abZbau8tZo.npy", "labels": "/m/07swgks,/m/09x0r", "caption": "Swirling wind followed by a man speaking and then a child talks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/YwSHzVxdMiTo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YwSHzVxdMiTo.npy", "labels": "/m/09x0r,/t/dd00018", "caption": "A pig squealing as a camera muffles and a man speaks briefly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y22L_3pBa1AI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y22L_3pBa1AI.npy", "labels": "/m/07yv9,/m/0k4j,/t/dd00134", "caption": "A car is shifting gears" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YZBtgrP4vU_w.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YZBtgrP4vU_w.npy", "labels": "/m/07p9k1k", "caption": "Food and oil sizzling rapidly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YFA11v4SmdBc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YFA11v4SmdBc.npy", "labels": "/m/01w250,/m/09x0r", "caption": "A man speaks then whistles" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YTOaQMYc79Mw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YTOaQMYc79Mw.npy", "labels": "/m/07yv9,/t/dd00130", "caption": "A vehicle struggling to start with some clicks and whines" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part15/YGIOApFAWDOc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YGIOApFAWDOc.npy", "labels": "/m/015p6,/m/020bb7,/m/07pggtn", "caption": "Birds chirping and tweeting followed by light wood tapping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YS8k47ME-YT4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YS8k47ME-YT4.npy", "labels": "/m/06mb1,/m/0jb2l,/m/0ngt1", "caption": "Plastic cranking as rain heavily pours while a stream of water rapidly flows" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/Yo3mZR8OvPko.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yo3mZR8OvPko.npy", "labels": "/m/07yv9,/m/0k4j,/m/0ltv,/t/dd00128", "caption": "A vehicle engine driving by while tires skid" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YEBCH7TPgiPc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YEBCH7TPgiPc.npy", "labels": "/m/07q2z82,/m/07yv9,/m/0k4j", "caption": "Engine revs very high for a while, then begins to slow down" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YnD1K1Zo0qrM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YnD1K1Zo0qrM.npy", "labels": "/m/032s66,/m/04zjc", "caption": "A series of machine gunfire and two gunshots firing as a jet aircraft flies by followed by soft music playing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YkOYg4ZtKcAs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YkOYg4ZtKcAs.npy", "labels": "/m/01yrx,/m/068hy,/m/07qrkrw,/m/0jbk", "caption": "A small motor vibrating followed by a cat meowing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part19/YMVGhC-xB79s.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YMVGhC-xB79s.npy", "labels": "/m/015p6,/m/09x0r,/m/0h0rv,/t/dd00128", "caption": "A child talking then a man speaking with bird sounds in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YB3O476LeuXY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YB3O476LeuXY.npy", "labels": "/m/07pb8fc,/t/dd00130", "caption": "A loud engine idles followed by an increase and decrease in the engine sounds" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YQ0anPAIkfBE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YQ0anPAIkfBE.npy", "labels": "/m/0463cq4,/m/09x0r,/t/dd00002,/t/dd00125", "caption": "A baby cries and a woman speaks followed by some light rustling and someone speaking faintly over a television" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/YfmEft49sPfE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YfmEft49sPfE.npy", "labels": "/m/05zppz,/m/09t49,/m/09x0r", "caption": "A man is speaking with the wind blowing in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YQ3vkJMVMbC8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YQ3vkJMVMbC8.npy", "labels": "/m/01jt3m", "caption": "Toilet flushes with a young girl shouting from a distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/Yj0KvrVE_Oww.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yj0KvrVE_Oww.npy", "labels": "/m/0912c9,/m/09x0r,/t/dd00125", "caption": "A door shutting followed by two men talking then a horn honking and slapping on a wooden surface" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9U8COLzEegs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9U8COLzEegs.npy", "labels": "/m/02fs_r,/m/09x0r", "caption": "A series of electronic beeps as a man is talking while water trickles in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YFL8KTgMGrN4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YFL8KTgMGrN4.npy", "labels": "/m/06wzb,/m/07rjwbb", "caption": "A vacuum running" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part9/Y8OTd45_6cvY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y8OTd45_6cvY.npy", "labels": "/m/07qlf79", "caption": "Footsteps with intermittent aerosol can activation" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YCMNlIW6Lkwc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YCMNlIW6Lkwc.npy", "labels": "/m/014zdl,/m/07qsvvw,/m/09x0r", "caption": "A man talking as a camera muffles followed by a loud explosion then a group of people laughing and talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part19/YMTIF_l_8d4Q.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YMTIF_l_8d4Q.npy", "labels": "/m/0463cq4,/m/09x0r", "caption": "An infant crying followed by a child speaking in the background then a young woman talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YLF6x7B0Ppvo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YLF6x7B0Ppvo.npy", "labels": "/m/07yv9,/m/0k4j,/m/0ltv", "caption": "A vehicle engine accelerating as plastic rattles and wind blows into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part38/Yup2PpjTzyyc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yup2PpjTzyyc.npy", "labels": "/m/01yrx,/m/07qrkrw,/m/09x0r,/m/0jbk", "caption": "Electronic beeping followed by a cat singing then meowing as paper shuffles and a man talks with music playing in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part15/YGuizRlAQ8qQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YGuizRlAQ8qQ.npy", "labels": "/m/01d380", "caption": "High powered vibrations from a power tool" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YriM7b5bJ9KQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YriM7b5bJ9KQ.npy", "labels": "/m/01j3sz,/m/09x0r", "caption": "Continuous laughing with brief tapping and speech" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/Yific_gRalg0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yific_gRalg0.npy", "labels": "/m/07swgks", "caption": "Rustling and tapping followed by brief gurgling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YYIqpIjjee00.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YYIqpIjjee00.npy", "labels": "/m/01jt3m", "caption": "A toilet flushing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y404cD3bVXDc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y404cD3bVXDc.npy", "labels": "/m/09x0r,/t/dd00002", "caption": "An infant crying then yelling as a man speaks through a television speaker" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/Yp_BB_rJaF7Q.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yp_BB_rJaF7Q.npy", "labels": "/m/09ld4", "caption": "Male speaking softly with nature sounds in background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YR_g4RpU9mO0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YR_g4RpU9mO0.npy", "labels": "/m/019jd,/m/02rlv9,/m/07yv9", "caption": "An engine running and then accelerating" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YFXdoNvmrYxo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YFXdoNvmrYxo.npy", "labels": "/m/03vt0,/m/09x0r,/t/dd00129", "caption": "A young girl talking followed by a man talking then a young boy softly talking as birds are chirping in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YQoEal_hKz4Q.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YQoEal_hKz4Q.npy", "labels": "/m/032s66,/m/04zjc", "caption": "Gunshots, machine gun fire, and artillery fire are ongoing, an adult male speaks in the foreground, and another adult male speaks in the far background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/YeqcdsdLz954.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YeqcdsdLz954.npy", "labels": "/m/014zdl,/m/07qsvvw", "caption": "An explosion and crackling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y1j5NMuq1X30.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1j5NMuq1X30.npy", "labels": "/m/07qlf79", "caption": "Liquid is being sprayed" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YLWng-4PDzPM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YLWng-4PDzPM.npy", "labels": "/m/01w250", "caption": "Rustling followed by whistling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YLKhokVsJhN0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YLKhokVsJhN0.npy", "labels": "/m/07bgp,/m/0ch8v,/m/0jbk", "caption": "Several sheep bleat" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YY3lNEe-ZGF0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YY3lNEe-ZGF0.npy", "labels": "/m/07qjznl,/m/07qjznt", "caption": "A clock ticking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YrgrmLLhxoCQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YrgrmLLhxoCQ.npy", "labels": "/t/dd00112", "caption": "Continuous crinkling in a quiet environment" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YZTYAQBnU4GM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YZTYAQBnU4GM.npy", "labels": "/m/015p6,/m/068hy,/m/07pggtn", "caption": "Pet birds tweet, chirp, and sing while music plays" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/Yh3UhoHIMfpw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yh3UhoHIMfpw.npy", "labels": "/m/02_41,/m/03m9d0z,/t/dd00092", "caption": "Wind blowing with some rustling and humming of engines" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part9/Y8ipe6b1LwHQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y8ipe6b1LwHQ.npy", "labels": "/m/023pjk,/m/04brg2", "caption": "Porcelain dishes clank followed by metal rattling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YbQNX7vDalQw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YbQNX7vDalQw.npy", "labels": "/m/07p9k1k", "caption": "A deep voice followed by sizzling food" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part1/Y0Dt-pH0pW-Y.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y0Dt-pH0pW-Y.npy", "labels": "/m/04_sv,/m/07yv9,/m/09x0r", "caption": "A small vehicle engine is running and an adult male speaks in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/YhVUmQfBIYe8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YhVUmQfBIYe8.npy", "labels": "/m/02dgv", "caption": "A man speaks with some clicking followed by wind blowing and a door opening" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/YxBZnvfniA1c.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YxBZnvfniA1c.npy", "labels": "/m/09x0r,/m/0ytgt,/t/dd00125", "caption": "A man speaking as a man talks over an intercom in the background followed by a girl talking then a group of people laughing and a man and woman talk" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part0/Y-DmjkgWa-rw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y-DmjkgWa-rw.npy", "labels": "/m/0395lw", "caption": "A bell ringing repeatedly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y466ucPGoNSQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y466ucPGoNSQ.npy", "labels": "/m/01yrx,/m/068hy,/m/07qrkrw,/m/09x0r,/m/0jbk", "caption": "A cat meowing as a man talks followed by wood knocking and a person breathing while a machine hums in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YQTSKjweEWew.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YQTSKjweEWew.npy", "labels": "/m/03m9d0z,/m/09x0r,/t/dd00129", "caption": "Wind blows hard then a man speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y6cyKp3EDm-0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y6cyKp3EDm-0.npy", "labels": "/m/015p6,/m/09x0r,/m/0h0rv", "caption": "Pigeons are making noises, and a man talks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YT9_ep-3BZDY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YT9_ep-3BZDY.npy", "labels": "/m/09x0r,/t/dd00112,/t/dd00125", "caption": "A woman speaks followed by crinkling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YENTi8Sn4vdM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YENTi8Sn4vdM.npy", "labels": "/m/0j6m2", "caption": "A river stream flowing while a woman and a kid are talking as birds chirp in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/YzEM94PH29VQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YzEM94PH29VQ.npy", "labels": "/m/09x0r,/t/dd00002", "caption": "A kid crying as a crowd of people talk in the background and a woman is yelling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YrINmxSXMR-s.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YrINmxSXMR-s.npy", "labels": "/m/07qdb04,/m/09ddx,/m/0jbk", "caption": "Water splashing occurs while a person quacks to imitate a duck and an adult female laughs" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y11SEBDuoqSk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y11SEBDuoqSk.npy", "labels": "/m/07yv9,/m/0cmf2,/m/0k5j", "caption": "Machine gun fire coming from an airplane" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/YfwhkCnOeyC0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YfwhkCnOeyC0.npy", "labels": "/m/028ght,/m/09x0r", "caption": "A man and a woman talking followed by a bell ringing and a cat meowing as a crowd of people applaud" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YmGa2JgAiKV8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YmGa2JgAiKV8.npy", "labels": "/m/07pqc89,/m/09x0r", "caption": "A man speaks then a second man speaks followed by a woman speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YkLYCjD6vWI4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YkLYCjD6vWI4.npy", "labels": "/m/06wzb,/m/07rjwbb", "caption": "A steam engine is hissing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YmaVYiednkSg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YmaVYiednkSg.npy", "labels": "/m/07qlf79,/m/09x0r", "caption": "A man speaks with spraying and vibration in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/YhiJB_95IWiE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YhiJB_95IWiE.npy", "labels": "/m/02p01q,/m/07pdjhy", "caption": "Male speech and then scraping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part1/Y096oTVzc5Gs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y096oTVzc5Gs.npy", "labels": "/m/09x0r,/m/0bt9lr,/m/0jbk,/t/dd00136", "caption": "Some rustling followed by a woman speaking with some groaning" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part7/Y6OlHuvJR_Dk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y6OlHuvJR_Dk.npy", "labels": "/m/07yv9,/m/09ct_", "caption": "Helicoptor flying" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YKVbmN9ZRg5Q.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YKVbmN9ZRg5Q.npy", "labels": "/m/01g50p,/m/0284vy3,/m/06d_3,/m/07jdr,/m/07rwm0c", "caption": "Loud hissing followed by a loud continuous horn and brief clanking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YCh0LMmhBUg4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YCh0LMmhBUg4.npy", "labels": "/m/03m9d0z,/m/06q74,/m/07yv9,/m/09x0r,/t/dd00129", "caption": "A man is speaking with wind background noise, and a child speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YECw5Yf7QoMo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YECw5Yf7QoMo.npy", "labels": "/m/02qldy,/m/05zppz,/m/09x0r", "caption": "A man talking in the foreground as another man talks in the background followed by a crowd of people applauding" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YQTSKjweEWew.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YQTSKjweEWew.npy", "labels": "/m/03m9d0z,/m/09x0r,/t/dd00129", "caption": "A brisk wind is blowing, hissing is ongoing, and an adult male speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YriM7b5bJ9KQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YriM7b5bJ9KQ.npy", "labels": "/m/01j3sz,/m/09x0r", "caption": "A man laughs followed by laughter and speech from other people" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YCchRf2jq6fc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YCchRf2jq6fc.npy", "labels": "/m/02qldy,/m/02zsn,/m/09x0r", "caption": "A young woman speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part15/YGGgQR7aIofY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YGGgQR7aIofY.npy", "labels": "/m/012f08,/m/01bjv,/m/07yv9", "caption": "A horn playing as a vehicle drives in the distance as gusts of wind blow" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YFR7BDRhMATo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YFR7BDRhMATo.npy", "labels": "/m/06hck5,/m/06wzb,/m/07rjwbb", "caption": "A high pitched loud horn honking followed by clanking and bells ringing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YUAmDLPjNyMg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YUAmDLPjNyMg.npy", "labels": "/m/07yv9,/m/0cmf2,/m/0k5j", "caption": "An aircraft flying in the distance as wind blows into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YJC2ZrXzCX4Y.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YJC2ZrXzCX4Y.npy", "labels": "/m/01d3sd,/m/09x0r", "caption": "A person snores while people communicate" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YWqXFAY4k79s.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YWqXFAY4k79s.npy", "labels": "/m/06mb1,/t/dd00038", "caption": "A person coughs with rain noise in the background, and a woman speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part9/Y8F-ndyrEWJ8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y8F-ndyrEWJ8.npy", "labels": "/m/012n7d,/m/03j1ly,/m/03kmc9", "caption": "Car is speeding down road, emergency siren is sounding, and a man speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/Yek9Fsmm3xqk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yek9Fsmm3xqk.npy", "labels": "/m/019jd,/m/03m9d0z,/m/056ks2,/m/07yv9", "caption": "Water splashing and trickling as wind blows into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YXJba7pTbpD0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YXJba7pTbpD0.npy", "labels": "/m/07qlf79", "caption": "Air spraying followed by fire igniting then audio static proceeded by pressurized air releasing before softly hissing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part1/Y0On6-JiVwRs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y0On6-JiVwRs.npy", "labels": "/m/01yrx,/m/068hy,/m/09t49,/m/0jbk,/t/dd00128", "caption": "Cat meowing sadly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/Yd6gu2w19YQo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yd6gu2w19YQo.npy", "labels": "/m/01j3sz", "caption": "A baby laughs repetitively" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YOVQMFBeCHq0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YOVQMFBeCHq0.npy", "labels": "/m/012n7d,/m/03j1ly,/m/03kmc9", "caption": "Low frequency emergency siren going off followed by the siren slowing briefly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/Yo_3MDLl_aH0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yo_3MDLl_aH0.npy", "labels": "/m/032s66,/m/0_1c", "caption": "Large booming explosions" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YRdC8cviN6Bs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YRdC8cviN6Bs.npy", "labels": "/m/06mb1,/t/dd00038", "caption": "Rain falling followed by footsteps walking on grass then a vehicle door opening then closing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/YjYPU6aSDo88.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YjYPU6aSDo88.npy", "labels": "/m/014yck,/m/07yv9,/m/09x0r,/m/0k5j", "caption": "An airplane engine and then light talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YtwFypUcdgRc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YtwFypUcdgRc.npy", "labels": "/m/01bjv,/m/07yv9,/m/09x0r", "caption": "Wind blowing hard as people speak" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YOMGHnJV0l2U.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YOMGHnJV0l2U.npy", "labels": "/m/02p01q,/m/07pdjhy,/m/083vt", "caption": "Metal scrapping against a wooden surface followed by light sanding then metal scraping against a wooden surface" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part27/YaMhu5eMQAsI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YaMhu5eMQAsI.npy", "labels": "/m/07yv9,/m/0k5j,/t/dd00129", "caption": "Humming from a large engine" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/Yo7-X8DAToGc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yo7-X8DAToGc.npy", "labels": "/m/012f08,/m/07yv9,/m/0ltv,/t/dd00134", "caption": "A vehicle driving by with tires briefly skidding and accelerating then slowing down" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part9/Y83j4GgHXTLE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y83j4GgHXTLE.npy", "labels": "/m/01j3sz,/m/09x0r,/m/0ytgt,/t/dd00125", "caption": "People laugh followed by whispering and a child speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part1/Y0UJtGcoPYa0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y0UJtGcoPYa0.npy", "labels": "/m/07jdr,/m/07yv9,/m/0912c9,/t/dd00128", "caption": "A motor is humming and a loud horn is honked" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YXplKBvZaHXA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YXplKBvZaHXA.npy", "labels": "/m/04_sv,/m/07yv9,/m/09x0r,/t/dd00129", "caption": "A man talking as a motorbike engine revs and accelerates" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/YzwoqJY03yHE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YzwoqJY03yHE.npy", "labels": "/m/03fwl,/m/068hy,/m/09x0r,/m/0jbk", "caption": "Women speak and a goat bleats" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YrINmxSXMR-s.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YrINmxSXMR-s.npy", "labels": "/m/07qdb04,/m/09ddx,/m/0jbk", "caption": "Water splashes then a duck quacks then a person laughs" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YWLzzpzOKtnY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YWLzzpzOKtnY.npy", "labels": "/m/01h3n,/m/09x0r", "caption": "Two men communicating with each other as an insect buzzes by while wind blows into a microphone and birds chirping in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YmGa2JgAiKV8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YmGa2JgAiKV8.npy", "labels": "/m/07pqc89,/m/09x0r", "caption": "A young boy talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/Yeu5bq0A3XVQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yeu5bq0A3XVQ.npy", "labels": "/m/03q5_w,/m/09x0r", "caption": "Burping and a man speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YZ0IrCa4MvOA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YZ0IrCa4MvOA.npy", "labels": "/m/0130jx,/m/02jz0l,/m/07pqc89,/m/0838f", "caption": "A stream of water trickling followed by water pouring down a drain" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part24/YV4PLSw_WzVw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YV4PLSw_WzVw.npy", "labels": "/m/07r04,/m/07rknqz,/m/07yv9", "caption": "A vehicle engine revving as tires skid and squeal" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/Ynq0BF9zGkzg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ynq0BF9zGkzg.npy", "labels": "/m/09x0r,/t/dd00018", "caption": "A low slow scream then a crash then birds chirping and men speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part7/Y5rh5-MCjqq8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y5rh5-MCjqq8.npy", "labels": "/m/01d3sd", "caption": "A brief loud snoring" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/Yj_NSuPnx5LA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yj_NSuPnx5LA.npy", "labels": "/m/07cx4", "caption": "Dialing phone followed by clack sound" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/YpuZL08fzpXk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YpuZL08fzpXk.npy", "labels": "/m/032s66,/m/04zjc", "caption": "Person talking as two different gunshot sounds are firing at a constant rhythmic rate where one is low like a bongo and the other is a rifle" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y2EsxcKe1A4w.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y2EsxcKe1A4w.npy", "labels": "/m/068hy,/m/07rc7d9,/m/09x0r,/m/0bt9lr,/m/0jbk", "caption": "A dog barking during camera muffling and footsteps shuffling on dirt followed by a man talking then a bicycle riding" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YEp72tyiL3as.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YEp72tyiL3as.npy", "labels": "/m/0ngt1", "caption": "A very loud thunder happened" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part27/Y_YS5uKWoB6g.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y_YS5uKWoB6g.npy", "labels": "/m/09x0r,/t/dd00002", "caption": "A baby cries as adults speak with clicking and banging of a car door" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/Ygbi6MxPf3hA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ygbi6MxPf3hA.npy", "labels": "/m/034srq,/m/03m9d0z,/m/05kq4,/t/dd00092", "caption": "Wind is mixed with a musical tone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part38/Yup2PpjTzyyc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yup2PpjTzyyc.npy", "labels": "/m/01yrx,/m/07qrkrw,/m/09x0r,/m/0jbk", "caption": "A man speaks with some quick meows and digital beeps" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YCwxgQS3SXic.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YCwxgQS3SXic.npy", "labels": "/m/0llzx", "caption": "Vibrations from a sewing machine" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YBoe3MeEpn_c.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBoe3MeEpn_c.npy", "labels": "/m/04brg2,/m/09x0r,/t/dd00125", "caption": "A man speaks with some faint banging and a few sprays" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3qrVku794u0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3qrVku794u0.npy", "labels": "/m/02fs_r,/m/09x0r,/m/0fx9l", "caption": "A man speaks followed by a beep and a child speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3ghVB-KaU_E.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3ghVB-KaU_E.npy", "labels": "/m/07rjwbb", "caption": "Cloth scrapping followed by cloth rubbing as a man is talking and compressed air hisses in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part15/YFhimNYClv40.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YFhimNYClv40.npy", "labels": "/m/012ndj,/m/03j1ly,/m/03kmc9", "caption": "Sirens and a humming engine approach and pass" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YXL8JV9qXGLE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YXL8JV9qXGLE.npy", "labels": "/m/0463cq4,/m/09x0r,/m/0ytgt,/t/dd00002,/t/dd00125", "caption": "An infant whimpering and distant speech and brief laughter" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YRrmBGjJqlEo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YRrmBGjJqlEo.npy", "labels": "/m/0316dw", "caption": "Clicking on a keyboard with a man speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part7/Y67BsqRkh-dU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y67BsqRkh-dU.npy", "labels": "/m/01jt3m,/m/0838f", "caption": "A toilet flushing water as music plays in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/YxQDq3A4Zfbo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YxQDq3A4Zfbo.npy", "labels": "/m/019jd,/m/034srq,/m/03m9d0z,/m/05kq4,/m/0hsrw,/t/dd00092", "caption": "Water splashes and wind blows" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YtNxfdAd14qE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YtNxfdAd14qE.npy", "labels": "/m/07p9k1k", "caption": "Sizzle sound with clicking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part9/Y8nUqSYC66mI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y8nUqSYC66mI.npy", "labels": "/m/0j6m2", "caption": "People are shouting, laughing and clapping, water is rushing and splashing, and an adult male speaks and laughs in the foreground" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y0yxEvdnimGg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y0yxEvdnimGg.npy", "labels": "/m/068hy,/m/07rc7d9,/m/09x0r,/m/0bt9lr,/m/0jbk", "caption": "Barks of distant dogs with men speaking and wind blowing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YE9zN3-C64KE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YE9zN3-C64KE.npy", "labels": "/m/09x0r,/t/dd00018", "caption": "A woman talking before and after a pig oinking then cloth rustling followed by camera muffling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4_DjmCg8Ra8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4_DjmCg8Ra8.npy", "labels": "/m/032s66,/m/0_1c", "caption": "Artillery guns fire followed by a man yelling as someone whistles while gunshots fire and a group of men shout in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part9/Y8Zo30kV5aiI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y8Zo30kV5aiI.npy", "labels": "/m/012n7d,/m/03j1ly,/m/03kmc9", "caption": "Emergency vehicle siren passing by then fading" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YBZCEDkx37rI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBZCEDkx37rI.npy", "labels": "/m/02mk9,/m/07pb8fc,/t/dd00066,/t/dd00130", "caption": "Humming of an idling engine" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YBz9Y5nZK3eo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBz9Y5nZK3eo.npy", "labels": "/m/01m2v,/m/0316dw", "caption": "Typing on a keyboard" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part0/Y-SkjbQVgJ0M.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y-SkjbQVgJ0M.npy", "labels": "/m/07yv9,/m/09x0r,/m/0k4j,/t/dd00134", "caption": "A car passes by shortly after a man starts talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YKtinboYbmHQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YKtinboYbmHQ.npy", "labels": "/m/07rknqz,/m/07yv9,/m/0h9mv,/m/0k4j", "caption": "Tires skidding and squealing as a vehicle engine accelerates and revs several times" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YNmmbNqmsPaY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YNmmbNqmsPaY.npy", "labels": "/m/07pb8fc,/m/07yv9,/m/0k4j", "caption": "A car engine idling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YDNtF_mGzQes.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YDNtF_mGzQes.npy", "labels": "/m/07r04,/m/07yv9,/m/09x0r", "caption": "A man speaks over a loudspeaker as people speak and an engine hums" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part0/Y--0w1YA1Hm4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y--0w1YA1Hm4.npy", "labels": "/m/01bjv,/m/07yv9,/m/09x0r", "caption": "Men speak and laugh with humming of an engine" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part0/Y-DmjkgWa-rw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y-DmjkgWa-rw.npy", "labels": "/m/0395lw", "caption": "Large church bells ring" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YsqsI2UyrcBQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YsqsI2UyrcBQ.npy", "labels": "/m/07q2z82,/m/07yv9,/m/0k4j", "caption": "A vehicle engine revving then slowing down before revving again" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/YcN-oYKd-M4E.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YcN-oYKd-M4E.npy", "labels": "/m/07bgp,/m/0ch8v,/m/0jbk", "caption": "Sheep baaing followed by plastic thumping as birds chirp in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/Yhmd6pa2e_rs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yhmd6pa2e_rs.npy", "labels": "/m/01bjv,/m/07yv9,/m/09x0r", "caption": "A large motor vehicle engine is running and accelerates, and an adult male speaks in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YCbe2B6ohBpw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YCbe2B6ohBpw.npy", "labels": "/m/015p6,/m/068hy,/m/09ddx,/m/0ch8v,/m/0dbvp,/m/0jbk", "caption": "Ducks quack with blowing wind and faint splashes" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y41D0yXSBqfI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y41D0yXSBqfI.npy", "labels": "/m/015p6,/m/0h0rv,/t/dd00125", "caption": "Pigeons cooing and bird wings flapping while gravel shuffles and wood clacks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y1slvoNgzBLE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1slvoNgzBLE.npy", "labels": "/m/01g50p,/m/06d_3,/m/07jdr,/m/07yv9,/m/0912c9", "caption": "An electronic signal followed by compressed air releasing then an electronic bell playing as a train runs on tracks in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part19/YN_s9F4CI_98.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YN_s9F4CI_98.npy", "labels": "/m/015p6,/m/020bb7,/m/07r_25d,/m/0h0rv", "caption": "Pigeons cooing followed by bird wings flapping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3XuyGJqaXv8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3XuyGJqaXv8.npy", "labels": "/m/068hy,/m/07rc7d9,/m/09x0r,/m/0bt9lr,/m/0jbk", "caption": "A man speaks over an intercom as crowd of people talking in the background followed by a dog barking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9vZDsGjyh5M.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9vZDsGjyh5M.npy", "labels": "/m/07r04,/m/07yv9,/m/0k4j", "caption": "An idle vehicle engine running" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part9/Y8o-Y4QP8LWs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y8o-Y4QP8LWs.npy", "labels": "/m/023pjk,/m/04brg2", "caption": "An adult male speaks, after which clattering, thumping, metal pinging and a whistle occur, liquid splashes, and the adult male speaks again" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YOmmPaIAXN0s.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YOmmPaIAXN0s.npy", "labels": "/m/03k3r,/m/07rv9rh,/m/09x0r,/m/0jbk", "caption": "A man speaking continuously" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YOFVzrakJhbw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YOFVzrakJhbw.npy", "labels": "/m/068hy,/m/07bgp,/m/07q0h5t,/m/0jbk", "caption": "A woman laughing followed by a sheep baaing and wind blowing into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/Yc3nlaAkv9bA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yc3nlaAkv9bA.npy", "labels": "/m/03fwl,/m/068hy,/m/09x0r,/m/0ch8v,/m/0jbk", "caption": "A man speaking softly followed by a goat speaking then a cow mooing in the distance as birds chirp in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YOUUckswAaNI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YOUUckswAaNI.npy", "labels": "/m/02dgv", "caption": "Hammering and then a man speaks followed by rubbing and then a second man speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YTWOgvDaDqlU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YTWOgvDaDqlU.npy", "labels": "/m/083vt", "caption": "Machine grinding wood" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/YggN4-K5AgoM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YggN4-K5AgoM.npy", "labels": "/m/01jt3m,/m/0838f", "caption": "A toilet flushing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YlTJLvSvjUZk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YlTJLvSvjUZk.npy", "labels": "/m/01w250", "caption": "Whistling to music" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part19/YMVGhC-xB79s.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YMVGhC-xB79s.npy", "labels": "/m/015p6,/m/09x0r,/m/0h0rv,/t/dd00128", "caption": "A repeated whistling sound and a small child babbling, followed by a man talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3qTL7QRk-tg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3qTL7QRk-tg.npy", "labels": "/m/07swgks,/m/0j6m2", "caption": "Water running together with distant singing and brief clanking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part4/Y31WGUPOYS5g.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y31WGUPOYS5g.npy", "labels": "/m/012ndj,/m/03j1ly,/m/03kmc9", "caption": "The buzz of the crowd is interrupted by a child shouting, followed by a police siren and a horn honking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YrBUCIK8JRLg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YrBUCIK8JRLg.npy", "labels": "/m/034srq,/m/03m9d0z,/m/05kq4,/t/dd00092", "caption": "White noise followed by some rustling and splashing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part1/Y-oy0BkpMGAk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y-oy0BkpMGAk.npy", "labels": "/m/012f08,/m/07rknqz,/m/07yv9,/m/0k4j,/t/dd00134", "caption": "Revving of an engine and a skidding sound" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/YyLu4b01t53k.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YyLu4b01t53k.npy", "labels": "/m/012f08,/m/07pb8fc,/m/07yv9", "caption": "The loud idling of a machine" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YBQ-r9mEHssU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBQ-r9mEHssU.npy", "labels": "/m/03k3r,/m/07rv9rh,/m/09x0r,/m/0jbk", "caption": "A woman laughs then talks as horse breaths and gallops on grass" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/YggN4-K5AgoM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YggN4-K5AgoM.npy", "labels": "/m/01jt3m,/m/0838f", "caption": "Metal clanking followed by a toilet flushing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YWq4OD3olO2w.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YWq4OD3olO2w.npy", "labels": "/m/07r660_,/m/09x0r,/m/0ytgt,/t/dd00125", "caption": "Speech and laughter followed by more speech and hollering" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YWHRnyGXcdy8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YWHRnyGXcdy8.npy", "labels": "/t/dd00002", "caption": "A baby crying loudly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4sb9jN0SgTM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4sb9jN0SgTM.npy", "labels": "/m/02mk9,/m/07pb8fc,/m/07q2z82,/m/07yv9,/m/09x0r,/m/0k4j,/t/dd00066", "caption": "A motor vehicle engine runs and revs, then it stops and an adult male speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part19/YMOxddxW5PXs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YMOxddxW5PXs.npy", "labels": "/m/09x0r,/m/0dxrf", "caption": "Male voice speaking and sizzling of food cooking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YbLZFtoWXYTA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YbLZFtoWXYTA.npy", "labels": "/m/02jz0l", "caption": "Tap water is running followed by a tapping noise" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part7/Y5rh5-MCjqq8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y5rh5-MCjqq8.npy", "labels": "/m/01d3sd", "caption": "A person snoring as plastic repeatedly taps the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3qrVku794u0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3qrVku794u0.npy", "labels": "/m/02fs_r,/m/09x0r,/m/0fx9l", "caption": "An appliance motor is running and obvious vibration and knocking are occurring, and an adult male and a child speak and the vibration continues, followed by an electronic beep" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YDAN1t9ukkg0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YDAN1t9ukkg0.npy", "labels": "/m/01m2v,/m/0316dw", "caption": "Typing is occurring on a keyboard in a quiet environment" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/YcNARVD02-tw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YcNARVD02-tw.npy", "labels": "/m/02jz0l,/m/09x0r", "caption": "A man and an elderly woman talking as plastic clacks followed by a faucet pouring water as water runs down a drain" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YQARuiRtfy-k.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YQARuiRtfy-k.npy", "labels": "/m/01d380", "caption": "A power tool drilling followed by someone blows air then a man talking as rock music plays in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/YdlsiellSFf0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YdlsiellSFf0.npy", "labels": "/m/019jd,/m/02rlv9,/m/07yv9", "caption": "A high frequency motor hums loudly and splashes water" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YK03ydb1uaoQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YK03ydb1uaoQ.npy", "labels": "/m/01d3sd,/t/dd00125", "caption": "Loud snoring repeating" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part9/Y7upINC4seBw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y7upINC4seBw.npy", "labels": "/m/019jd,/m/02rlv9,/m/07yv9,/m/09x0r", "caption": "An idle motorboat engine running as a man is speaking while wind blows into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/YhFCmq9pCBbM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YhFCmq9pCBbM.npy", "labels": "/m/09x0r,/t/dd00112", "caption": "A girl speaking with plastic crinkling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part9/Y8IdCiapDYCU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y8IdCiapDYCU.npy", "labels": "/m/068hy,/m/07rc7d9,/m/0bt9lr,/m/0jbk", "caption": "A few electronic-sounding animal noises followed by barking from a small dog" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part19/YNX0gR9Eebp0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YNX0gR9Eebp0.npy", "labels": "/m/03dnzn,/m/09x0r,/m/0ytgt", "caption": "A child speaking as water trickles and splashes followed by a woman moaning" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part4/Y2t82STv2GR8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y2t82STv2GR8.npy", "labels": "/m/0395lw", "caption": "Chiming of loud bells" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/Yt3VFlDiEKgY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yt3VFlDiEKgY.npy", "labels": "/m/03vt0,/m/09f96,/m/0h2mp", "caption": "A mosquito is buzzing and continues to do so as a man starts to talk" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part15/YGMP8m09j5vk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YGMP8m09j5vk.npy", "labels": "/m/015p6,/m/020bb7,/m/07pggtn", "caption": "Birds call while another bird sings" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y8ycflE3dIHw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y8ycflE3dIHw.npy", "labels": "/m/01g50p,/m/0284vy3,/m/06d_3,/m/07jdr,/m/07rwm0c", "caption": "Train passing followed by short honk" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/Yc0V_HAul7rI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yc0V_HAul7rI.npy", "labels": "/m/01j3sz,/m/07rgt08,/m/09x0r", "caption": "People laugh and speak" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YKtTLsveexOg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YKtTLsveexOg.npy", "labels": "/m/0llzx", "caption": "A sewing machine running as a heavy machine motor hums while sawing wood in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part19/YMVGhC-xB79s.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YMVGhC-xB79s.npy", "labels": "/m/015p6,/m/09x0r,/m/0h0rv,/t/dd00128", "caption": "Whistling is ongoing, a child speaks and an adult male speaks, birds coo, and rustling and soft metal clattering are occurring" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YalaxBd_EEUc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YalaxBd_EEUc.npy", "labels": "/m/03q5_w,/m/09x0r", "caption": "A man speaks briefly followed by a succession of several eructations" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YETb9EIQOMAA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YETb9EIQOMAA.npy", "labels": "/m/02qldy,/m/02zsn,/m/09x0r", "caption": "A woman giving a speech" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/YzIgGMlZENTs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YzIgGMlZENTs.npy", "labels": "/m/07qdb04,/m/09ddx,/m/09x0r", "caption": "Ducks quack and a man speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y13CBvjHZhOA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y13CBvjHZhOA.npy", "labels": "/m/012f08,/m/07yv9,/m/0k4j,/t/dd00134", "caption": "A vehicle engine running idle as a series of plastic and metal clacks while race vehicles drive by" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YF-47fRplQEc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YF-47fRplQEc.npy", "labels": "/m/07bgp,/m/07q0h5t,/m/09x0r", "caption": "Three young ladies' speech while sheep bleats" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part27/Y_YS5uKWoB6g.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y_YS5uKWoB6g.npy", "labels": "/m/09x0r,/t/dd00002", "caption": "A kid crying as a man and woman talk while a vehicle door opens then closes" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/YhpDltmawxIM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YhpDltmawxIM.npy", "labels": "/m/0130jx,/m/02jz0l,/m/0838f", "caption": "Water pouring from a faucet onto a metal surface and filling a glass container" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YEYTz1LPDHsc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YEYTz1LPDHsc.npy", "labels": "/m/02dgv", "caption": "A car door opening as a crow caws and birds chirp followed by a vehicle driving by in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9z2OwpftxUE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9z2OwpftxUE.npy", "labels": "/m/0ngt1", "caption": "Heavy wind and thunder" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part27/Y_GI7meqlYZk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y_GI7meqlYZk.npy", "labels": "/m/01yrx,/m/068hy,/m/07qrkrw,/m/09x0r,/m/0jbk", "caption": "A cat screaming then meowing as a young boy is talking during a series of electronic buzzing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YK-7Y8yhcUiw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YK-7Y8yhcUiw.npy", "labels": "/m/01d3sd,/m/068hy,/m/0bt9lr,/m/0jbk", "caption": "An animal snores" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/Yo7jW6Suyfbs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yo7jW6Suyfbs.npy", "labels": "/m/012f08,/m/07yv9,/m/0k4j,/m/0ltv", "caption": "Race car revving its engine" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YlTJLvSvjUZk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YlTJLvSvjUZk.npy", "labels": "/m/01w250", "caption": "A person whistling while drums play" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/Ym8wV38lf2jg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ym8wV38lf2jg.npy", "labels": "/m/03j1ly,/m/03kmc9,/m/04qvtq,/m/07yv9,/m/09x0r,/m/0k4j", "caption": "Emergency vehicle sirens are ongoing, and two adult males speak" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YB8rdur4aams.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YB8rdur4aams.npy", "labels": "/m/07yv9,/m/0912c9,/t/dd00128", "caption": "Rattling and humming with a horn echoing and wind blowing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/YfK4QBQZ6i7w.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YfK4QBQZ6i7w.npy", "labels": "/m/01j3sz,/m/07rgt08,/m/07s04w4", "caption": "A hissing sound followed by laughter" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YszkiW0GXEOI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YszkiW0GXEOI.npy", "labels": "/m/015p6,/m/01w250", "caption": "Whistling with birds chirping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YkgjNIDmO8a8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YkgjNIDmO8a8.npy", "labels": "/m/012ndj,/m/03j1ly,/m/03kmc9", "caption": "Sirens ring and traffic passes as people speak" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/Ym8wV38lf2jg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ym8wV38lf2jg.npy", "labels": "/m/03j1ly,/m/03kmc9,/m/04qvtq,/m/07yv9,/m/09x0r,/m/0k4j", "caption": "Emergency sirens and muffled speech" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YmJ6ZO3xEcgw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YmJ6ZO3xEcgw.npy", "labels": "/m/01hsr_", "caption": "A woman sneezing repeatedly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YRNBoH2LHQEM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YRNBoH2LHQEM.npy", "labels": "/m/028ght", "caption": "A crowd of people applauding" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/YjjHIINDfE1c.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YjjHIINDfE1c.npy", "labels": "/m/07yv9,/m/0912c9,/t/dd00129", "caption": "A tractor driving by as a car horn honks while wind blows into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YBXxlqaDvdaA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBXxlqaDvdaA.npy", "labels": "/m/05kq4,/m/07yv9,/m/09x0r,/m/0hsrw,/m/0j6m2", "caption": "Wind blowing and water splashing as a man speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part27/Y_z6pymOet7g.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y_z6pymOet7g.npy", "labels": "/m/01jt3m,/m/09x0r", "caption": "A man talking followed by a toilet flushing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YWCYfCfW9NA0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YWCYfCfW9NA0.npy", "labels": "/m/07yv9,/m/09ct_,/t/dd00129", "caption": "High pitched humming with whooshes of spinning helicopter blades" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part24/YUjje3lSabsg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YUjje3lSabsg.npy", "labels": "/m/01d3sd", "caption": "A very light snoring" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YHxZADVzNIqs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YHxZADVzNIqs.npy", "labels": "/m/015p6,/m/020bb7,/m/07pggtn", "caption": "Birds chirping and water dripping with some banging in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YDjKGzOe_COc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YDjKGzOe_COc.npy", "labels": "/m/02qldy,/m/02zsn,/m/09x0r", "caption": "A woman is performing a speech" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/YzwoqJY03yHE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YzwoqJY03yHE.npy", "labels": "/m/03fwl,/m/068hy,/m/09x0r,/m/0jbk", "caption": "Two women talking then laughing as fabric shuffles followed by a goat baaing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part15/YH7rd9bZtbgc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YH7rd9bZtbgc.npy", "labels": "/m/0395lw", "caption": "A bell sounds the horn" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YmUGmCSNETcg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YmUGmCSNETcg.npy", "labels": "/m/07ptfmf,/m/0dxrf", "caption": "Women talk while food fries" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part15/YGOD8Bt5LfDE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YGOD8Bt5LfDE.npy", "labels": "/m/07jdr,/m/09x0r,/m/0ytgt", "caption": "Small child speaking and a train running followed by a woman speaking and laughter" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/Yjf4iyQPJSvk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yjf4iyQPJSvk.npy", "labels": "/m/07pqc89,/m/0838f,/m/0j2kx,/t/dd00129", "caption": "Water flowing and trickling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part38/YvaujJ7msKfc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YvaujJ7msKfc.npy", "labels": "/m/012n7d,/m/03j1ly,/m/03kmc9", "caption": "Light music playing in the background during city ambiance followed by police sirens sounding in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YHdPSebdDxe4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YHdPSebdDxe4.npy", "labels": "/m/03q5_w", "caption": "Man speaks followed by buzzing and then a loud burp" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/YxQDq3A4Zfbo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YxQDq3A4Zfbo.npy", "labels": "/m/019jd,/m/034srq,/m/03m9d0z,/m/05kq4,/m/0hsrw,/t/dd00092", "caption": "Water splashing and wind blowing hard" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/YemGPabOePzA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YemGPabOePzA.npy", "labels": "/m/03q5_w,/m/09x0r", "caption": "Laughing and speech in a slowed speed" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YmGa2JgAiKV8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YmGa2JgAiKV8.npy", "labels": "/m/07pqc89,/m/09x0r", "caption": "Young man speaking with slight movement sounds" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/YyhDw7PZje3g.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YyhDw7PZje3g.npy", "labels": "/m/01h3n,/m/09x0r,/t/dd00129", "caption": "Many insects are buzzing, and an adult male speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/Yzq00Oe1ecpE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yzq00Oe1ecpE.npy", "labels": "/m/012f08,/m/01bjv,/m/07yv9", "caption": "A bus engine slowing down then accelerating" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YPZBUdlKwX04.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YPZBUdlKwX04.npy", "labels": "/m/09x0r,/m/0j2kx,/m/0j6m2", "caption": "Water splashes and a man speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YItS07xtdi4s.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YItS07xtdi4s.npy", "labels": "/m/07qsvvw,/m/09x0r", "caption": "Popping along with swooshing occur then a bonging" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YWqXFAY4k79s.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YWqXFAY4k79s.npy", "labels": "/m/06mb1,/t/dd00038", "caption": "A person laughing followed by a girl shouting as rain is falling on a plastic surface" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y2EsxcKe1A4w.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y2EsxcKe1A4w.npy", "labels": "/m/068hy,/m/07rc7d9,/m/09x0r,/m/0bt9lr,/m/0jbk", "caption": "A large dog barks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part38/Yv59uHr-B1no.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yv59uHr-B1no.npy", "labels": "/m/09ld4", "caption": "Frogs and crickets chirping during nature ambiance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YrjUrB1WUpcI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YrjUrB1WUpcI.npy", "labels": "/m/07swgks", "caption": "Water drains with gurgling noise" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part19/YMdlEswBfZMQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YMdlEswBfZMQ.npy", "labels": "/m/07rgt08,/m/09x0r,/m/0ytgt,/t/dd00125", "caption": "One toddler crying with several others laughing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part38/YvruDH_YLaPI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YvruDH_YLaPI.npy", "labels": "/m/032s66", "caption": "Several loud gunshots" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/YhGWarNR6xmg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YhGWarNR6xmg.npy", "labels": "/m/06wzb,/m/07rjwbb", "caption": "Repetitive loud hissing with some static" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part27/Y_z-bidQYVao.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y_z-bidQYVao.npy", "labels": "/m/07qjznl,/m/09x0r", "caption": "A faint siren followed by a man speaking and wooing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/YpuZL08fzpXk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YpuZL08fzpXk.npy", "labels": "/m/032s66,/m/04zjc", "caption": "Gunshots followed by people speaking and explosions" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part7/Y6OlHuvJR_Dk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y6OlHuvJR_Dk.npy", "labels": "/m/07yv9,/m/09ct_", "caption": "A helicopter flies with loud chopping noises" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3wV3ST-c4PE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3wV3ST-c4PE.npy", "labels": "/m/07qjznl", "caption": "Rhythmic ticking is occurring" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part27/Y_oKXrY5Ff0g.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y_oKXrY5Ff0g.npy", "labels": "/m/01j3sz,/m/09x0r", "caption": "An adult female speaks and several people laugh, while slight rustling occurs in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part7/Y5xC4hkAWiao.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y5xC4hkAWiao.npy", "labels": "/m/012f08,/m/02mk9,/m/07yv9", "caption": "A large motor vehicle engine is idling, then it labors and creaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/YoOMtaqvQ3_M.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YoOMtaqvQ3_M.npy", "labels": "/m/07yv9,/m/09ct_,/m/0k5j", "caption": "An engine running consistently with heavy wind" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part9/Y8b9z7N25DmU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y8b9z7N25DmU.npy", "labels": "/m/01bjv,/m/07yv9,/m/09x0r,/t/dd00129", "caption": "Bus coming to a stop and door opening" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/Yj0KvrVE_Oww.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yj0KvrVE_Oww.npy", "labels": "/m/0912c9,/m/09x0r,/t/dd00125", "caption": "A man speaks and then a horn blows." }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9xoYx3lTJ9I.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9xoYx3lTJ9I.npy", "labels": "/m/019jd,/m/02rlv9,/m/03m9d0z,/t/dd00092", "caption": "Wind noise while a water vehicle is traveling across water, and a man talks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/Ylq9RvAA4mqY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ylq9RvAA4mqY.npy", "labels": "/m/07ptfmf,/m/0dxrf", "caption": "A man talking and metal clanking as food and oil sizzle" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YLF6x7B0Ppvo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YLF6x7B0Ppvo.npy", "labels": "/m/07yv9,/m/0k4j,/m/0ltv", "caption": "A racing car is driving fast" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part4/Y2j8pxiFvElM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y2j8pxiFvElM.npy", "labels": "/m/01yrx,/m/068hy,/m/07qrkrw,/m/0jbk", "caption": "A cat meowing twice" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y6dLkgq9EKPE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y6dLkgq9EKPE.npy", "labels": "/m/01bjv,/m/07yv9,/m/09x0r", "caption": "A man talking followed by plastic clacking and a woman speaking as steam hisses while a bus engine runs idle in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YJZloTOdIY_c.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YJZloTOdIY_c.npy", "labels": "/m/03k3r,/m/07q5rw0,/m/07rv9rh,/m/0jbk", "caption": "A horse neighs followed by horse trotting and snorting" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part27/YaMhu5eMQAsI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YaMhu5eMQAsI.npy", "labels": "/m/07yv9,/m/0k5j,/t/dd00129", "caption": "Aircraft engine with wind blowing hard" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part19/YMSziND26UTA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YMSziND26UTA.npy", "labels": "/m/01h3n,/m/03vt0,/m/0h2mp", "caption": "Bees buzzing and then a rooster crowing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YZ3wDry8nnJs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YZ3wDry8nnJs.npy", "labels": "/m/09x0r,/m/0ytgt,/t/dd00125", "caption": "A girl speaking and brushing teeth" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YJnSwRonB9wI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YJnSwRonB9wI.npy", "labels": "/m/019jd,/m/02rlv9,/m/034srq,/m/05kq4", "caption": "Several people screaming and laughing with a humming engine and splashing waves" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9z8XIRyUq9Q.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9z8XIRyUq9Q.npy", "labels": "/m/02qldy,/m/02zsn,/m/09x0r", "caption": "A woman performs a speech" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/YzwoqJY03yHE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YzwoqJY03yHE.npy", "labels": "/m/03fwl,/m/068hy,/m/09x0r,/m/0jbk", "caption": "A woman speaking followed by another woman talking followed by a goat baaing as cloth rustles" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y0yETgW44MZU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y0yETgW44MZU.npy", "labels": "/m/01g50p,/m/0284vy3,/m/04zmvq,/m/06d_3,/m/07jdr,/m/07yv9,/t/dd00129", "caption": "A train sounds horn while the engine taps" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YkLYCjD6vWI4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YkLYCjD6vWI4.npy", "labels": "/m/06wzb,/m/07rjwbb", "caption": "Wind blowing with loud puffs of air and hissing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/YdJYO3RbBabE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YdJYO3RbBabE.npy", "labels": "/m/02fs_r", "caption": "A digital beep followed by a man speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y7RMpCCkQks0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y7RMpCCkQks0.npy", "labels": "/m/07rjwbb", "caption": "Velcro scrapping off fabric followed as an air ventilation system hums in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YnuZEAuAl8hQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YnuZEAuAl8hQ.npy", "labels": "/m/015p6,/m/09ddx,/m/0ch8v", "caption": "A duck quacking as wind lightly blows and water splats in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YsVYTOURVsQ0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YsVYTOURVsQ0.npy", "labels": "/m/07pqc89,/m/09x0r", "caption": "A man talking as water streams in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YBwnGxJD9xh8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBwnGxJD9xh8.npy", "labels": "/m/03fwl,/m/068hy,/m/07bgp,/m/0jbk", "caption": "A man talking followed by a goat baaing as gusts of wind blow and birds chirp in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part24/YUmNrhFKpWIY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YUmNrhFKpWIY.npy", "labels": "/m/07q2z82,/m/07yv9,/m/0k4j", "caption": "A vehicle engine revving then turning off" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9E8BmPZ9mWc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9E8BmPZ9mWc.npy", "labels": "/m/07r04,/m/07yv9,/m/09x0r", "caption": "A truck engine is running with people talking in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YlgwpIImXCWA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YlgwpIImXCWA.npy", "labels": "/m/083vt,/m/09x0r,/t/dd00125", "caption": "Man speaking while sawing something" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y7P0N61TVOxE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y7P0N61TVOxE.npy", "labels": "/m/034srq,/m/03m9d0z,/m/05kq4,/m/085jw", "caption": "A motorboat engine running as water splashes then fades out followed by glasses clanking as a group of people talk and woodwind instruments play" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part9/Y7upINC4seBw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y7upINC4seBw.npy", "labels": "/m/019jd,/m/02rlv9,/m/07yv9,/m/09x0r", "caption": "A man speaks along with a running boat and wind blowing by and water splashing quietly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YKSHpYhuTotY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YKSHpYhuTotY.npy", "labels": "/m/01h3n,/m/03vt0,/m/0h2mp", "caption": "Insects buzz and men speak" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/Yj_NSuPnx5LA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yj_NSuPnx5LA.npy", "labels": "/m/07cx4", "caption": "Electronic touch tone telephone dialing occurs, followed by thumping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4YMXgLFcR94.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4YMXgLFcR94.npy", "labels": "/m/02qldy,/m/05zppz,/m/09x0r", "caption": "An adult male speaks, with his voice amplified, after which crowd of people clap" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/YjjfUaMQaG1A.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YjjfUaMQaG1A.npy", "labels": "/m/01d380,/m/09x0r", "caption": "A male speaking and then a drill turned on and off." }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YbQNX7vDalQw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YbQNX7vDalQw.npy", "labels": "/m/07p9k1k", "caption": "Male speech and then sizzling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YNwoBDrTlbTI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YNwoBDrTlbTI.npy", "labels": "/t/dd00018", "caption": "A gerbil squeaking during audio static" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YkEP-BwMarf8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YkEP-BwMarf8.npy", "labels": "/m/09x0r,/t/dd00112", "caption": "A wrapper crinkling and a woman's soft voice" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/Ybgbnu5YKTDg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ybgbnu5YKTDg.npy", "labels": "/m/032s66", "caption": "A male speech and then repeated gunfire followed by a male speech." }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/Ys_EWjoiVfzo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ys_EWjoiVfzo.npy", "labels": "/m/0llzx", "caption": "A sewing machine operating several times followed by metal clanking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YJfaj4P3us9M.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YJfaj4P3us9M.npy", "labels": "/m/02c8p,/m/07cx4", "caption": "A telephone dialing tone beeping as a plastic switch flip on and off" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4YMXgLFcR94.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4YMXgLFcR94.npy", "labels": "/m/02qldy,/m/05zppz,/m/09x0r", "caption": "A man speaks and then an audience claps" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part15/YFhimNYClv40.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YFhimNYClv40.npy", "labels": "/m/012ndj,/m/03j1ly,/m/03kmc9", "caption": "An emergency vehicle horn honking as a large truck accelerates and drives by" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/Yjj2RyNDj7no.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yjj2RyNDj7no.npy", "labels": "/m/01h3n,/m/03vt0,/m/0h2mp", "caption": "A man talking softly as insects buzz by while birds chirp in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YTwR8BA6buMI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YTwR8BA6buMI.npy", "labels": "/m/07qjznl", "caption": "A clock ticking as a piano note is playing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YnU-AI3Cmc3M.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YnU-AI3Cmc3M.npy", "labels": "/m/015p6,/m/0h0rv,/t/dd00129", "caption": "Pigeons coo and flap their wings" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YETb9EIQOMAA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YETb9EIQOMAA.npy", "labels": "/m/02qldy,/m/02zsn,/m/09x0r", "caption": "A woman speaking on a microphone as a crowd of people talk in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YE3Q1jfTeuWs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YE3Q1jfTeuWs.npy", "labels": "/t/dd00002", "caption": "A baby cries followed by rustling and heavy breathing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YnLZeG9LaLgw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YnLZeG9LaLgw.npy", "labels": "/m/07yv9,/m/0k4j,/m/0ltv", "caption": "Loud humming of a car speeding into the distance with wind blowing and tires squealing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part38/Yv59uHr-B1no.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yv59uHr-B1no.npy", "labels": "/m/09ld4", "caption": "Frogs and crickets chirping and croaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/YzIgGMlZENTs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YzIgGMlZENTs.npy", "labels": "/m/07qdb04,/m/09ddx,/m/09x0r", "caption": "Several quacks of a duck are followed by a man speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/Yrp3CQsWxVgE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yrp3CQsWxVgE.npy", "labels": "/m/07yv9,/m/0912c9,/m/0k4j,/t/dd00128", "caption": "A vehicle horn blares out a musical tune" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part38/YvaujJ7msKfc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YvaujJ7msKfc.npy", "labels": "/m/012n7d,/m/03j1ly,/m/03kmc9", "caption": "Wind blowing with distant traffic passing and sirens ringing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YF-47fRplQEc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YF-47fRplQEc.npy", "labels": "/m/07bgp,/m/07q0h5t,/m/09x0r", "caption": "A woman talking as a sheep baa and birds are cawing in the background followed by a woman speaking in the foreground then another woman and kid talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YTtRtURWVYBE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YTtRtURWVYBE.npy", "labels": "/m/0395lw", "caption": "Bells chime and ring" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YF7QtqKtllK0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YF7QtqKtllK0.npy", "labels": "/m/01d3sd", "caption": "A person snoring followed by a man exhaling loudly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YOVQMFBeCHq0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YOVQMFBeCHq0.npy", "labels": "/m/012n7d,/m/03j1ly,/m/03kmc9", "caption": "Sirens ring and vehicles pass on a wet road" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YRtenf2XSXRc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YRtenf2XSXRc.npy", "labels": "/m/07q2z82,/m/07yv9,/m/0k4j", "caption": "A car idling and revving" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9F3sutgYTvo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9F3sutgYTvo.npy", "labels": "/m/09x0r,/t/dd00002", "caption": "A man talks loudly followed by a baby crying and female voice laughing and talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YLWng-4PDzPM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YLWng-4PDzPM.npy", "labels": "/m/01w250", "caption": "Orchestral music playing followed by heavy fabric thumping then a person whistling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part15/YGGgQR7aIofY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YGGgQR7aIofY.npy", "labels": "/m/012f08,/m/01bjv,/m/07yv9", "caption": "A horn beeps a tune, and a large motor vehicle engine is running and gets louder" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YHkbCUN4V3TU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YHkbCUN4V3TU.npy", "labels": "/m/09x0r,/m/0ytgt,/t/dd00125", "caption": "A woman talking then laughing followed by wood thumping as a young kid screams" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YniwgMbB6tpQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YniwgMbB6tpQ.npy", "labels": "/m/01d3sd", "caption": "High pitched snoring occurs repeatedly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y2ABngPM3raQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y2ABngPM3raQ.npy", "labels": "/m/09ld4,/m/09x0r,/m/0jbk", "caption": "A man talking while bongos play followed by frogs croaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part38/Yu84FiZ_omhA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yu84FiZ_omhA.npy", "labels": "/m/015p6,/m/07pggtn,/m/0jbk", "caption": "A woman singing then choking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3ndid3jni7M.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3ndid3jni7M.npy", "labels": "/m/01g50p,/m/0284vy3,/m/06d_3,/m/07jdr,/m/07rwm0c", "caption": "A loud horn honking followed by a bell ringing together with clickety-clacking train passing by" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part27/Y_ezm-TpKj1w.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y_ezm-TpKj1w.npy", "labels": "/m/07q2z82,/m/09x0r,/m/0k4j", "caption": "A vehicle engine revving several times as a crowd of people talk" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/YxpZna_FwDhI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YxpZna_FwDhI.npy", "labels": "/m/09x0r,/m/0llzx", "caption": "Woman speaks and then sewing machine stitches" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/Yir1XTdyt4IY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yir1XTdyt4IY.npy", "labels": "/m/014zdl,/m/07qsvvw,/m/09x0r", "caption": "Released air hissing followed by a popping explosion then a metal ding persists as a person is laughing and a man is talking." }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3ue0gJM0THk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3ue0gJM0THk.npy", "labels": "/m/02l6bg,/m/02mk9,/m/07pb8fc,/m/07q2z82,/t/dd00066", "caption": "A power tool motor running then revving" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/Yo7jW6Suyfbs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yo7jW6Suyfbs.npy", "labels": "/m/012f08,/m/07yv9,/m/0k4j,/m/0ltv", "caption": "Humming of powerful engines" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YIdBDl9Wr51A.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YIdBDl9Wr51A.npy", "labels": "/m/07rqsjt", "caption": "Electronic laser blasts and explosions followed by a deep-voiced man talking while a man commentates followed by a woman chuckling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YrbO727iF03I.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YrbO727iF03I.npy", "labels": "/m/03q5_w,/m/09x0r", "caption": "A person belching followed by two men talking then a group of people laughing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part7/Y6Pywt0f_NFY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y6Pywt0f_NFY.npy", "labels": "/m/02jz0l,/m/03dnzn,/m/0838f", "caption": "Water trickling as a machine hums in the background followed by water spraying" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part27/Y_9mgOkzm-xg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y_9mgOkzm-xg.npy", "labels": "/m/09x0r,/m/0dxrf,/t/dd00125", "caption": "A man speaks as food sizzles with some banging and some cracking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YCO6-i8NLbeo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YCO6-i8NLbeo.npy", "labels": "/m/03fwl,/m/09x0r,/m/0jbk", "caption": "A man talking followed by a goat talking as a metal gate slides shut while ducks quack and wind blows into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/YemGPabOePzA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YemGPabOePzA.npy", "labels": "/m/03q5_w,/m/09x0r", "caption": "Laughter followed by slow speech" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y1vCYiVvZ7VE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1vCYiVvZ7VE.npy", "labels": "/m/02qldy,/m/02zsn,/m/09x0r", "caption": "A woman is giving a speech" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y1WTSW96XP6E.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1WTSW96XP6E.npy", "labels": "/m/04_sv,/m/07yv9,/m/09x0r", "caption": "A man is talking and a motorcycle engine is started" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y14ekd4nkpwc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y14ekd4nkpwc.npy", "labels": "/t/dd00002", "caption": "A baby is crying" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part7/Y5xC4hkAWiao.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y5xC4hkAWiao.npy", "labels": "/m/012f08,/m/02mk9,/m/07yv9", "caption": "A vehicle's engine starts to die down" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YEfk5kdn9lR8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YEfk5kdn9lR8.npy", "labels": "/m/02dgv,/m/02y_763,/m/09x0r", "caption": "Child talking then door crashing and her screaming" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YJZloTOdIY_c.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YJZloTOdIY_c.npy", "labels": "/m/03k3r,/m/07q5rw0,/m/07rv9rh,/m/0jbk", "caption": "Horses neighing and snorting while trotting on grass" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/Yo3mZR8OvPko.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yo3mZR8OvPko.npy", "labels": "/m/07yv9,/m/0k4j,/m/0ltv,/t/dd00128", "caption": "A race car accelerating and tires skidding" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YNlKlRKz8OKI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YNlKlRKz8OKI.npy", "labels": "/m/015p6,/m/020bb7,/m/07pggtn", "caption": "A woman talking then laughing followed by plastic tapping and birds chirping in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YBvw2gv1fcZw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBvw2gv1fcZw.npy", "labels": "/m/03q5_w,/m/09x0r", "caption": "A person speaks followed by a burping sound and laughter" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YZ3wDry8nnJs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YZ3wDry8nnJs.npy", "labels": "/m/09x0r,/m/0ytgt,/t/dd00125", "caption": "Water splashes followed by a girl speaking then scraping followed by spitting" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part15/YGE1aZSnPr2Q.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YGE1aZSnPr2Q.npy", "labels": "/m/01j3sz", "caption": "A person laughing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YBwnGxJD9xh8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBwnGxJD9xh8.npy", "labels": "/m/03fwl,/m/068hy,/m/07bgp,/m/0jbk", "caption": "Speech and a goat bleating" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YEUZaxaWqhwg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YEUZaxaWqhwg.npy", "labels": "/m/07yv9,/m/0cmf2,/m/0k5j", "caption": "A slap occurs and an aircraft engine runs as a man and child talk" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YNeZerAPXR-A.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YNeZerAPXR-A.npy", "labels": "/m/01j3sz,/m/09x0r,/t/dd00125", "caption": "Woman laughing and talking with another man and woman while something is clanging" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4eyY1w2QyM0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4eyY1w2QyM0.npy", "labels": "/m/0j6m2", "caption": "Ocean waves are hitting the shores" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YENTi8Sn4vdM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YENTi8Sn4vdM.npy", "labels": "/m/0j6m2", "caption": "A woman and young boy talking as a river stream flows and a young girl talks in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4ftDFi4684Y.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4ftDFi4684Y.npy", "labels": "/m/07qjznl", "caption": "A clock ticks, and an object is tapped" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part38/YwAZrOPvul4Y.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YwAZrOPvul4Y.npy", "labels": "/m/09x0r,/t/dd00112", "caption": "An adult male is speaking and plastic is crinkling, and music is playing softly in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YbLZFtoWXYTA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YbLZFtoWXYTA.npy", "labels": "/m/02jz0l", "caption": "A cup is filled from a faucet" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/Ydkiwn2FdDVw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ydkiwn2FdDVw.npy", "labels": "/m/09ddx,/m/09x0r", "caption": "A pretend duck quacks in cartoon fashion while an adult female speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/YfwhkCnOeyC0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YfwhkCnOeyC0.npy", "labels": "/m/028ght,/m/09x0r", "caption": "An audience applauds and cheers as an adult male speaks, a bell and buzzer ring, and the adult male speaks again" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YJdFmMw0zyKA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YJdFmMw0zyKA.npy", "labels": "/m/01j3sz,/m/09x0r", "caption": "A woman speaks, and a person makes animal sounds followed by laughter" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YWmDe2xbnSY4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YWmDe2xbnSY4.npy", "labels": "/m/07qsvvw", "caption": "Gunshots and explosions" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YXi6V0LGvqoo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YXi6V0LGvqoo.npy", "labels": "/m/01z5f,/m/068hy,/m/07rc7d9,/m/0bt9lr,/m/0jbk", "caption": "A dog barking followed by a dog growling as footsteps squeak on a hard surface floor and followed by series of metal clicks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/YfBYDJWChe5c.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YfBYDJWChe5c.npy", "labels": "/m/01d3sd", "caption": "A person snoring" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y2ABngPM3raQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y2ABngPM3raQ.npy", "labels": "/m/09ld4,/m/09x0r,/m/0jbk", "caption": "A man is speaking as frogs croak" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part7/Y5K1mISHwggI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y5K1mISHwggI.npy", "labels": "/m/02mk9,/m/07yv9,/m/09x0r", "caption": "A man speaks with others speaking in the distance and traffic passing with a few horns honking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part0/Y-mb4Fw4Z0xg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y-mb4Fw4Z0xg.npy", "labels": "/m/012f08,/m/07yv9,/m/09x0r,/m/0k4j,/t/dd00134", "caption": "Race car racing by some people laughing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YkF1KWybdRpM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YkF1KWybdRpM.npy", "labels": "/m/014yck,/m/07yv9,/m/0cmf2,/m/0k5j", "caption": "An airplane engine and wind" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part38/Yvsy1IpYmrSY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yvsy1IpYmrSY.npy", "labels": "/m/0h9mv", "caption": "Tires squealing and an engine revving repeatedly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/YpO8kbg9IJnc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YpO8kbg9IJnc.npy", "labels": "/m/0130jx,/m/02jz0l,/m/0838f", "caption": "Metal squeaking then plastic clacking as a man is talking followed by a faucet pouring water" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y54eRRbCtPn8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y54eRRbCtPn8.npy", "labels": "/m/02qldy,/m/02zsn,/m/09x0r", "caption": "An adult female speaks in a quiet environment" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YS8k47ME-YT4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YS8k47ME-YT4.npy", "labels": "/m/06mb1,/m/0jb2l,/m/0ngt1", "caption": "Rain and thunder" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3ejndVEAcmQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3ejndVEAcmQ.npy", "labels": "/m/01yrx,/m/068hy,/m/07qrkrw,/m/07r81j2,/m/0jbk", "caption": "A cat meowing and hissing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YmYQrjcYNrW0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YmYQrjcYNrW0.npy", "labels": "/m/01bjv,/m/07qv_d5,/m/07yv9", "caption": "A large motor vehicle engine is running, and a motor vehicle horn blows repeatedly and then stops" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part15/YGE1aZSnPr2Q.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YGE1aZSnPr2Q.npy", "labels": "/m/01j3sz", "caption": "A man laughing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YJhGp7HmRQxg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YJhGp7HmRQxg.npy", "labels": "/m/03k3r,/m/07q5rw0,/m/09x0r,/m/0jbk", "caption": "Birds chirping and a horse neighing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/Yfx4r_KuW6No.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yfx4r_KuW6No.npy", "labels": "/m/09x0r,/m/0ytgt,/t/dd00126", "caption": "A child speaking with crying and an adult female speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YnuZEAuAl8hQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YnuZEAuAl8hQ.npy", "labels": "/m/015p6,/m/09ddx,/m/0ch8v", "caption": "Wind with loud quacking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YPWjEfOkb6ro.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YPWjEfOkb6ro.npy", "labels": "/m/07swgks,/m/09x0r", "caption": "Rain is falling and hitting surfaces and then splashing into puddles" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/YwrQDkX0NbTA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YwrQDkX0NbTA.npy", "labels": "/m/019jd,/m/02rlv9,/m/07yv9", "caption": "A distant engine hums loudly with splashing water and blowing wind" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/Yt3VFlDiEKgY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yt3VFlDiEKgY.npy", "labels": "/m/03vt0,/m/09f96,/m/0h2mp", "caption": "An insect buzzing followed by a man talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YAagLJkfrFMk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YAagLJkfrFMk.npy", "labels": "/m/01jt3m", "caption": "Water hissing followed by a man breathing loudly then a toilet flushing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/Ykdflh3akyH8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ykdflh3akyH8.npy", "labels": "/m/0ghcn6,/m/0jbk,/t/dd00136", "caption": "A group of puppies whimpering alongside scrapping against a cardboard surface." }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y8ycflE3dIHw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y8ycflE3dIHw.npy", "labels": "/m/01g50p,/m/0284vy3,/m/06d_3,/m/07jdr,/m/07rwm0c", "caption": "Railroad track sounds then fading followed by a loud horn" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9U8COLzEegs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9U8COLzEegs.npy", "labels": "/m/02fs_r,/m/09x0r", "caption": "Water running softly in the background followed by several shrill beeps and a man speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part7/Y5QZ0NtdoKJ8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y5QZ0NtdoKJ8.npy", "labels": "/m/02fs_r,/m/07pp_mv,/m/09x0r", "caption": "Continuous digital beeps with a person speaking and bird chirping in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part1/Y0_ogYGDGDco.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y0_ogYGDGDco.npy", "labels": "/m/019jd,/m/034srq,/m/03m9d0z,/m/056ks2,/m/05kq4,/t/dd00092", "caption": "A boat is traveling while water is splashing with wind noise, and a man is speaking on a two-way radio" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YQARuiRtfy-k.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YQARuiRtfy-k.npy", "labels": "/m/01d380", "caption": "A power tool drilling followed by a person blowing air then a man speaking as light rock music plays in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YQvATUKXYFBs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YQvATUKXYFBs.npy", "labels": "/m/01g50p,/m/0284vy3,/m/06d_3,/m/07jdr,/m/07rwm0c", "caption": "Warning bells ring and a train passes with a honking horn" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part0/Y-AheI8Epim4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y-AheI8Epim4.npy", "labels": "/m/07qsvvw,/m/09x0r", "caption": "Rustling with some distant banging and people speaking in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/Ye9MWXS34o48.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ye9MWXS34o48.npy", "labels": "/m/01hsr_", "caption": "A person breathes heavily and sneezes" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/YdlsiellSFf0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YdlsiellSFf0.npy", "labels": "/m/019jd,/m/02rlv9,/m/07yv9", "caption": "A toy motor buzzing as water splashes and birds chirp in the distance." }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YlTfNLKEy1RU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YlTfNLKEy1RU.npy", "labels": "/m/01d3sd,/m/0bt9lr,/m/0jbk", "caption": "A dog snoring and gurgling followed by paper sliding" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/YyRoKi7rhSRo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YyRoKi7rhSRo.npy", "labels": "/m/01jt3m,/m/0838f", "caption": "A toilet flushes as a bird chirps in the distance followed by a man speaking in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/YhVUmQfBIYe8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YhVUmQfBIYe8.npy", "labels": "/m/02dgv", "caption": "A man speaks followed by a door opening" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part15/YGPj8h-WcjWs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YGPj8h-WcjWs.npy", "labels": "/m/01bjv,/m/07yv9,/m/09x0r", "caption": "Humming of an engine with a woman speaking over a loudspeaker" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y2ABngPM3raQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y2ABngPM3raQ.npy", "labels": "/m/09ld4,/m/09x0r,/m/0jbk", "caption": "A man talking as music is playing followed by a frog croaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y2JutOgAnqWA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y2JutOgAnqWA.npy", "labels": "/m/01d380,/m/07k1x,/m/0_ksk", "caption": "A tool motor is running, a rattling sound occurs, then humming also, then soft squealing occurs" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YNwoBDrTlbTI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YNwoBDrTlbTI.npy", "labels": "/t/dd00018", "caption": "A guinea pig chirping then squeaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/Ygr5Zss89yLQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ygr5Zss89yLQ.npy", "labels": "/m/01bjv,/m/07yv9,/m/09x0r", "caption": "An engine running consistently with brief muffled female speech" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YAKHZMg9ba30.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YAKHZMg9ba30.npy", "labels": "/m/07rv9rh,/m/09x0r,/m/0jbk", "caption": "Clip-clop of horse while man speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/Yf2fSxfvmkZQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yf2fSxfvmkZQ.npy", "labels": "/m/01d380,/m/09x0r", "caption": "A man talking as a metal thumps followed by a power tool sanding as a metal pot clanks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YQRtuOWWya30.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YQRtuOWWya30.npy", "labels": "/m/0dxrf", "caption": "Tapping noises followed by a man talking with gurgling background noises" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y1DKLyH3FixM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1DKLyH3FixM.npy", "labels": "/m/015p6,/m/020bb7,/m/07pggtn", "caption": "Nature sounds with birds chirping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/Ye2rScj9UyMs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ye2rScj9UyMs.npy", "labels": "/m/015p6,/m/0h0rv,/t/dd00125", "caption": "Birds cooing with clanging in background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YPVvi2SDOjVc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YPVvi2SDOjVc.npy", "labels": "/m/07yv9,/m/0912c9,/m/0k4j,/t/dd00128", "caption": "Humming of traffic followed by a loud car horn" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YITlqMkR5alY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YITlqMkR5alY.npy", "labels": "/m/03fwl,/m/09x0r,/m/0ch8v,/m/0jbk", "caption": "Wind blows hard followed by screaming" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part7/Y5t6tSW0yT40.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y5t6tSW0yT40.npy", "labels": "/m/07qlf79", "caption": "A motor hums softly followed by spraying" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part4/Y2bq2lc3DLwM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y2bq2lc3DLwM.npy", "labels": "/m/07yv9,/m/09x0r,/m/0k4j,/t/dd00134", "caption": "A man speaking and a car driving closer than passing by" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YCM49C3RkzV8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YCM49C3RkzV8.npy", "labels": "/m/02qldy,/m/02zsn,/m/09x0r", "caption": "A woman speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YYIqpIjjee00.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YYIqpIjjee00.npy", "labels": "/m/01jt3m", "caption": "A flush occurs with water splashing and gurgling, and then water runs steadily" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YQHfyKaOHSz4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YQHfyKaOHSz4.npy", "labels": "/m/07st88b,/m/09ld4", "caption": "A fly buzzing and a frog croaking with musical sounds" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YFL8KTgMGrN4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YFL8KTgMGrN4.npy", "labels": "/m/06wzb,/m/07rjwbb", "caption": "A vacuum cleaner cleaning a surface and hissing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YB-gTt3_rceQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YB-gTt3_rceQ.npy", "labels": "/m/09x0r,/m/0ytgt,/t/dd00125", "caption": "A group of people talking followed by a man speaking then a kid talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part27/Y_z6pymOet7g.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y_z6pymOet7g.npy", "labels": "/m/01jt3m,/m/09x0r", "caption": "A man speaks before a toilet flush" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y7-HCqJFwHoI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y7-HCqJFwHoI.npy", "labels": "/m/01m2v,/m/0316dw", "caption": "Typing on computer keyboards" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part9/Y86dNVnTwH6U.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y86dNVnTwH6U.npy", "labels": "/m/09x0r,/m/0llzx", "caption": "A quick burst followed by a single hiss then rapid hissing and humming" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/YeUecAF626A8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YeUecAF626A8.npy", "labels": "/m/07yv9,/m/09x0r,/m/0k4j,/m/0ltv", "caption": "Vehicles hum and vibrate as they rev their engines" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9MgGaTbmc6g.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9MgGaTbmc6g.npy", "labels": "/m/02mk9,/m/07q2z82,/m/07yv9,/m/0k4j,/t/dd00066", "caption": "A car engine accelerating and revving while tires skid" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YJdFmMw0zyKA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YJdFmMw0zyKA.npy", "labels": "/m/01j3sz,/m/09x0r", "caption": "A kid speaking followed by a seal making noises then water splashing as a kid and woman are laughing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/YzEaGx6an4es.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YzEaGx6an4es.npy", "labels": "/m/01d380,/m/07k1x", "caption": "High pitched motorized vibrations" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/Yy93cZqNCtks.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yy93cZqNCtks.npy", "labels": "/m/032s66,/m/04zjc", "caption": "Multiple gunfire sounds, and men speak" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YT9_ep-3BZDY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YT9_ep-3BZDY.npy", "labels": "/m/09x0r,/t/dd00112,/t/dd00125", "caption": "Crinkling plastic and a person speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part19/YMBP4RcnwGZw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YMBP4RcnwGZw.npy", "labels": "/m/02zsn,/m/07qfr4h,/m/09x0r", "caption": "A woman speaks with others speaking in the distance and wind blowing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part38/Yvsy1IpYmrSY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yvsy1IpYmrSY.npy", "labels": "/m/0h9mv", "caption": "Race car engine passing by along with tire screeching noises" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y5G6b_QWL3nY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y5G6b_QWL3nY.npy", "labels": "/m/07p9k1k,/m/0dxrf", "caption": "A woman talking as food and oil sizzles followed by water gurgling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YndxkSQKxaak.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YndxkSQKxaak.npy", "labels": "/m/04_sv,/m/07yv9,/m/09x0r", "caption": "Motorcycle engine idling as man starts talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/Ym_NCf-q4Gn0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ym_NCf-q4Gn0.npy", "labels": "/m/04_sv,/m/07qnq_y,/m/07yv9,/t/dd00128", "caption": "Plastic thumping as an idle motorcycle engine runs" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y1GgEpRZDWN0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1GgEpRZDWN0.npy", "labels": "/m/01h8n0,/m/02zsn,/m/09x0r", "caption": "A woman and man speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YZBtgrP4vU_w.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YZBtgrP4vU_w.npy", "labels": "/m/07p9k1k", "caption": "Food and oil sizzling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part19/YMjSegUnQXr4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YMjSegUnQXr4.npy", "labels": "/m/015p6,/m/0h0rv,/t/dd00125", "caption": "Pigeons make sounds and flapping noises" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part27/Ya0yXS7PmVR0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ya0yXS7PmVR0.npy", "labels": "/m/07qlf79", "caption": "Continuous white noise" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YWUyeFOyKIg0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YWUyeFOyKIg0.npy", "labels": "/m/07yv9,/m/09x0r,/m/0k4j,/m/0ltv,/t/dd00129", "caption": "A vehicle driving in the distance followed by tires skidding as a vehicle drives by while a crowd of people talk in the background and wind blows into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part1/Y0Rpjl1AO-P0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y0Rpjl1AO-P0.npy", "labels": "/m/07yv9,/m/0k4j,/t/dd00134", "caption": "A car engine idling then starts to rev shortly after" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YTSnq6n8tElo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YTSnq6n8tElo.npy", "labels": "/m/0242l,/m/04brg2", "caption": "A young child talking followed by tapping on glass then metal rattling on a glass surface" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9MgGaTbmc6g.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9MgGaTbmc6g.npy", "labels": "/m/02mk9,/m/07q2z82,/m/07yv9,/m/0k4j,/t/dd00066", "caption": "A vehicle revving and accelerating as tires skid and squeak on a road" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YBwnGxJD9xh8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBwnGxJD9xh8.npy", "labels": "/m/03fwl,/m/068hy,/m/07bgp,/m/0jbk", "caption": "A man speaks and a goat bleats" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/Ye9MWXS34o48.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ye9MWXS34o48.npy", "labels": "/m/01hsr_", "caption": "A woman sneezing and sniffling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YU5ij0M7T-hk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YU5ij0M7T-hk.npy", "labels": "/m/02dgv,/m/09x0r", "caption": "Footsteps walking on a hard surface followed by a door sliding open then a man talking before a door creaks and closes shut" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/YpuZL08fzpXk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YpuZL08fzpXk.npy", "labels": "/m/032s66,/m/04zjc", "caption": "Much gunfire and guns clicking while people talk in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part1/Y0_ogYGDGDco.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y0_ogYGDGDco.npy", "labels": "/m/019jd,/m/034srq,/m/03m9d0z,/m/056ks2,/m/05kq4,/t/dd00092", "caption": "A stream of water trickling and splashing while a man talks over a radio alongside wind blowing into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y6dLkgq9EKPE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y6dLkgq9EKPE.npy", "labels": "/m/01bjv,/m/07yv9,/m/09x0r", "caption": "A man speaks with some faint clicks and humming" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/YcPiSd5nJLrI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YcPiSd5nJLrI.npy", "labels": "/m/014zdl,/m/07pxg6y,/m/07qsvvw", "caption": "A group of people laughing and screaming alongside firecrackers igniting then exploding followed by a muffled explosion" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YTQr9v-PQOc4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YTQr9v-PQOc4.npy", "labels": "/m/01hsr_", "caption": "Someone sneezes through static and then coughs several times in quick succession" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part1/Y0AsXkZkqelg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y0AsXkZkqelg.npy", "labels": "/m/028ght", "caption": "A vehicle running idle then stuttering" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y466ucPGoNSQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y466ucPGoNSQ.npy", "labels": "/m/01yrx,/m/068hy,/m/07qrkrw,/m/09x0r,/m/0jbk", "caption": "A cat meowing and whining" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y404cD3bVXDc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y404cD3bVXDc.npy", "labels": "/m/09x0r,/t/dd00002", "caption": "A baby crying with a television on in background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YqakN0JNbpcU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YqakN0JNbpcU.npy", "labels": "/m/01h3n,/m/03vt0,/m/09x0r", "caption": "A man speaks while bees are buzzing all around" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YUAmDLPjNyMg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YUAmDLPjNyMg.npy", "labels": "/m/07yv9,/m/0cmf2,/m/0k5j", "caption": "An aircraft flying as a person briefly sniffs aloud while wind blows into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YK-7Y8yhcUiw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YK-7Y8yhcUiw.npy", "labels": "/m/01d3sd,/m/068hy,/m/0bt9lr,/m/0jbk", "caption": "A light and brief snoring" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/Yi6MQCm58zlY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yi6MQCm58zlY.npy", "labels": "/m/020bb7,/m/068hy,/m/0jbk", "caption": "Squealing and whimpering with a man speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YSmdj6JFB9MQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YSmdj6JFB9MQ.npy", "labels": "/m/01jt3m,/m/09x0r", "caption": "A woman talking followed by a toilet flushing while a kid talks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YXplKBvZaHXA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YXplKBvZaHXA.npy", "labels": "/m/04_sv,/m/07yv9,/m/09x0r,/t/dd00129", "caption": "A man speaks as a motorcycle accelerates" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YsbW7XwwUtSU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YsbW7XwwUtSU.npy", "labels": "/m/07qjznl,/m/07qjznt", "caption": "A clock ticking repeatedly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/YA61Mry8zBwE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YA61Mry8zBwE.npy", "labels": "/m/07rv9rh,/m/09x0r,/m/0jbk", "caption": "Applause from a crowd with distant clicking and a man speaking over a loudspeaker" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part38/Yu8bQf0SnCVI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yu8bQf0SnCVI.npy", "labels": "/m/0130jx,/m/02jz0l,/t/dd00125", "caption": "Swiping occurs then a faucet runs and drains" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/YgW7s3YAthpI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YgW7s3YAthpI.npy", "labels": "/m/02jz0l,/m/0838f", "caption": "Chewing as liquid is poured and some light banging on a hard surface" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YnuZEAuAl8hQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YnuZEAuAl8hQ.npy", "labels": "/m/015p6,/m/09ddx,/m/0ch8v", "caption": "Ducks quack and then a dog barks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/YeJCaRgf1M20.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YeJCaRgf1M20.npy", "labels": "/m/07qjznl", "caption": "A bell chimes followed by camera muffling and metal shuffling then a gear cranking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part9/Y8ZH_PoK0clI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y8ZH_PoK0clI.npy", "labels": "/m/02dgv,/m/09x0r", "caption": "A door repeatedly slamming as a group of men and women talk" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YO90Qy2xG6oA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YO90Qy2xG6oA.npy", "labels": "/m/068hy,/m/0jbk,/t/dd00002", "caption": "A parrot vocalizing and then a baby laughing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part27/YZsf2YvJfCKw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YZsf2YvJfCKw.npy", "labels": "/m/01jt3m", "caption": "A toilet flushing and water running" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part7/Y6Pywt0f_NFY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y6Pywt0f_NFY.npy", "labels": "/m/02jz0l,/m/03dnzn,/m/0838f", "caption": "Water running and gurgling followed by some spring" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YtJhVH3VIrnE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YtJhVH3VIrnE.npy", "labels": "/m/02dgv", "caption": "A object is hitting a surface followed by a loud boom" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/YoOMtaqvQ3_M.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YoOMtaqvQ3_M.npy", "labels": "/m/07yv9,/m/09ct_,/m/0k5j", "caption": "Helicopter propellers spinning and wind" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YPuLuZ_TXv-0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YPuLuZ_TXv-0.npy", "labels": "/m/0316dw,/m/0c2wf", "caption": "Rapid typing and then sliding" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/Ysl_Pxpc7beo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ysl_Pxpc7beo.npy", "labels": "/m/07yv9,/m/0912c9,/t/dd00128", "caption": "A vehicle is honking the horn" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/Yj1AiqT5oHZc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yj1AiqT5oHZc.npy", "labels": "/m/02fs_r,/m/09x0r,/t/dd00125", "caption": "A male speaking and repeated beeps" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YWq4OD3olO2w.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YWq4OD3olO2w.npy", "labels": "/m/07r660_,/m/09x0r,/m/0ytgt,/t/dd00125", "caption": "Children screaming and speaking and a female speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y404cD3bVXDc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y404cD3bVXDc.npy", "labels": "/m/09x0r,/t/dd00002", "caption": "An infant crying then shouting as a man talks through a television speaker" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part15/YH7rd9bZtbgc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YH7rd9bZtbgc.npy", "labels": "/m/0395lw", "caption": "Bells ringing repeatedly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YSePTNAN7s-w.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YSePTNAN7s-w.npy", "labels": "/m/01jt3m,/m/0838f", "caption": "Speech followed by a toilet flushing and more speech" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/Ye6jSpvTvfJ0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ye6jSpvTvfJ0.npy", "labels": "/m/06mb1,/m/0cj0r", "caption": "It is raining with wind noise" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/Ygr5Zss89yLQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ygr5Zss89yLQ.npy", "labels": "/m/01bjv,/m/07yv9,/m/09x0r", "caption": "A woman speaks, and a motor vehicle revs its engine" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YAWGnTI0e2Fs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YAWGnTI0e2Fs.npy", "labels": "/m/09ct_", "caption": "A helicopter is taking off and flying" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/Ye4ph6bIC5zc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ye4ph6bIC5zc.npy", "labels": "/m/012f08,/m/07yv9,/m/0k4j,/m/0ltv", "caption": "Distant murmuring and distant engine revving" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part19/YMOxddxW5PXs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YMOxddxW5PXs.npy", "labels": "/m/09x0r,/m/0dxrf", "caption": "Food and oil sizzling as a man is talking while metal clanks against a pan" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YLxu-3_h4kc4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YLxu-3_h4kc4.npy", "labels": "/m/03q5_w", "caption": "A series of belching followed by a group of kids laughing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YL2dyilgQ8iM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YL2dyilgQ8iM.npy", "labels": "/m/09t49,/t/dd00092", "caption": "Footsteps walking on snow with wind blowing on a microphone and camera muffling during audio feedback buzzing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9z8XIRyUq9Q.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9z8XIRyUq9Q.npy", "labels": "/m/02qldy,/m/02zsn,/m/09x0r", "caption": "An adult female is speaking and her voice is amplified" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YkagkXkAVPNo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YkagkXkAVPNo.npy", "labels": "/m/07yv9,/m/0912c9,/m/09x0r,/m/0k4j", "caption": "An engine revving followed by a loud honk, then several other honks and a woman talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YXamQAY_WXRY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YXamQAY_WXRY.npy", "labels": "/m/0j6m2", "caption": "A man speaks while water slaps on a surface" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/Yw_Utn3CwAXE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yw_Utn3CwAXE.npy", "labels": "/m/01jt3m,/m/0838f", "caption": "A toilet flushes followed by a metal latch clanking then a door slowly creaking open" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/YyVVLq4ao1Ck.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YyVVLq4ao1Ck.npy", "labels": "/m/015p6,/m/020bb7,/m/07pggtn", "caption": "A bird is chirping while a fly is buzzing and another insect is making ringing sounds" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/YggN4-K5AgoM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YggN4-K5AgoM.npy", "labels": "/m/01jt3m,/m/0838f", "caption": "A toilet flushes and water drains" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y77nElZGi5NU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y77nElZGi5NU.npy", "labels": "/m/07qsvvw,/m/09x0r", "caption": "A loud burst followed by laughter" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/YxIztYnMIWUA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YxIztYnMIWUA.npy", "labels": "/m/01hnzm,/m/07cx4,/m/07pp8cl", "caption": "A telephone rings several times" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YrE6BJ0Bo4w4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YrE6BJ0Bo4w4.npy", "labels": "/m/02jz0l,/m/09x0r,/t/dd00125", "caption": "A woman is speaking, then water runs from a faucet, then she speaks again and there is a slapping sound" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YIvg_q4t-3w0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YIvg_q4t-3w0.npy", "labels": "/m/02dgv,/m/09x0r", "caption": "A female speaking and then a door slamming" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y1HCuBnPLMqQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1HCuBnPLMqQ.npy", "labels": "/m/07pqc89", "caption": "A liquid makes a trickling noise" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y0fMXnvD38zI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y0fMXnvD38zI.npy", "labels": "/m/019jd,/m/034srq,/m/03m9d0z,/m/05kq4,/t/dd00092", "caption": "Ocean waves crashing as water trickles as gusts of wind blow and seagulls squawk in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YKOBkbROPv4c.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YKOBkbROPv4c.npy", "labels": "/m/07rknqz,/m/07yv9,/m/0h9mv,/m/0ltv", "caption": "Humming and revving of an engine with squealing tires as a car speeds past" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/YjOYvIISk--4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YjOYvIISk--4.npy", "labels": "/m/0130jx,/m/02jz0l,/m/0838f", "caption": "A man talking as a sink faucet turns on and off twice as water sprays then drains down a pipe" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YJmWaRt8-u0s.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YJmWaRt8-u0s.npy", "labels": "/m/04_sv,/m/07yv9,/m/09x0r,/t/dd00066", "caption": "Humming of engines with people speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/Yb1PXsfgQw5w.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yb1PXsfgQw5w.npy", "labels": "/m/01j3sz,/m/07r660_,/m/09x0r", "caption": "A group of people laughing followed by a man talking then more laughter" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YHqndxoujCYI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YHqndxoujCYI.npy", "labels": "/m/07qjznl,/m/09x0r", "caption": "A bell chiming as a clock ticks and a man talks through a television speaker in the background followed by a muffled bell chiming" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YQHfyKaOHSz4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YQHfyKaOHSz4.npy", "labels": "/m/07st88b,/m/09ld4", "caption": "An insect buzzing as wood clacks twice followed by a person gulping then another insect buzzing proceeded by another person gulping and talking while an electric guitar strums" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YE9zN3-C64KE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YE9zN3-C64KE.npy", "labels": "/m/09x0r,/t/dd00018", "caption": "A woman speaks affectionately as a pig oinks quietly, then wood creaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YqakN0JNbpcU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YqakN0JNbpcU.npy", "labels": "/m/01h3n,/m/03vt0,/m/09x0r", "caption": "A man is speaking and a fly is buzzing around" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y7JWHbs3gu1w.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y7JWHbs3gu1w.npy", "labels": "/m/01g50p,/m/0284vy3,/m/06d_3,/m/07jdr,/m/07rwm0c", "caption": "A train roars and honks it horn" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part0/Y-SkjbQVgJ0M.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y-SkjbQVgJ0M.npy", "labels": "/m/07yv9,/m/09x0r,/m/0k4j,/t/dd00134", "caption": "A man talking near a road with fast moving vehicles passing by" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/YzEaGx6an4es.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YzEaGx6an4es.npy", "labels": "/m/01d380,/m/07k1x", "caption": "A sustained and coarse drilling noise" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part19/YN_s9F4CI_98.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YN_s9F4CI_98.npy", "labels": "/m/015p6,/m/020bb7,/m/07r_25d,/m/0h0rv", "caption": "Bird cooing and wings flapping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9BGLAUSF0sk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9BGLAUSF0sk.npy", "labels": "/m/01jwx6,/m/0chx_", "caption": "An idling engine humming non stop" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/Yr2KhpX_QgXA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yr2KhpX_QgXA.npy", "labels": "/m/02mk9,/m/02x984l,/m/09x0r", "caption": "A man speaks as a machine hums quietly and then increases in volume" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YLKhokVsJhN0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YLKhokVsJhN0.npy", "labels": "/m/07bgp,/m/0ch8v,/m/0jbk", "caption": "A flock of sheep baaing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part19/YMkbP_8zJwXU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YMkbP_8zJwXU.npy", "labels": "/m/015p6,/m/068hy,/m/09ddx,/t/dd00129", "caption": "Water lightly splashing as a bird chirps and wind blows into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YWOywdRmySs0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YWOywdRmySs0.npy", "labels": "/m/09x0r,/t/dd00112", "caption": "A man talking followed by plastic crinkling and crumpling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YlfAFQ0-wDJU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YlfAFQ0-wDJU.npy", "labels": "/m/034srq,/m/03m9d0z", "caption": "Ocean waves crashing as wind blows into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part4/Y35b9BSmN5JM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y35b9BSmN5JM.npy", "labels": "/m/07q2z82,/m/07yv9,/m/0k4j", "caption": "A motor vehicle accelerates and revs" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YCefFMA3klxk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YCefFMA3klxk.npy", "labels": "/m/012f08,/m/07r04,/m/07yv9,/m/0912c9", "caption": "Semi-truck honking then taking off." }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y5I8lmN8rwDM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y5I8lmN8rwDM.npy", "labels": "/m/01d380,/m/07k1x,/t/dd00125", "caption": "A power tool sanding" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YBz9Y5nZK3eo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBz9Y5nZK3eo.npy", "labels": "/m/01m2v,/m/0316dw", "caption": "Typing on a computer keyboard" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/Yc6YJgZ3qzOw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yc6YJgZ3qzOw.npy", "labels": "/m/09ct_", "caption": "A toy helicopter flying followed by wind blowing into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YNmmbNqmsPaY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YNmmbNqmsPaY.npy", "labels": "/m/07pb8fc,/m/07yv9,/m/0k4j", "caption": "An engine idling with bells ringing in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/YhiJB_95IWiE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YhiJB_95IWiE.npy", "labels": "/m/02p01q,/m/07pdjhy", "caption": "An adult male speaks and then metal scraping occurs, followed by metal clattering and another metal scrape" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YCMUuelJFJ7Q.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YCMUuelJFJ7Q.npy", "labels": "/m/07qjznl,/m/07qjznt", "caption": "One long chime" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y77nElZGi5NU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y77nElZGi5NU.npy", "labels": "/m/07qsvvw,/m/09x0r", "caption": "A loud explosion followed by people cheering and laughing as wind blows into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part1/Y0Dt-pH0pW-Y.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y0Dt-pH0pW-Y.npy", "labels": "/m/04_sv,/m/07yv9,/m/09x0r", "caption": "A motorcycle running and male speech and then laughing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YCvNAwby6Xos.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YCvNAwby6Xos.npy", "labels": "/m/09x0r,/m/0llzx,/t/dd00125", "caption": "A sewing machine running as a man is talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YIJ6pm5Kns8A.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YIJ6pm5Kns8A.npy", "labels": "/m/03q5_w,/m/09x0r", "caption": "A man talking followed by a person clapping then electronic chimes alongside a woman talking before another person claps proceeded by a person belching and two people laughing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y7RMpCCkQks0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y7RMpCCkQks0.npy", "labels": "/m/07rjwbb", "caption": "An industrial motor is humming, and ripping and tearing are occurring" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YDt53UZgyznE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YDt53UZgyznE.npy", "labels": "/m/09x0r,/t/dd00002", "caption": "Baby cries and then man speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/YjXkLS_QzUrI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YjXkLS_QzUrI.npy", "labels": "/m/068hy,/m/07qrkrw", "caption": "A small motor is running, five hisses and a meow occur, then five more hisses and a meow occur" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YHqnSyliKTKA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YHqnSyliKTKA.npy", "labels": "/m/03k3r,/m/07q5rw0,/m/07rv9rh,/m/09x0r,/m/0jbk", "caption": "A crowd of people talking followed by a horse neighing as a lawn mower runs in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YCO6-i8NLbeo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YCO6-i8NLbeo.npy", "labels": "/m/03fwl,/m/09x0r,/m/0jbk", "caption": "A man talking followed by a goat baaing then a metal gate sliding as ducks quack and wind blows into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4bUL_ttiOdw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4bUL_ttiOdw.npy", "labels": "/t/dd00002", "caption": "Baby upset and crying" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/YwSHzVxdMiTo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YwSHzVxdMiTo.npy", "labels": "/m/09x0r,/t/dd00018", "caption": "A pig squeezing and male speech" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YlX3k5p2I_g0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YlX3k5p2I_g0.npy", "labels": "/m/014yck,/m/02mk9,/m/07yv9,/m/09x0r,/m/0cmf2,/m/0k5j", "caption": "Man talking in the wind and someone yells in the background while an engine makes squealing and air puffing sounds" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y0qbHT34qTZE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y0qbHT34qTZE.npy", "labels": "/m/032s66,/m/06q74,/m/09x0r", "caption": "Gunfire is ongoing and water is splashing, adult males are shouting in the background, and an adult male speaks in the foreground" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/YfwhkCnOeyC0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YfwhkCnOeyC0.npy", "labels": "/m/028ght,/m/09x0r", "caption": "A man and a woman talking followed by a bell ringing as a crowd of people applaud" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part19/YN_s9F4CI_98.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YN_s9F4CI_98.npy", "labels": "/m/015p6,/m/020bb7,/m/07r_25d,/m/0h0rv", "caption": "Birds are cooing, and wings flap" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YYk274Wr5iIE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YYk274Wr5iIE.npy", "labels": "/m/06mb1", "caption": "A large amount of water is splashing and gurgling, and the wind is blowing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part4/Y350OCezayrk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y350OCezayrk.npy", "labels": "/m/02mk9,/m/07yv9,/m/0k4j,/t/dd00066,/t/dd00130", "caption": "An engine being turned over and then started" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YZ-SIyOChVh8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YZ-SIyOChVh8.npy", "labels": "/m/06mb1,/m/0jb2l,/m/0ngt1", "caption": "Rain and thunder" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part0/Y-JP1GqPEKtw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y-JP1GqPEKtw.npy", "labels": "/m/07k1x,/m/083vt,/m/09x0r", "caption": "A male voice and a machine buzzing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part24/YVjSEIRnLAh8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YVjSEIRnLAh8.npy", "labels": "/m/09x0r,/m/0dxrf", "caption": "Frying and female speech" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YD9tinq3RMpU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YD9tinq3RMpU.npy", "labels": "/m/019jd,/m/02rlv9,/m/07yv9,/m/09x0r", "caption": "A large motor is running smoothly, water is splashing, people are talking in the background, and an adult male speaks in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part9/Y8ZH_PoK0clI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y8ZH_PoK0clI.npy", "labels": "/m/02dgv,/m/09x0r", "caption": "A series of doors slamming open as footsteps shuffle and plastic clack while a woman speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YkEP-BwMarf8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YkEP-BwMarf8.npy", "labels": "/m/09x0r,/t/dd00112", "caption": "Paper crackling with female speaking lightly in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/YoNHCc_izsDE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YoNHCc_izsDE.npy", "labels": "/m/01j3sz,/m/07rrlb6", "caption": "Water splashing and a baby laughing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/YonBZOH88OYs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YonBZOH88OYs.npy", "labels": "/m/07qlf79", "caption": "Repeated bursts of spray" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YEBCH7TPgiPc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YEBCH7TPgiPc.npy", "labels": "/m/07q2z82,/m/07yv9,/m/0k4j", "caption": "A vehicle engine accelerating at a rapid rate before slowing down" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/YeRU-rABp8nk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YeRU-rABp8nk.npy", "labels": "/m/04_sv,/m/07yv9,/m/09x0r", "caption": "Two men talking as a motorcycle engine runs idle and a group of people laugh" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YBQ-r9mEHssU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBQ-r9mEHssU.npy", "labels": "/m/03k3r,/m/07rv9rh,/m/09x0r,/m/0jbk", "caption": "Laughing and rustling with horse hooves" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/Yt4prXmPwthg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yt4prXmPwthg.npy", "labels": "/m/09x0r,/m/0llzx", "caption": "A sewing machine running and then female speech" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y0jGH7A_hpBM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y0jGH7A_hpBM.npy", "labels": "/m/02qldy,/m/05zppz,/m/09x0r", "caption": "One man speaking, then another man speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/Yn-JyOqYSLQM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yn-JyOqYSLQM.npy", "labels": "/m/07qlf79", "caption": "A few loud bangs with some rattling and hissing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YWCYfCfW9NA0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YWCYfCfW9NA0.npy", "labels": "/m/07yv9,/m/09ct_,/t/dd00129", "caption": "High-pitched turbine noise from helicopter, rhythmic squeaking, motor sound grows louder" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YTdl9SmBbRnA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YTdl9SmBbRnA.npy", "labels": "/m/012f08,/m/01bjv,/m/07yv9,/m/09x0r", "caption": "A large motor vehicle engine accelerates and then slows and idles, while an adult male speaks in the foreground" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y6TO9PEGpZcQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y6TO9PEGpZcQ.npy", "labels": "/m/012n7d,/m/012ndj,/m/03j1ly,/m/03kmc9", "caption": "Emergency sirens followed by an engine idling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9xoYx3lTJ9I.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9xoYx3lTJ9I.npy", "labels": "/m/019jd,/m/02rlv9,/m/03m9d0z,/t/dd00092", "caption": "Wind sounds as motor boat travels followed by a woman speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part24/YV4PLSw_WzVw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YV4PLSw_WzVw.npy", "labels": "/m/07r04,/m/07rknqz,/m/07yv9", "caption": "A motor vehicle is skidding its tires" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YLF6x7B0Ppvo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YLF6x7B0Ppvo.npy", "labels": "/m/07yv9,/m/0k4j,/m/0ltv", "caption": "A vehicle engine revving then accelerating at a high rate as wind blows heavily into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YXL8JV9qXGLE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YXL8JV9qXGLE.npy", "labels": "/m/0463cq4,/m/09x0r,/m/0ytgt,/t/dd00002,/t/dd00125", "caption": "A baby cries and a woman speaks with other people speaking in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YmUGmCSNETcg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YmUGmCSNETcg.npy", "labels": "/m/07ptfmf,/m/0dxrf", "caption": "Women talk over sizzling and clanking, motor sound in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YAUJPx81qKtY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YAUJPx81qKtY.npy", "labels": "/m/01h3n,/m/03vt0,/m/0h2mp", "caption": "A man talking as a swarm of insects are buzzing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YcFHFVGOtp6g.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YcFHFVGOtp6g.npy", "labels": "/m/09ld4,/m/09x0r", "caption": "A throbbing noise with a woman speaking in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/YgbtcDoh0q3c.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YgbtcDoh0q3c.npy", "labels": "/m/01j3sz,/m/07s04w4,/m/09x0r", "caption": "Man talks while striking and popping occurs then a second man laughs" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part38/Yu8bQf0SnCVI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yu8bQf0SnCVI.npy", "labels": "/m/0130jx,/m/02jz0l,/t/dd00125", "caption": "Some light banging followed by water splashing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YKel-hfZ_9h8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YKel-hfZ_9h8.npy", "labels": "/m/09x0r,/m/0ytgt,/t/dd00013", "caption": "A child laughing followed by a man talking as snow shuffles in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part7/Y67BsqRkh-dU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y67BsqRkh-dU.npy", "labels": "/m/01jt3m,/m/0838f", "caption": "A toilet is flushed" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3hzy-FL24no.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3hzy-FL24no.npy", "labels": "/m/0j6m2", "caption": "Mechanical engine and running water" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YDAN1t9ukkg0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YDAN1t9ukkg0.npy", "labels": "/m/01m2v,/m/0316dw", "caption": "A person is typing keyboard with some mouse clicking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YBzHTqyX69pI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBzHTqyX69pI.npy", "labels": "/m/07pdjhy,/m/083vt", "caption": "Wood sawing as pigeons coo and bird wings flap followed by a woman speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3rna9zo5ZOs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3rna9zo5ZOs.npy", "labels": "/m/02qldy,/m/05zppz,/m/09x0r", "caption": "A man is giving a speech and a crowd cheers" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part0/Y-mhFGevxLUg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y-mhFGevxLUg.npy", "labels": "/m/07rqsjt,/m/09x0r", "caption": "Male speaking with another male voice in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YWU3qB7gf6ao.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YWU3qB7gf6ao.npy", "labels": "/m/02fs_r", "caption": "An electronic beep and several faints ticks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part9/Y8BPTQO_cx7E.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y8BPTQO_cx7E.npy", "labels": "/m/028ght", "caption": "A man speaking followed by applause and laughter from an audience" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YRp4Ct_TQvAM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YRp4Ct_TQvAM.npy", "labels": "/m/06mb1,/m/09x0r", "caption": "Rain falling as a machine motor runs followed by a man speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part38/YwAZrOPvul4Y.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YwAZrOPvul4Y.npy", "labels": "/m/09x0r,/t/dd00112", "caption": "A man talking as plastic is crinkling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YEp72tyiL3as.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YEp72tyiL3as.npy", "labels": "/m/0ngt1", "caption": "Thunder crashes and echos" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YOmmPaIAXN0s.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YOmmPaIAXN0s.npy", "labels": "/m/03k3r,/m/07rv9rh,/m/09x0r,/m/0jbk", "caption": "A man speaking followed by a horse trotting" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part7/Y6CDl4CqOgMg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y6CDl4CqOgMg.npy", "labels": "/m/068hy,/m/0bt9lr,/m/0jbk,/t/dd00136", "caption": "An animal heavily breathing then snorting followed by footsteps on a hard surface and a camera muffling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YKVAIaRPry24.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YKVAIaRPry24.npy", "labels": "/m/01h3n,/m/03vt0,/m/0h2mp", "caption": "An insect buzzing as plastic clacks then slaps a hard surface in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/Yh5_1pnkl_SY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yh5_1pnkl_SY.npy", "labels": "/m/02jz0l,/m/0838f", "caption": "A man speaks as water runs" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y1N_DtRpdAp8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1N_DtRpdAp8.npy", "labels": "/m/01jwx6", "caption": "A mid-size engine is idling and vibrating and is revved up one time" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4eyY1w2QyM0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4eyY1w2QyM0.npy", "labels": "/m/0j6m2", "caption": "Ocean waves crashing and water splashing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part1/Y0Dt-pH0pW-Y.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y0Dt-pH0pW-Y.npy", "labels": "/m/04_sv,/m/07yv9,/m/09x0r", "caption": "An engine running loudly and continuously together with muffled speech" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y1wW0YJQ-Xa0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1wW0YJQ-Xa0.npy", "labels": "/m/07qlf79,/m/09x0r", "caption": "A person coughing followed by a series of compressed air sprays as tin and plastic rattle then a man speaking as a crowd of people talk in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YBQ-r9mEHssU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBQ-r9mEHssU.npy", "labels": "/m/03k3r,/m/07rv9rh,/m/09x0r,/m/0jbk", "caption": "A woman laughs and talk as a hose clip-clops" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/YelztUCeNQvQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YelztUCeNQvQ.npy", "labels": "/m/0195fx,/m/01g50p,/m/0284vy3,/m/06d_3,/m/07jdr", "caption": "A train horn honking as a train runs on railroad tracks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part1/Y-oy0BkpMGAk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y-oy0BkpMGAk.npy", "labels": "/m/012f08,/m/07rknqz,/m/07yv9,/m/0k4j,/t/dd00134", "caption": "A motor vehicle is skidding and drifting" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part15/YGIOApFAWDOc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YGIOApFAWDOc.npy", "labels": "/m/015p6,/m/020bb7,/m/07pggtn", "caption": "Birds chirping and singing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YEzWEO2WD_MM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YEzWEO2WD_MM.npy", "labels": "/m/01d380", "caption": "A whirring followed by an object hitting a surface" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y2ABngPM3raQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y2ABngPM3raQ.npy", "labels": "/m/09ld4,/m/09x0r,/m/0jbk", "caption": "An adult male speaks while thumps occur in the background, then frogs croak and the adult male speaks again" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y2ErfX6ZT5pM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y2ErfX6ZT5pM.npy", "labels": "/m/01jt3m", "caption": "A toilet flushing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YHeEa1GZpUGI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YHeEa1GZpUGI.npy", "labels": "/m/032s66", "caption": "Semiautomatic gunfire then clicks of a magazine change followed by more gunfire" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part7/Y6BJ455B1aAs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y6BJ455B1aAs.npy", "labels": "/m/014zdl,/m/07qsvvw", "caption": "A whistling and then an explosion and crackling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YBA-lFjpzad4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBA-lFjpzad4.npy", "labels": "/m/012f08,/m/04_sv,/m/07yv9,/m/09x0r,/t/dd00134", "caption": "Motor vehicle traffic is ongoing, and a motorcycle engine accelerates and then decelerates in the foreground" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y8ycflE3dIHw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y8ycflE3dIHw.npy", "labels": "/m/01g50p,/m/0284vy3,/m/06d_3,/m/07jdr,/m/07rwm0c", "caption": "A train running on railroad tracks followed by a train horn honking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y6aWnK1GyeJY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y6aWnK1GyeJY.npy", "labels": "/m/0463cq4,/m/09x0r", "caption": "A baby is crying and a person sneezes then another person speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/YoN0IcZaHD_8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YoN0IcZaHD_8.npy", "labels": "/m/01d380,/m/07k1x,/m/083vt,/m/09x0r,/t/dd00125", "caption": "Male voice speaking briefly followed by drilling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/YzF3xXn6NTyU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YzF3xXn6NTyU.npy", "labels": "/m/0j6m2", "caption": "Water runs quickly, while someone talks, coughs, and then talks again close by" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/Yo7jW6Suyfbs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yo7jW6Suyfbs.npy", "labels": "/m/012f08,/m/07yv9,/m/0k4j,/m/0ltv", "caption": "A man talks in the distance followed by several vehicles driving and accelerating" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YPMMdAKZxI_I.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YPMMdAKZxI_I.npy", "labels": "/m/03q5_w,/m/09x0r", "caption": "Burping noise while a woman talks followed by a woman laughing with a television playing in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YU90e2P9jy30.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YU90e2P9jy30.npy", "labels": "/m/07pqc89,/m/09x0r", "caption": "A man yelling in the background as several basketballs bounce and shoes squeak on a hardwood surface" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part38/Yup2PpjTzyyc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yup2PpjTzyyc.npy", "labels": "/m/01yrx,/m/07qrkrw,/m/09x0r,/m/0jbk", "caption": "Man speaking with electronic sounds in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YI_vN_BFUr0Y.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YI_vN_BFUr0Y.npy", "labels": "/m/01g50p,/m/0284vy3,/m/04zmvq,/m/06d_3,/m/07jdr,/m/07yv9", "caption": "A train horn blowing as a train runs and railroad crossing signals ring in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part4/Y30D1tqNFHMc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y30D1tqNFHMc.npy", "labels": "/m/01jwx6,/m/0chx_", "caption": "Mechanical humming with several beeps" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/YfrOqlk0Wm5Y.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YfrOqlk0Wm5Y.npy", "labels": "/m/07pdjhy", "caption": "A man is speaking followed by saw blade noises" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YsCzRVvu9XeY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YsCzRVvu9XeY.npy", "labels": "/m/01w250", "caption": "Whistling a tune" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part7/Y5YzNSjmZ3Wg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y5YzNSjmZ3Wg.npy", "labels": "/m/01h3n,/m/09x0r", "caption": "A man speaking with a buzzing sound in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/Yj_NSuPnx5LA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yj_NSuPnx5LA.npy", "labels": "/m/07cx4", "caption": "Someone dials a push button phone melodically" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YBrPFQDr99Gg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBrPFQDr99Gg.npy", "labels": "/m/02qldy,/m/05zppz,/m/09x0r", "caption": "A crowd of people applauding as cheering followed by an elderly man speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YLvhvAA11oxE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YLvhvAA11oxE.npy", "labels": "/m/07yv9,/m/09x0r,/m/0h9mv,/m/0ltv,/t/dd00128", "caption": "Race cars are racing and skidding tires" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YFR7BDRhMATo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YFR7BDRhMATo.npy", "labels": "/m/06hck5,/m/06wzb,/m/07rjwbb", "caption": "A train running and the horn blowing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YWOywdRmySs0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YWOywdRmySs0.npy", "labels": "/m/09x0r,/t/dd00112", "caption": "A man talking followed by plastic crinkling and crumpling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YAUmY0YRAFQE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YAUmY0YRAFQE.npy", "labels": "/m/04qvtq,/m/07yv9,/m/0k4j,/t/dd00134", "caption": "Sirens ring as a vehicle speeds past" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YZ_smJ66Tb3c.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YZ_smJ66Tb3c.npy", "labels": "/m/015p6,/m/020bb7,/m/07r_25d,/m/0h0rv", "caption": "A man speaks as birds call and pigeons coo" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part0/Y-R69Fa-mCaY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y-R69Fa-mCaY.npy", "labels": "/m/01j4z9,/m/083vt", "caption": "A chainsaw cutting as wood cracks and creaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YJon_DEFqsfM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YJon_DEFqsfM.npy", "labels": "/m/020bb7,/m/06_y0by,/m/09ddx", "caption": "Birds chirping with distant humming" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part9/Y8OTd45_6cvY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y8OTd45_6cvY.npy", "labels": "/m/07qlf79", "caption": "Footsteps and intermittent spraying" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part27/Y_ezm-TpKj1w.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y_ezm-TpKj1w.npy", "labels": "/m/07q2z82,/m/09x0r,/m/0k4j", "caption": "A vehicle engine revving as a crowd of people talk in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YJHhEjsAkZoc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YJHhEjsAkZoc.npy", "labels": "/m/01g50p,/m/0284vy3,/m/06d_3,/m/07jdr,/m/07rwm0c", "caption": "A train is passing by and sound its whistle." }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part9/Y8GHLfJ6y6zA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y8GHLfJ6y6zA.npy", "labels": "/m/01m2v,/m/0316dw,/m/09x0r", "caption": "A person speaks followed by clicking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YDlWd7Wmdi1E.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YDlWd7Wmdi1E.npy", "labels": "/m/015p6,/m/07rc7d9,/m/09x0r,/m/0jbk", "caption": "A man speaking as monkeys scream and dogs bark followed by birds cawing in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YqF72bT878gw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YqF72bT878gw.npy", "labels": "/m/019jd,/m/02rlv9,/m/07yv9", "caption": "Humming from an engine with wind blowing hard" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/Yyau2WIRkxb8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yyau2WIRkxb8.npy", "labels": "/m/09ct_", "caption": "A small high frequency motor vibrates" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YLvMA1Wcgu3w.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YLvMA1Wcgu3w.npy", "labels": "/m/09ld4", "caption": "A man talking followed by plastic creaking and clacking as frogs croak and crickets chirp" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part38/Yvsy1IpYmrSY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yvsy1IpYmrSY.npy", "labels": "/m/0h9mv", "caption": "Engines hum and rev with squealing tires" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YR91bUbtKrRs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YR91bUbtKrRs.npy", "labels": "/m/09x0r,/t/dd00002", "caption": "Two women are talking, and a baby cries" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YbmEF-c-M174.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YbmEF-c-M174.npy", "labels": "/m/015p6,/m/09ddx,/m/09x0r", "caption": "Quacking with brief chirping and speech" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part27/YZsf2YvJfCKw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YZsf2YvJfCKw.npy", "labels": "/m/01jt3m", "caption": "Water gurgling followed by a toilet flushing then a footstep shuffling on a hard surface" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YEbpOXac13yo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YEbpOXac13yo.npy", "labels": "/m/01bjv,/m/07yv9,/m/09x0r", "caption": "Loud bus roaring and voices" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/Yo3mZR8OvPko.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yo3mZR8OvPko.npy", "labels": "/m/07yv9,/m/0k4j,/m/0ltv,/t/dd00128", "caption": "A racing vehicle accelerating and revving while tires skid and squeal" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YAJtNitYMa1I.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YAJtNitYMa1I.npy", "labels": "/m/07p9k1k,/m/0dxrf", "caption": "Food and oil sizzling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YQRtuOWWya30.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YQRtuOWWya30.npy", "labels": "/m/0dxrf", "caption": "Metal clacking followed by a man talking as metal rattles while light guitar music plays in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y2KEfkDO6hlA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y2KEfkDO6hlA.npy", "labels": "/m/012f08,/m/07yv9,/m/0k4j,/t/dd00134", "caption": "Humming of an accelerating engine with rustling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y7D7xgd4WJ50.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y7D7xgd4WJ50.npy", "labels": "/m/0395lw", "caption": "A medium-pitched, metal bell is ringing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part24/YVQnmlf2OsUg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YVQnmlf2OsUg.npy", "labels": "/m/09ct_", "caption": "Helicopter rotors are turning." }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y52IxrdTxGs4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y52IxrdTxGs4.npy", "labels": "/m/07qsvvw,/m/09x0r", "caption": "A quick loud explosion as music plays with pulsating sounds followed by a man talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YB-gTt3_rceQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YB-gTt3_rceQ.npy", "labels": "/m/09x0r,/m/0ytgt,/t/dd00125", "caption": "Small child with a man and woman speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YUAmDLPjNyMg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YUAmDLPjNyMg.npy", "labels": "/m/07yv9,/m/0cmf2,/m/0k5j", "caption": "Humming of a distant large engine with wind blowing hard" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YLKhokVsJhN0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YLKhokVsJhN0.npy", "labels": "/m/07bgp,/m/0ch8v,/m/0jbk", "caption": "A group of sheep are baaing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/Ye4ph6bIC5zc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ye4ph6bIC5zc.npy", "labels": "/m/012f08,/m/07yv9,/m/0k4j,/m/0ltv", "caption": "People are communicating followed by a dog barking and a vehicle moving" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YTWOgvDaDqlU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YTWOgvDaDqlU.npy", "labels": "/m/083vt", "caption": "A power tool sawing wood followed by a machine motor running while cutting wood" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3rna9zo5ZOs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3rna9zo5ZOs.npy", "labels": "/m/02qldy,/m/05zppz,/m/09x0r", "caption": "A man speaking while a large crowd cheers in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YqZEIs6tS5vk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YqZEIs6tS5vk.npy", "labels": "/m/07r04,/m/07rknqz,/m/07yv9", "caption": "A vehicle engine revving followed by tires skidding as a group of people talk in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YObWjGBJF_94.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YObWjGBJF_94.npy", "labels": "/m/02jz0l,/m/07ptzwd", "caption": "Hissing and rattling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part19/YMvHpNzDpC6Q.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YMvHpNzDpC6Q.npy", "labels": "/m/012f08,/m/03q5_w,/m/07yv9,/m/09x0r,/m/0k4j", "caption": "Men riding in the car talking then man burps loudly and then the other chuckles" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part15/YFi4-IqJo2xQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YFi4-IqJo2xQ.npy", "labels": "/m/02mk9,/m/07rqsjt,/m/07yv9,/m/0k4j", "caption": "Humming and rattling from a revving engine" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YsTMKled6Q1M.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YsTMKled6Q1M.npy", "labels": "/m/015p6,/m/0h0rv,/t/dd00129", "caption": "Whistling with wings flapping, birds chirping, and pigeons cooing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4xrL4TSgHwU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4xrL4TSgHwU.npy", "labels": "/m/02mk9,/m/07pb8fc,/m/07q2z82,/m/07yv9,/t/dd00066,/t/dd00130", "caption": "Loud banging followed by chugging engine" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YtNxfdAd14qE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YtNxfdAd14qE.npy", "labels": "/m/07p9k1k", "caption": "Mechanical rotation and then a loud click occurs" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part1/Y0Rpjl1AO-P0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y0Rpjl1AO-P0.npy", "labels": "/m/07yv9,/m/0k4j,/t/dd00134", "caption": "A motor vehicle engine is running and vibrating, and it accelerates and then idles" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part9/Y8IdCiapDYCU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y8IdCiapDYCU.npy", "labels": "/m/068hy,/m/07rc7d9,/m/0bt9lr,/m/0jbk", "caption": "A dog growling while an electronic toy mimics laughter followed by a plastic thud then small dog barking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/YhVUmQfBIYe8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YhVUmQfBIYe8.npy", "labels": "/m/02dgv", "caption": "Something jangles then someone begins speaking then a door clanks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part0/Y-FW109cbv0g.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y-FW109cbv0g.npy", "labels": "/m/01hsr_,/m/09x0r", "caption": "Speech and then a sneeze and laughter" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YcK2kSVR1d2o.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YcK2kSVR1d2o.npy", "labels": "/m/07qsvvw,/m/0g6b5", "caption": "Popping and cracking followed by a loud burst" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YqZEIs6tS5vk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YqZEIs6tS5vk.npy", "labels": "/m/07r04,/m/07rknqz,/m/07yv9", "caption": "An engine revving and then tires screeching" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part27/Ya3GzZKxUTy8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ya3GzZKxUTy8.npy", "labels": "/m/015p6,/m/09ddx,/m/0bt9lr,/m/0jbk", "caption": "Birds chirping and then a dog barking and a duck quaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YD9tinq3RMpU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YD9tinq3RMpU.npy", "labels": "/m/019jd,/m/02rlv9,/m/07yv9,/m/09x0r", "caption": "A ship engine running as a crowd of people talk followed by a ship hull creaking as wind blows heavily into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YsI7_ycEYzAY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YsI7_ycEYzAY.npy", "labels": "/m/07qjznl,/m/07qjznt", "caption": "A clock ticks low and loud and someone breathes sharply near the end" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YKJhGuhNHToA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YKJhGuhNHToA.npy", "labels": "/m/083vt", "caption": "Wood scrapping against a stone surface" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/YzFzPOsOKog4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YzFzPOsOKog4.npy", "labels": "/m/01h3n,/m/03vt0,/m/0h2mp", "caption": "Wood thumping and a series of metal clanks while a swarm of insects are buzzing and birds chirp in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y0rSETXszQM0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y0rSETXszQM0.npy", "labels": "/m/028v0c,/m/04_sv,/m/07yv9,/t/dd00128", "caption": "Motorcycle starting and taking off" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4pv3w--cRrA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4pv3w--cRrA.npy", "labels": "/m/09t49", "caption": "An electric motor runs then a person speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YlX3k5p2I_g0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YlX3k5p2I_g0.npy", "labels": "/m/014yck,/m/02mk9,/m/07yv9,/m/09x0r,/m/0cmf2,/m/0k5j", "caption": "A man talking followed by another man yelling in the background then an aircraft engine starting up as vehicles drive by" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/YzoctgurhvHE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YzoctgurhvHE.npy", "labels": "/m/012f08,/m/02dgv,/m/04gxbd,/m/07yv9", "caption": "A series of plastic clanking followed by a car door opening then a vehicle engine accelerating in the distance while a man is talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YKVbmN9ZRg5Q.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YKVbmN9ZRg5Q.npy", "labels": "/m/01g50p,/m/0284vy3,/m/06d_3,/m/07jdr,/m/07rwm0c", "caption": "A train running on railroad tracks followed by a train horn blowing and steam hissing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YEfk5kdn9lR8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YEfk5kdn9lR8.npy", "labels": "/m/02dgv,/m/02y_763,/m/09x0r", "caption": "A young girl talking then screaming as plastic crashes and tumbles followed by a plastic camera click" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/Yc0IggDOisOo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yc0IggDOisOo.npy", "labels": "/m/0395lw,/m/09x0r", "caption": "A church bell rings as a group of people talk in the background and wind blows into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3fomsZXG3aM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3fomsZXG3aM.npy", "labels": "/m/07q2z82,/m/07yv9,/t/dd00066", "caption": "An engine humming and ticking as it idles then revs" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4YMXgLFcR94.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4YMXgLFcR94.npy", "labels": "/m/02qldy,/m/05zppz,/m/09x0r", "caption": "A man speaks followed by applause" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YCBwXKOpJY_o.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YCBwXKOpJY_o.npy", "labels": "/m/01h8n0,/m/02zsn,/m/09x0r,/m/0ytgt", "caption": "A woman and young boy talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3IguMJkqpl4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3IguMJkqpl4.npy", "labels": "/m/07qdb04,/m/09ddx,/m/09x0r", "caption": "Duck quacking and man and woman talking while baby cries" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YLB6CZ0x-kns.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YLB6CZ0x-kns.npy", "labels": "/m/07r04,/m/07yv9,/t/dd00128", "caption": "A motor vehicle is accelerating followed by thumping and hissing noises" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part9/Y8o-Y4QP8LWs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y8o-Y4QP8LWs.npy", "labels": "/m/023pjk,/m/04brg2", "caption": "Banging and rattling with a man speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YI_8KqxP5xOA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YI_8KqxP5xOA.npy", "labels": "/m/07qlf79", "caption": "A sprayer is spraying surfaces" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YOpiWMltpj44.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YOpiWMltpj44.npy", "labels": "/m/015p6,/m/09ddx,/m/0dbvp", "caption": "Ducks are quaking along with geese honking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YJBWJQCS4SvA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YJBWJQCS4SvA.npy", "labels": "/m/034srq,/m/03m9d0z,/m/05kq4,/t/dd00092", "caption": "Seagulls squawking as ocean waves crash while wind blows heavily into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/Yoklu5ZJD_2U.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yoklu5ZJD_2U.npy", "labels": "/m/015p6,/m/068hy,/m/07pggtn", "caption": "Plastic tapping then rattling as a bird chirps" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YNi3dIj90Oa4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YNi3dIj90Oa4.npy", "labels": "/m/032s66", "caption": "Explosion followed by man speaking a short bit of music at the end" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/YjinJkonlrWc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YjinJkonlrWc.npy", "labels": "/m/09ct_,/m/09x0r", "caption": "A man speaks with a small motor buzzing and wind blowing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YBa92IrXFvJo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBa92IrXFvJo.npy", "labels": "/m/019jd,/m/02rlv9,/m/07yv9", "caption": "Cracking and humming from an engine" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YAKHZMg9ba30.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YAKHZMg9ba30.npy", "labels": "/m/07rv9rh,/m/09x0r,/m/0jbk", "caption": "A man talking in the foreground as another man laughs then talks in the background while a horse trots and snorts" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YJQz40TkjymY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YJQz40TkjymY.npy", "labels": "/m/01m2v,/m/0316dw", "caption": "Typing on a computer keyboard" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y6pssFJ0m-kU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y6pssFJ0m-kU.npy", "labels": "/m/015p6,/m/020bb7,/m/07pggtn", "caption": "White noise and then birds chirping." }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YKnXNy5Q6YS4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YKnXNy5Q6YS4.npy", "labels": "/m/01h3n,/m/03vt0,/m/09x0r", "caption": "Men speak as insects buzz" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YErxgH5g3Kx0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YErxgH5g3Kx0.npy", "labels": "/m/03k3r,/m/07rv9rh,/m/0jbk", "caption": "Metal clinking with faint clip-clops of a horse" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YQRtuOWWya30.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YQRtuOWWya30.npy", "labels": "/m/0dxrf", "caption": "Something bangs and clicks then a man talks and scrapes something" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YS0SQyFXbqF8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YS0SQyFXbqF8.npy", "labels": "/m/09ld4", "caption": "A woman speaking and person laughing followed by some gurgling and squeaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YmW1EpJYcy_E.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YmW1EpJYcy_E.npy", "labels": "/m/04_sv,/m/07yv9,/t/dd00128", "caption": "A motorbike accelerating and revving as wind blows into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part0/Y-mb4Fw4Z0xg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y-mb4Fw4Z0xg.npy", "labels": "/m/012f08,/m/07yv9,/m/09x0r,/m/0k4j,/t/dd00134", "caption": "A car engine accelerating and then laughter" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part1/Y0NGSrwioYjA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y0NGSrwioYjA.npy", "labels": "/m/03fwl,/m/068hy,/m/09ld4,/m/09x0r,/m/0jbk", "caption": "A man speaking followed by a goat baaing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part7/Y5YzNSjmZ3Wg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y5YzNSjmZ3Wg.npy", "labels": "/m/01h3n,/m/09x0r", "caption": "A man speaking as an insect is buzzing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part4/Y32565FEuksc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y32565FEuksc.npy", "labels": "/m/02qldy,/m/02zsn,/m/09x0r", "caption": "A woman speaking as a crowd of people applaud" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y59VP93Tzjmg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y59VP93Tzjmg.npy", "labels": "/m/01g50p,/m/0284vy3,/m/06d_3,/m/07jdr", "caption": "Distant honks of a train horn with leaves rustling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YE3D_z0aoUEg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YE3D_z0aoUEg.npy", "labels": "/m/07st88b,/m/09ld4", "caption": "Crickets chirping very loudly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YNi3dIj90Oa4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YNi3dIj90Oa4.npy", "labels": "/m/032s66", "caption": "A few gunshots followed by a man speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/YyRoKi7rhSRo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YyRoKi7rhSRo.npy", "labels": "/m/01jt3m,/m/0838f", "caption": "A toilet flushes and water drains" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YLs2vrr9TamU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YLs2vrr9TamU.npy", "labels": "/m/083vt", "caption": "Drilling and crackling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/YoNHCc_izsDE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YoNHCc_izsDE.npy", "labels": "/m/01j3sz,/m/07rrlb6", "caption": "A baby laughing and splashing and a female laughing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/Yc0IggDOisOo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yc0IggDOisOo.npy", "labels": "/m/0395lw,/m/09x0r", "caption": "Birds chirping, wind blowing, and a bell ringing with faint speech" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YLbken4JCr94.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YLbken4JCr94.npy", "labels": "/m/06mb1,/m/0jb2l,/m/0ngt1", "caption": "Rolling thunder with lightning strikes" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YFc9pG54DDJM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YFc9pG54DDJM.npy", "labels": "/m/01jt3m,/m/0838f", "caption": "A toilet flushing followed by paper crinkling and a door slamming in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YHkbCUN4V3TU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YHkbCUN4V3TU.npy", "labels": "/m/09x0r,/m/0ytgt,/t/dd00125", "caption": "A girl screams and people speak" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YQOmV7O9mFwg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YQOmV7O9mFwg.npy", "labels": "/m/01bjv,/m/07yv9,/m/09x0r", "caption": "Laughter with people talking in the background and a girl talks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YawxrHOpt-sE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YawxrHOpt-sE.npy", "labels": "/m/03fwl,/m/09x0r,/m/0ch8v,/m/0jbk", "caption": "People speak and a goat screams" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YAI1OweEW8C0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YAI1OweEW8C0.npy", "labels": "/m/06mb1,/m/07r10fb,/m/0jb2l,/m/0ngt1", "caption": "Rain falling and dripping from a roof, then thunder rolls" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/YpTJKJxaheI8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YpTJKJxaheI8.npy", "labels": "/m/07qjznl,/m/07qjznt", "caption": "A man speaks with faint ticks of a clock" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part15/YG3YO2unWz7k.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YG3YO2unWz7k.npy", "labels": "/m/04_sv,/m/07yv9,/t/dd00128", "caption": "Sputtering of an idling and revving engine" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9MgGaTbmc6g.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9MgGaTbmc6g.npy", "labels": "/m/02mk9,/m/07q2z82,/m/07yv9,/m/0k4j,/t/dd00066", "caption": "An engine revving and tires squealing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YTSnq6n8tElo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YTSnq6n8tElo.npy", "labels": "/m/0242l,/m/04brg2", "caption": "A man yells, followed by a banging sound and a coin dropping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/YonBZOH88OYs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YonBZOH88OYs.npy", "labels": "/m/07qlf79", "caption": "Short bursts of spraying" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YPRUfwpmYwJ8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YPRUfwpmYwJ8.npy", "labels": "/m/07qlf79,/m/09x0r", "caption": "A man talking as a series of compressed air sprays" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y1FNJbN-eHY4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1FNJbN-eHY4.npy", "labels": "/m/03q5_w,/m/09x0r", "caption": "A group of kids burping and laughing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part0/Y-Sz4z0QwEuM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y-Sz4z0QwEuM.npy", "labels": "/m/03q5_w", "caption": "A long burp ends in a sigh" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part19/YMOxddxW5PXs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YMOxddxW5PXs.npy", "labels": "/m/09x0r,/m/0dxrf", "caption": "A man speaks accompanied by sizzling and tapping as food is fried" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y1IoHRTUp86c.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1IoHRTUp86c.npy", "labels": "/m/07yv9,/m/0k5j,/t/dd00129", "caption": "A muffled aircraft engine running before accelerating as a woman talks over an intercom" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y6pssFJ0m-kU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y6pssFJ0m-kU.npy", "labels": "/m/015p6,/m/020bb7,/m/07pggtn", "caption": "Leaves rustle in the wind as small birds chirp" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YaZAXO2WZn84.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YaZAXO2WZn84.npy", "labels": "/m/06wzb,/m/07rjwbb", "caption": "A train running on railroad tracks as a bell chimes followed by a lawn mower engine running then a steam engine operating as steam hisses and a train whistle blows while a crowd of people talk in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/YzFzPOsOKog4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YzFzPOsOKog4.npy", "labels": "/m/01h3n,/m/03vt0,/m/0h2mp", "caption": "Bees buzz as clanking occurs" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YBOB65Nd0pXo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBOB65Nd0pXo.npy", "labels": "/m/02l6bg,/m/07yv9,/m/09ct_", "caption": "Strong wind is blowing, an aircraft motor is operating, and metallic whirring and faint rotor slapping are present" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y77nElZGi5NU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y77nElZGi5NU.npy", "labels": "/m/07qsvvw,/m/09x0r", "caption": "Wind blowing hard with a loud explosion and people laughing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y7P6lcyeDKNI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y7P6lcyeDKNI.npy", "labels": "/m/0199g,/m/04_sv,/m/07yv9,/m/09x0r", "caption": "Walking on gravel and then a man speaks briefly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y7P0N61TVOxE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y7P0N61TVOxE.npy", "labels": "/m/034srq,/m/03m9d0z,/m/05kq4,/m/085jw", "caption": "Music plays over an engine noise" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YTgxst7Ft9js.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YTgxst7Ft9js.npy", "labels": "/m/02p01q,/m/07pdjhy", "caption": "Rustling and rubbing followed by male speech" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y1wW0YJQ-Xa0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1wW0YJQ-Xa0.npy", "labels": "/m/07qlf79,/m/09x0r", "caption": "People speak and traffic passes in the distance with a nearby cough followed by rattling and spraying" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y7XXSOzDQ2z0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y7XXSOzDQ2z0.npy", "labels": "/m/07yv9,/m/0h9mv,/m/0k4j,/m/0ltv", "caption": "A race car engine is idling and then the car accelerates away quickly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y7XUt6sQS7nM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y7XUt6sQS7nM.npy", "labels": "/m/07bgp,/m/07q0h5t,/m/09x0r", "caption": "A sheep is bleating and a crowd is murmuring" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YI_8KqxP5xOA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YI_8KqxP5xOA.npy", "labels": "/m/07qlf79", "caption": "Spraying fades in and out while clicking occurs" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YB8rdur4aams.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YB8rdur4aams.npy", "labels": "/m/07yv9,/m/0912c9,/t/dd00128", "caption": "Rustling and shaking followed by a horn and gusts of wind" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/YeXj9OAik5cc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YeXj9OAik5cc.npy", "labels": "/m/04_sv,/m/07yv9,/t/dd00128", "caption": "An engine idling with light wind" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y1vCYiVvZ7VE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1vCYiVvZ7VE.npy", "labels": "/m/02qldy,/m/02zsn,/m/09x0r", "caption": "A woman speeches" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/Yram-QPKSQYc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yram-QPKSQYc.npy", "labels": "/m/09ct_", "caption": "A helicopter flies with spinning blades" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y41D0yXSBqfI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y41D0yXSBqfI.npy", "labels": "/m/015p6,/m/0h0rv,/t/dd00125", "caption": "Pigeons coo with some rustling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part15/YGkb4f6yodPE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YGkb4f6yodPE.npy", "labels": "/m/01b82r,/m/07pdjhy,/m/083vt", "caption": "Tapping followed by high pitched buzzing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YWCYfCfW9NA0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YWCYfCfW9NA0.npy", "labels": "/m/07yv9,/m/09ct_,/t/dd00129", "caption": "Blades of a helicopter spinning and getting ready to take off" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YW7OJevEgq7w.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YW7OJevEgq7w.npy", "labels": "/m/05tny_,/m/068hy,/m/07rc7d9,/m/0bt9lr,/m/0jbk", "caption": "A dog whimpering and barking while breathing rapidly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YXf5LjaE_JQ0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YXf5LjaE_JQ0.npy", "labels": "/m/07qlf79,/m/09x0r", "caption": "Traffic sounds going by as man speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/YdmUOSyPXkUw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YdmUOSyPXkUw.npy", "labels": "/m/06wzb,/m/07rjwbb", "caption": "A train makes hissing sound followed by people speaking lowly in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4IeDBwyQ9ZQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4IeDBwyQ9ZQ.npy", "labels": "/m/04brg2", "caption": "Clinking and rustling followed by a woman speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4fz0-Kx2oNs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4fz0-Kx2oNs.npy", "labels": "/m/0dxrf", "caption": "A continuous sizzling with oil popping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part7/Y5K1mISHwggI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y5K1mISHwggI.npy", "labels": "/m/02mk9,/m/07yv9,/m/09x0r", "caption": "A man speaking with distant hums and horns of passing traffic" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/YdYZSKX7vuRI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YdYZSKX7vuRI.npy", "labels": "/m/01d3sd,/m/09x0r", "caption": "Loud snoring followed by brief silence then speech" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YCchRf2jq6fc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YCchRf2jq6fc.npy", "labels": "/m/02qldy,/m/02zsn,/m/09x0r", "caption": "A young woman talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YL_CNz9Vrtkw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YL_CNz9Vrtkw.npy", "labels": "/m/028ght,/m/09x0r", "caption": "A man speaks followed by a crowd applauding" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YtJhVH3VIrnE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YtJhVH3VIrnE.npy", "labels": "/m/02dgv", "caption": "Wood cracking and metal clanking with a series of hammering on a wooden surface" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YmSF_FqBtRPs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YmSF_FqBtRPs.npy", "labels": "/m/01hnzm,/m/07cx4", "caption": "A telephone ringing with loud echo" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YO90Qy2xG6oA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YO90Qy2xG6oA.npy", "labels": "/m/068hy,/m/0jbk,/t/dd00002", "caption": "A bird cawing as an infant is crying" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YXZTt1xdK8uQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YXZTt1xdK8uQ.npy", "labels": "/m/07swgks", "caption": "An engine is accelerating" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YmlnUJH4BQnk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YmlnUJH4BQnk.npy", "labels": "/m/07pdjhy", "caption": "Female speech and rubbing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YbhlhcGONisM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YbhlhcGONisM.npy", "labels": "/m/0316dw,/m/09x0r", "caption": "Man talking and a tapping clicking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part9/Y8BPTQO_cx7E.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y8BPTQO_cx7E.npy", "labels": "/m/028ght", "caption": "A man speaks and then a crowd breaks into applause and laughter" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/YpPLisQ_QXxw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YpPLisQ_QXxw.npy", "labels": "/m/07yv9,/m/0912c9,/m/0k4j", "caption": "An engine running and a horn" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part27/Y_iUX8CibElk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y_iUX8CibElk.npy", "labels": "/m/0ngt1", "caption": "Does not sound like anything but static" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/YwBs02amFGXs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YwBs02amFGXs.npy", "labels": "/m/015p6,/m/0h0rv,/t/dd00125,/t/dd00129", "caption": "A rooster crowing and birds cooing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/YglAeihz0NAM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YglAeihz0NAM.npy", "labels": "/m/09x0r,/m/0ytgt,/t/dd00129", "caption": "A child speaking and then an adult speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YRk-ujWKzPuc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YRk-ujWKzPuc.npy", "labels": "/m/06mb1,/t/dd00038", "caption": "Continuous rainfall" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y473wBEwC35M.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y473wBEwC35M.npy", "labels": "/m/02qldy,/m/05zppz,/m/09x0r", "caption": "Male speech with horns honking in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3XcIVh40pTI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3XcIVh40pTI.npy", "labels": "/m/01d3sd", "caption": "A person is snoring steadily" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9U8COLzEegs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9U8COLzEegs.npy", "labels": "/m/02fs_r,/m/09x0r", "caption": "A man speaking and item beeping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YEY4p0_NJVQs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YEY4p0_NJVQs.npy", "labels": "/m/02qldy,/m/02zsn,/m/09x0r", "caption": "A female speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YZ7yDwpdGelM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YZ7yDwpdGelM.npy", "labels": "/m/07pqc89,/m/09x0r", "caption": "Water trickling, plastic crinkling, followed by a male speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YnD1K1Zo0qrM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YnD1K1Zo0qrM.npy", "labels": "/m/032s66,/m/04zjc", "caption": "An aircraft engine operates and whooshing is ongoing while a machine gun clicks and fires, after which music plays" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part15/YGPj8h-WcjWs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YGPj8h-WcjWs.npy", "labels": "/m/01bjv,/m/07yv9,/m/09x0r", "caption": "Bus engine going then an announcers female voice speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part7/Y6Nvu6EcpdE8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y6Nvu6EcpdE8.npy", "labels": "/m/07pb8fc,/m/07yv9,/m/09x0r,/t/dd00130", "caption": "Wind blows and a man speaks with a quick pop" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y1j5NMuq1X30.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1j5NMuq1X30.npy", "labels": "/m/07qlf79", "caption": "High pressure liquid spraying as a radio plays in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/Ys_EWjoiVfzo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ys_EWjoiVfzo.npy", "labels": "/m/0llzx", "caption": "A sewing machine hums and operates several times before a metal click" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part9/Y8F-ndyrEWJ8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y8F-ndyrEWJ8.npy", "labels": "/m/012n7d,/m/03j1ly,/m/03kmc9", "caption": "A distant police siren, then racing car engine noise, and a man calling in police code over his radio" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part24/YV8A0VRGdgwM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YV8A0VRGdgwM.npy", "labels": "/m/03fwl,/m/07q0h5t,/m/0ch8v,/m/0jbk", "caption": "Pebbles and rocks bouncing off of a wooden surface as footsteps walk on gravel and dirt followed by a goat baaing as a muffled animal moan in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YIFRmbxWK8u0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YIFRmbxWK8u0.npy", "labels": "/m/07qjznl", "caption": "A clock ticking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y7P0N61TVOxE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y7P0N61TVOxE.npy", "labels": "/m/034srq,/m/03m9d0z,/m/05kq4,/m/085jw", "caption": "A band plays horn and string instruments while waves crash nearby" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y2EsxcKe1A4w.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y2EsxcKe1A4w.npy", "labels": "/m/068hy,/m/07rc7d9,/m/09x0r,/m/0bt9lr,/m/0jbk", "caption": "A dog barking followed by a man talking in the distance while gravel and dirt shuffle during a series of camera muffles" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/Yt3VFlDiEKgY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yt3VFlDiEKgY.npy", "labels": "/m/03vt0,/m/09f96,/m/0h2mp", "caption": "Mosquitoes are buzzing, and a man speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part38/YvaujJ7msKfc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YvaujJ7msKfc.npy", "labels": "/m/012n7d,/m/03j1ly,/m/03kmc9", "caption": "City ambiance with light music playing in the background followed by police sirens sounding in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9U8COLzEegs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9U8COLzEegs.npy", "labels": "/m/02fs_r,/m/09x0r", "caption": "Water pours, a horn honks, and a man speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part7/Y63KW_EQ72yU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y63KW_EQ72yU.npy", "labels": "/m/014zdl,/m/07qsvvw", "caption": "A loud explosion as gusts of wind blow" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YajheseWZmmU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YajheseWZmmU.npy", "labels": "/m/01yrx,/m/07qrkrw,/m/0jbk", "caption": "A cat meowing as a person makes kissing noises followed by a guy chuckling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YYH4qi8Ul6v0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YYH4qi8Ul6v0.npy", "labels": "/m/09x0r,/t/dd00002", "caption": "A man talking as an infant is crying followed by a man humming" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YJdFmMw0zyKA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YJdFmMw0zyKA.npy", "labels": "/m/01j3sz,/m/09x0r", "caption": "A child speaking followed by a seal speaking then water splashing as a kid and woman laugh in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YIsUG5SKWNZA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YIsUG5SKWNZA.npy", "labels": "/m/09x0r,/t/dd00002", "caption": "A woman whispering then talking as an infant cries followed by a man yelling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YkXjzsroVTtw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YkXjzsroVTtw.npy", "labels": "/m/020bb7,/m/07pggtn,/m/09x0r", "caption": "A man speaks with small birds chirping in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YIPfaRF76gVU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YIPfaRF76gVU.npy", "labels": "/m/012ndj,/m/03j1ly,/m/07r04,/m/07yv9,/m/09x0r", "caption": "A truck engine driving by while emergency sirens wail as a crowd of people talk followed by a man speaking over an intercom" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YDt53UZgyznE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YDt53UZgyznE.npy", "labels": "/m/09x0r,/t/dd00002", "caption": "An kid crying followed by a man shouting" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y6i5eQOpFk_U.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y6i5eQOpFk_U.npy", "labels": "/m/0130jx,/m/02jz0l,/m/0838f", "caption": "Plastic clanking before and after a man talking as water flows from a faucet while a child talks in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YbAqgL5dCQOE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YbAqgL5dCQOE.npy", "labels": "/m/06mb1,/m/07r10fb,/t/dd00038", "caption": "Rain falls, tapping on metal, a vehicle runs in the distance, the tapping sound fades as the rain continues" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3IScngdQA4I.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3IScngdQA4I.npy", "labels": "/m/02dgv,/m/09x0r", "caption": "A woman speaks in a high pitch" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/Yr2KhpX_QgXA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yr2KhpX_QgXA.npy", "labels": "/m/02mk9,/m/02x984l,/m/09x0r", "caption": "An engine running with a male speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YcK2kSVR1d2o.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YcK2kSVR1d2o.npy", "labels": "/m/07qsvvw,/m/0g6b5", "caption": "Rustling and then a gunshot" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YYIqpIjjee00.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YYIqpIjjee00.npy", "labels": "/m/01jt3m", "caption": "Hissing and gurgling of water flowing down a toilet" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YsCzRVvu9XeY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YsCzRVvu9XeY.npy", "labels": "/m/01w250", "caption": "Musical whistling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YROootH-mtEI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YROootH-mtEI.npy", "labels": "/m/0j6m2", "caption": "A river stream flowing rapidly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/Yii3Geza3hAU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yii3Geza3hAU.npy", "labels": "/m/0llzx", "caption": "A sewing machine stitches rapidly then slows and then returns to rapid sewing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y1Uh74_rZ72k.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1Uh74_rZ72k.npy", "labels": "/m/07swgks", "caption": "Wind blows hard" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YlTJLvSvjUZk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YlTJLvSvjUZk.npy", "labels": "/m/01w250", "caption": "Whistling with music playing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/YxUWSHYoslPQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YxUWSHYoslPQ.npy", "labels": "/m/04brg2,/m/09x0r", "caption": "A male speech and dishes clanking and doors banging" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YE3Q1jfTeuWs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YE3Q1jfTeuWs.npy", "labels": "/t/dd00002", "caption": "A baby crying followed by heavy breathing and some light rattling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y6pssFJ0m-kU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y6pssFJ0m-kU.npy", "labels": "/m/015p6,/m/020bb7,/m/07pggtn", "caption": "Birds singing outdoors" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/Yyrxa6_P2I80.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yyrxa6_P2I80.npy", "labels": "/m/015p6,/m/0h0rv,/t/dd00129", "caption": "Several birds chirping and pigeons cooing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4YodC6RnplI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4YodC6RnplI.npy", "labels": "/m/01d3sd", "caption": "A female laughs, snoring occurs, and an adult male speaks in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3IguMJkqpl4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3IguMJkqpl4.npy", "labels": "/m/07qdb04,/m/09ddx,/m/09x0r", "caption": "A child cries and a man and woman speaking with a duck quacking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YbIiiIo20PsY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YbIiiIo20PsY.npy", "labels": "/m/01h3n,/m/09x0r", "caption": "Two men speak while bees buzz" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3xDZ-kdGE3o.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3xDZ-kdGE3o.npy", "labels": "/m/01jt3m,/m/0838f", "caption": "Footsteps then a toilet flushing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YR4fXcbWFhJg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YR4fXcbWFhJg.npy", "labels": "/m/03k3r,/m/09x0r,/m/0ch8v,/m/0jbk,/t/dd00129", "caption": "Horses run in the distance then a man speaks and a woman cheers then talks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/Yrp3CQsWxVgE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yrp3CQsWxVgE.npy", "labels": "/m/07yv9,/m/0912c9,/m/0k4j,/t/dd00128", "caption": "Traffic is present nearby, and a car horn plays the theme to the godfather" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YqF72bT878gw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YqF72bT878gw.npy", "labels": "/m/019jd,/m/02rlv9,/m/07yv9", "caption": "A water vehicle is traveling across water" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YkHIe4CfaccQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YkHIe4CfaccQ.npy", "labels": "/m/03fwl,/m/068hy,/m/0ch8v,/m/0jbk", "caption": "Continuous basing and rustling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YBGEMgl1xjac.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBGEMgl1xjac.npy", "labels": "/m/03vt0,/m/06hps,/m/09xqv", "caption": "Birds chirping with an animal clicking and calling out as crickets chirp" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YCMNlIW6Lkwc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YCMNlIW6Lkwc.npy", "labels": "/m/014zdl,/m/07qsvvw,/m/09x0r", "caption": "A man is talking while plastic clacks followed by a popping explosion then a group of people talking and laughing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part38/YvfNKduToki4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YvfNKduToki4.npy", "labels": "/m/07r04,/m/07yv9,/m/09x0r", "caption": "Truck engines are running, a shrill back-up alarm rings, air brakes engage, and adult males are talking in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/YwSHzVxdMiTo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YwSHzVxdMiTo.npy", "labels": "/m/09x0r,/t/dd00018", "caption": "Squealing from a pig" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YSNy_axSCoyw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YSNy_axSCoyw.npy", "labels": "/m/07qjznl", "caption": "A clock ticking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/YpCQEWAFGEjc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YpCQEWAFGEjc.npy", "labels": "/m/06wzb,/m/07rjwbb", "caption": "A train is making a hissing and chugging sound with people communicating in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YQt0_xTadAT0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YQt0_xTadAT0.npy", "labels": "/m/09ld4", "caption": "A group of frogs croaking as plastic flutters in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YZYWCwfCkBp4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YZYWCwfCkBp4.npy", "labels": "/m/01b82r,/m/07pdjhy,/m/083vt", "caption": "Wood sawing and metal filing as orchestral music plays in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YbX2vDaHL26U.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YbX2vDaHL26U.npy", "labels": "/m/07rknqz,/m/07yv9,/m/0k4j,/m/0ltv", "caption": "A car skidding its tires and racing away" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part19/YMtK8L8gXRrI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YMtK8L8gXRrI.npy", "labels": "/m/01jt3m", "caption": "Footsteps shuffling followed a cat meowing then a toilet flushing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part19/YMkbP_8zJwXU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YMkbP_8zJwXU.npy", "labels": "/m/015p6,/m/068hy,/m/09ddx,/t/dd00129", "caption": "Water trickling then splashing as a bird is chirping and wind is blowing into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YOxUVcZmeiyI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YOxUVcZmeiyI.npy", "labels": "/m/07qjznl,/m/07qjznt", "caption": "A clock ticktocks with music" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y1OyEgzXCkYE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1OyEgzXCkYE.npy", "labels": "/m/02qldy,/m/05zppz,/m/09x0r", "caption": "A man speaking into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3IScngdQA4I.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3IScngdQA4I.npy", "labels": "/m/02dgv,/m/09x0r", "caption": "A door shutting and a female speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part38/Yu84FiZ_omhA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yu84FiZ_omhA.npy", "labels": "/m/015p6,/m/07pggtn,/m/0jbk", "caption": "Person singing a long note and birds chirping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/YhJtOGmN_KVw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YhJtOGmN_KVw.npy", "labels": "/m/09x0r,/t/dd00112,/t/dd00125", "caption": "Plastic crinkling as a man is talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part27/Y_oKXrY5Ff0g.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y_oKXrY5Ff0g.npy", "labels": "/m/01j3sz,/m/09x0r", "caption": "Speech and laughter from many people" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YnLZeG9LaLgw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YnLZeG9LaLgw.npy", "labels": "/m/07yv9,/m/0k4j,/m/0ltv", "caption": "An engine revving" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/Ynq0BF9zGkzg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ynq0BF9zGkzg.npy", "labels": "/m/09x0r,/t/dd00018", "caption": "An animal cries, followed by a crash, then two people speak with one another" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/Yo3mZR8OvPko.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yo3mZR8OvPko.npy", "labels": "/m/07yv9,/m/0k4j,/m/0ltv,/t/dd00128", "caption": "A car engine revving and the squealing of tires" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part24/YW4GEwnXc9tQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YW4GEwnXc9tQ.npy", "labels": "/m/09ld4", "caption": "While music plays in the background, a frog croaks, young females speak and laugh, and a young male speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YRp4Ct_TQvAM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YRp4Ct_TQvAM.npy", "labels": "/m/06mb1,/m/09x0r", "caption": "Rain falling as a machine engine hums followed by a man talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YK-7Y8yhcUiw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YK-7Y8yhcUiw.npy", "labels": "/m/01d3sd,/m/068hy,/m/0bt9lr,/m/0jbk", "caption": "Repetitive snoring" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part1/Y-nQHwrRLfc0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y-nQHwrRLfc0.npy", "labels": "/m/02mk9,/m/07pb8fc,/t/dd00066", "caption": "An engine is idling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/Ytpm5IOD5d4o.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ytpm5IOD5d4o.npy", "labels": "/m/01w250", "caption": "A woman talking followed by a bird whistling then a person whistling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YlrKGCtSsAkA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YlrKGCtSsAkA.npy", "labels": "/m/09ct_", "caption": "A toy helicopter flying as wind blows into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YBGEMgl1xjac.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBGEMgl1xjac.npy", "labels": "/m/03vt0,/m/06hps,/m/09xqv", "caption": "Various insects and bugs are chirping with a rodent breathing sound in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/YelztUCeNQvQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YelztUCeNQvQ.npy", "labels": "/m/0195fx,/m/01g50p,/m/0284vy3,/m/06d_3,/m/07jdr", "caption": "A train horn honking followed by a subway train running on railroad tracks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YOxUVcZmeiyI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YOxUVcZmeiyI.npy", "labels": "/m/07qjznl,/m/07qjznt", "caption": "Ticking is ongoing, soft clicking occurs, and a cuckoo calls once followed by musical chimes" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/Yhzn_wGlzGpU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yhzn_wGlzGpU.npy", "labels": "/m/07yv9,/m/0k4j,/m/0ltv", "caption": "An aircraft engine accelerating followed by an object clanking against fiberglass as an emergency siren sounds in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YY3lNEe-ZGF0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YY3lNEe-ZGF0.npy", "labels": "/m/07qjznl,/m/07qjznt", "caption": "A clock ticking followed by a wooden latch opening" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/YemGPabOePzA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YemGPabOePzA.npy", "labels": "/m/03q5_w,/m/09x0r", "caption": "Speech in slow motion" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YlrKGCtSsAkA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YlrKGCtSsAkA.npy", "labels": "/m/09ct_", "caption": "A toy helicopter engine flying as wind blows into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YDt53UZgyznE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YDt53UZgyznE.npy", "labels": "/m/09x0r,/t/dd00002", "caption": "A baby cries, and a man talks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YJTHMXLC9YRs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YJTHMXLC9YRs.npy", "labels": "/m/09ddx,/m/0jbk", "caption": "Breathing and ducks quaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YsCzRVvu9XeY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YsCzRVvu9XeY.npy", "labels": "/m/01w250", "caption": "A rhythmic whistle plays a tune" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YXz56Q2Q5j5c.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YXz56Q2Q5j5c.npy", "labels": "/m/07k1x,/m/083vt", "caption": "A machine works while something is rasping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YtNxfdAd14qE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YtNxfdAd14qE.npy", "labels": "/m/07p9k1k", "caption": "Clicking and rustling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YWUpeplQr3A4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YWUpeplQr3A4.npy", "labels": "/m/01d380", "caption": "A power drill running followed by drilling noises and human screaming" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part27/Y_C2HinL8VlM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y_C2HinL8VlM.npy", "labels": "/m/03j1ly,/m/03kmc9,/m/04qvtq", "caption": "Humming of an engine with sirens ringing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YC8kR19NvynA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YC8kR19NvynA.npy", "labels": "/m/02qldy,/m/05zppz,/m/09x0r", "caption": "A male voice speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/YxqtrbqDlz28.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YxqtrbqDlz28.npy", "labels": "/m/01hsr_", "caption": "A high pitched sneeze followed by sniffling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YZBtgrP4vU_w.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YZBtgrP4vU_w.npy", "labels": "/m/07p9k1k", "caption": "Food and oil sizzling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YUE3XnVFodMI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YUE3XnVFodMI.npy", "labels": "/m/028ght,/m/09x0r", "caption": "Loud applause and woman speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YTOaQMYc79Mw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YTOaQMYc79Mw.npy", "labels": "/m/07yv9,/t/dd00130", "caption": "An engine struggling to start with some clicks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part0/Y-JP1GqPEKtw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y-JP1GqPEKtw.npy", "labels": "/m/07k1x,/m/083vt,/m/09x0r", "caption": "A man speaks while operating a power tool" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part19/YMTIF_l_8d4Q.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YMTIF_l_8d4Q.npy", "labels": "/m/0463cq4,/m/09x0r", "caption": "A baby is crying and a child speaks in the background, then an adult female speaks and the baby sobs" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/Ylh801oHGtD4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ylh801oHGtD4.npy", "labels": "/m/01d380,/m/09x0r", "caption": "Electronic humming followed by a man speaking and a door closing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/YhiJB_95IWiE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YhiJB_95IWiE.npy", "labels": "/m/02p01q,/m/07pdjhy", "caption": "A man speaking with some light knocking and high pitched scraping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4ftDFi4684Y.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4ftDFi4684Y.npy", "labels": "/m/07qjznl", "caption": "Several slight bangs occur during a constant ticktock" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YSE_3nszEw7o.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YSE_3nszEw7o.npy", "labels": "/m/06wzb,/m/07rjwbb", "caption": "A steam engine running on railroad tracks as steam releases and hisses" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YBUAPM4D3-h8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBUAPM4D3-h8.npy", "labels": "/m/015p6,/m/020bb7,/m/07pggtn", "caption": "Women, child talking and birds chirping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part4/Y2a6GNu6uCDE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y2a6GNu6uCDE.npy", "labels": "/m/02qldy,/m/02zsn,/m/09x0r", "caption": "A woman delivers a speech" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/Yhmd6pa2e_rs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yhmd6pa2e_rs.npy", "labels": "/m/01bjv,/m/07yv9,/m/09x0r", "caption": "A bus engine is running, and people are talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YTOaQMYc79Mw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YTOaQMYc79Mw.npy", "labels": "/m/07yv9,/t/dd00130", "caption": "An engine being started repeatedly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y6ukYSXzfEgQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y6ukYSXzfEgQ.npy", "labels": "/m/02jz0l,/m/0838f", "caption": "A tapping sound followed by running water" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YBzHTqyX69pI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBzHTqyX69pI.npy", "labels": "/m/07pdjhy,/m/083vt", "caption": "Wood sawing and scrapping followed by a woman speaking while pigeons are cooing and bird wings are flapping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3ejndVEAcmQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3ejndVEAcmQ.npy", "labels": "/m/01yrx,/m/068hy,/m/07qrkrw,/m/07r81j2,/m/0jbk", "caption": "A cat meowing and hissing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part38/Yu9px4Lwv9XI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yu9px4Lwv9XI.npy", "labels": "/m/07st88b,/m/09ld4", "caption": "Footsteps and a croaking frog" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part24/YVZLZ08k3YeA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YVZLZ08k3YeA.npy", "labels": "/m/01d3sd,/m/09x0r", "caption": "A man speaking as a person is snoring" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y5I8lmN8rwDM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y5I8lmN8rwDM.npy", "labels": "/m/01d380,/m/07k1x,/t/dd00125", "caption": "A tool buzzing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YZ-SIyOChVh8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YZ-SIyOChVh8.npy", "labels": "/m/06mb1,/m/0jb2l,/m/0ngt1", "caption": "Rain pours down with loud thunder" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YQKHpSAAjakY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YQKHpSAAjakY.npy", "labels": "/m/04_sv,/m/07yv9,/m/09x0r,/t/dd00128", "caption": "A motorcycle engine is running, and a man is talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/YwbPmnxCLoRQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YwbPmnxCLoRQ.npy", "labels": "/m/0395lw", "caption": "Large bells ringing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YAKHZMg9ba30.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YAKHZMg9ba30.npy", "labels": "/m/07rv9rh,/m/09x0r,/m/0jbk", "caption": "A man speaking as a horse is trotting while a man talks then laughs in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YSoO1HhaEc9Q.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YSoO1HhaEc9Q.npy", "labels": "/m/09x0r,/t/dd00018", "caption": "Rhythmic squeaking is ongoing, pigs oink, an adult male speaks, and music plays faintly in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YrINmxSXMR-s.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YrINmxSXMR-s.npy", "labels": "/m/07qdb04,/m/09ddx,/m/0jbk", "caption": "A duck quacks and splashes and a human chuckles" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y1N_DtRpdAp8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1N_DtRpdAp8.npy", "labels": "/m/01jwx6", "caption": "Clicking and humming of a revving idling engine" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YBL8ksJ0sTXk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBL8ksJ0sTXk.npy", "labels": "/m/01jwx6,/m/07pb8fc,/m/07yv9,/m/09x0r,/m/0k4j", "caption": "An idle vehicle engine running as a man is talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9MgGaTbmc6g.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9MgGaTbmc6g.npy", "labels": "/m/02mk9,/m/07q2z82,/m/07yv9,/m/0k4j,/t/dd00066", "caption": "Car accelerating and skidding on tarmac" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y2ItTq2JShdU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y2ItTq2JShdU.npy", "labels": "/m/07rqsjt", "caption": "Train click clacking sound going around the track" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/YgW7s3YAthpI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YgW7s3YAthpI.npy", "labels": "/m/02jz0l,/m/0838f", "caption": "Some light banging and rattling with liquid pouring and faint chewing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YlgwpIImXCWA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YlgwpIImXCWA.npy", "labels": "/m/083vt,/m/09x0r,/t/dd00125", "caption": "A man briefly speaks followed by a sawing sound, and then starts talking again" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/Yw_Utn3CwAXE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yw_Utn3CwAXE.npy", "labels": "/m/01jt3m,/m/0838f", "caption": "Water trickles down followed by some rattling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YQKHpSAAjakY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YQKHpSAAjakY.npy", "labels": "/m/04_sv,/m/07yv9,/m/09x0r,/t/dd00128", "caption": "Motorcycle engine idles while a man speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YFDwK7T1JO_0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YFDwK7T1JO_0.npy", "labels": "/m/01d380,/m/07k1x,/m/09x0r,/t/dd00125", "caption": "Two men talking followed by plastic clacking then a power tool drilling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part9/Y8DQfjqPCTI8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y8DQfjqPCTI8.npy", "labels": "/m/01h3n,/m/03vt0,/m/0h2mp", "caption": "Swarm of bees buzzing and two men speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part15/YG3YO2unWz7k.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YG3YO2unWz7k.npy", "labels": "/m/04_sv,/m/07yv9,/t/dd00128", "caption": "A motorcycle engine running idle then revving" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part38/YuY4fe5DT1gI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YuY4fe5DT1gI.npy", "labels": "/m/01m2v,/m/0316dw", "caption": "A person is typing on a computer keyboard" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/Yb1PXsfgQw5w.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yb1PXsfgQw5w.npy", "labels": "/m/01j3sz,/m/07r660_,/m/09x0r", "caption": "Men and women laughing then man speaking and laughter follows" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part4/Y31WGUPOYS5g.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y31WGUPOYS5g.npy", "labels": "/m/012ndj,/m/03j1ly,/m/03kmc9", "caption": "Yelling and then siren and horn" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part0/Y-mhFGevxLUg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y-mhFGevxLUg.npy", "labels": "/m/07rqsjt,/m/09x0r", "caption": "Man gives speech, echo heard in background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/YztSjcZNUY7A.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YztSjcZNUY7A.npy", "labels": "/m/09x0r,/t/dd00002", "caption": "An infant crying with murmuring in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YS_3aeOvniZc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YS_3aeOvniZc.npy", "labels": "/m/07yv9,/m/0k4j,/m/0ltv", "caption": "A race car is accelerating and shifting gears" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YWUyeFOyKIg0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YWUyeFOyKIg0.npy", "labels": "/m/07yv9,/m/09x0r,/m/0k4j,/m/0ltv,/t/dd00129", "caption": "Wind and people speaking and a car passing by" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YJsoBpL86R5U.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YJsoBpL86R5U.npy", "labels": "/m/03fwl,/m/07q0h5t,/m/09x0r,/m/0jbk", "caption": "People are speaking, and a goat bleats" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/YhqPBcvex1VU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YhqPBcvex1VU.npy", "labels": "/m/09x0r,/t/dd00002", "caption": "A child whining and crying" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YZ-SIyOChVh8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YZ-SIyOChVh8.npy", "labels": "/m/06mb1,/m/0jb2l,/m/0ngt1", "caption": "Thunderstorm sounds while raining" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YszkiW0GXEOI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YszkiW0GXEOI.npy", "labels": "/m/015p6,/m/01w250", "caption": "Whistling followed by birds chirping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YXIooZl1QdM4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YXIooZl1QdM4.npy", "labels": "/m/03q5_w", "caption": "Loud burping continuously" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YcFoXRmGgIME.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YcFoXRmGgIME.npy", "labels": "/m/01g50p,/m/0284vy3,/m/04zmvq,/m/06d_3,/m/07jdr,/m/07yv9", "caption": "A train running and then a horn honking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YsCzRVvu9XeY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YsCzRVvu9XeY.npy", "labels": "/m/01w250", "caption": "A person whistles a brief, five-note tune" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/YhuMLK0oA3L8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YhuMLK0oA3L8.npy", "labels": "/m/01w250", "caption": "A man speaks followed by whistling and guitar music" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YD4s5aHrsBgs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YD4s5aHrsBgs.npy", "labels": "/m/01w250", "caption": "A person whistling along to a music" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y7RMpCCkQks0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y7RMpCCkQks0.npy", "labels": "/m/07rjwbb", "caption": "Some whirring and sticky tape ripping off from a surface" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YQ87LBiwJjTE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YQ87LBiwJjTE.npy", "labels": "/m/07p9k1k,/m/0dxrf", "caption": "A woman speaks as food sizzles and music plays" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/YeRU-rABp8nk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YeRU-rABp8nk.npy", "labels": "/m/04_sv,/m/07yv9,/m/09x0r", "caption": "A group of men talking with each other as a motorcycle engine is running idle" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YD4s5aHrsBgs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YD4s5aHrsBgs.npy", "labels": "/m/01w250", "caption": "A person whistling as music plays in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YHeEa1GZpUGI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YHeEa1GZpUGI.npy", "labels": "/m/032s66", "caption": "Several gunshots followed by a click and glass breaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/YeJCaRgf1M20.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YeJCaRgf1M20.npy", "labels": "/m/07qjznl", "caption": "A bell chimes followed by camera muffling then plastic shuffling and a clock ticking as birds chirp in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/Yktc_tJxw8sc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yktc_tJxw8sc.npy", "labels": "/m/0463cq4", "caption": "Whining and loud crying" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/Yd1tL-9BILy8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yd1tL-9BILy8.npy", "labels": "/m/015p6,/m/020bb7,/m/07r_25d,/m/0h0rv", "caption": "Pigeons coo with a distant humming" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/YzBXoaQ1GVlc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YzBXoaQ1GVlc.npy", "labels": "/m/09x0r,/m/0ytgt,/t/dd00013,/t/dd00126", "caption": "A woman speaking as a group of children shout and talk in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/YA0E_UiD-fR4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YA0E_UiD-fR4.npy", "labels": "/m/02fs_r", "caption": "Digital beeping followed by rapid vibrations and humming" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/YwVi5w_NU6CM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YwVi5w_NU6CM.npy", "labels": "/m/012f08,/m/012ndj,/m/03j1ly,/m/03kmc9,/m/07r04,/m/07yv9", "caption": "A fire truck sounds the siren as it travels" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y41D0yXSBqfI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y41D0yXSBqfI.npy", "labels": "/m/015p6,/m/0h0rv,/t/dd00125", "caption": "Metal scrapping and gravel pouring while pigeons are cooing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YCxaPpRJRkn0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YCxaPpRJRkn0.npy", "labels": "/m/01d3sd", "caption": "A couple of loud snores one after the other" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YbX2vDaHL26U.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YbX2vDaHL26U.npy", "labels": "/m/07rknqz,/m/07yv9,/m/0k4j,/m/0ltv", "caption": "White noise, then a motor revving up and a tire skidding" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/Yz1ax0QPpd14.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yz1ax0QPpd14.npy", "labels": "/m/015p6,/m/09ddx", "caption": "Birds are chirping, and ducks are making noises" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4bUL_ttiOdw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4bUL_ttiOdw.npy", "labels": "/t/dd00002", "caption": "A baby is crying" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4IeDBwyQ9ZQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4IeDBwyQ9ZQ.npy", "labels": "/m/04brg2", "caption": "A tin can clacking followed by a girl talking then a woman talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YKJKHDKKW3XU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YKJKHDKKW3XU.npy", "labels": "/m/07swgks", "caption": "A stream of water softly trickling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/Yek9Fsmm3xqk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yek9Fsmm3xqk.npy", "labels": "/m/019jd,/m/03m9d0z,/m/056ks2,/m/07yv9", "caption": "Splashing with wind blowing hard" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part9/Y8VOibo9Q_Dc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y8VOibo9Q_Dc.npy", "labels": "/m/09ddx,/m/09x0r,/m/0jbk", "caption": "A small birds chirps as water splashes" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part38/YuJzAf4PaExI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YuJzAf4PaExI.npy", "labels": "/m/07yv9,/m/09x0r,/m/0k5j", "caption": "An aircraft flying followed by plastic creaking and rattling while a kid speaks in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YtxeXrpoMST4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YtxeXrpoMST4.npy", "labels": "/m/0130jx,/m/02jz0l,/m/03dnzn,/m/0838f", "caption": "Water trickling into a container" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YIKnx3hJv1bs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YIKnx3hJv1bs.npy", "labels": "/m/07qlf79", "caption": "Bad quality audio" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YPVvi2SDOjVc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YPVvi2SDOjVc.npy", "labels": "/m/07yv9,/m/0912c9,/m/0k4j,/t/dd00128", "caption": "A vehicle horn honking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/YdYvL6uEMl6E.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YdYvL6uEMl6E.npy", "labels": "/m/019jd,/m/02rlv9,/m/034srq,/m/03m9d0z,/m/05kq4,/t/dd00092", "caption": "A motorboat engine revving" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YS8k47ME-YT4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YS8k47ME-YT4.npy", "labels": "/m/06mb1,/m/0jb2l,/m/0ngt1", "caption": "Sounds of a thunderstorm with heavy rain" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YT32kii824pA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YT32kii824pA.npy", "labels": "/m/083vt", "caption": "A male speech and metal clanging." }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YQoEal_hKz4Q.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YQoEal_hKz4Q.npy", "labels": "/m/032s66,/m/04zjc", "caption": "Gunshots firing in the distance followed by gunshots and explosions going off as a man is talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y6ZwYgzcN6Is.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y6ZwYgzcN6Is.npy", "labels": "/m/09x0r,/m/0j6m2,/t/dd00129", "caption": "A woman yelling and laughing as a group of people shout while ocean waves crash and wind blows into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YCh0LMmhBUg4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YCh0LMmhBUg4.npy", "labels": "/m/03m9d0z,/m/06q74,/m/07yv9,/m/09x0r,/t/dd00129", "caption": "A man is speaking with natural outdoor noises, and a child speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y7QN3lwOzfdg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y7QN3lwOzfdg.npy", "labels": "/m/07cx4,/m/09x0r", "caption": "An adult speaks over a telephone and then an adult male speaks, and this pattern repeats three times" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part7/Y5eSRL3PRHzo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y5eSRL3PRHzo.npy", "labels": "/m/028ght,/m/03qtwd", "caption": "A crowd applauding and cheering" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/Yific_gRalg0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yific_gRalg0.npy", "labels": "/m/07swgks", "caption": "A series of loud metal hammering as liquid drains down a pipe followed by a metal chain rattling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YJp64Whpr3BA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YJp64Whpr3BA.npy", "labels": "/m/0llzx", "caption": "Rustling followed by a sewing machine running." }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YbA5zPFSFZAA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YbA5zPFSFZAA.npy", "labels": "/m/07rqsjt", "caption": "A series of electronic beeping and static" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/Ym8wV38lf2jg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ym8wV38lf2jg.npy", "labels": "/m/03j1ly,/m/03kmc9,/m/04qvtq,/m/07yv9,/m/09x0r,/m/0k4j", "caption": "A siren that gets louder and muffled male speech" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YkVYNXZd0MMY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YkVYNXZd0MMY.npy", "labels": "/m/01jwx6,/m/02mk9,/m/07yv9,/m/0k4j", "caption": "An idle vehicle engine running followed by bird cawing in the background and a plastic camera click" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part15/YH7-orYrKBeo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YH7-orYrKBeo.npy", "labels": "/m/01bjv,/m/0463cq4,/m/07yv9,/m/09x0r", "caption": "A child crying together with murmuring" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part4/Y2RjqBRzmxaM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y2RjqBRzmxaM.npy", "labels": "/m/06mb1,/m/07r10fb,/t/dd00038", "caption": "Music playing followed by a woman talking and rain falling then rain falling on a surface" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YP4qd8uodw_M.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YP4qd8uodw_M.npy", "labels": "/m/02fs_r,/m/09x0r", "caption": "A man talking faintly in the background followed by a metal click then a small horn honking twice" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YKel-hfZ_9h8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YKel-hfZ_9h8.npy", "labels": "/m/09x0r,/m/0ytgt,/t/dd00013", "caption": "Crunching and scraping followed by a child and a man speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part19/YMe4npKmtchA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YMe4npKmtchA.npy", "labels": "/m/07pqc89,/m/0838f,/m/09x0r", "caption": "Water trickling and faint, muffled speech" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part0/Y-mb4Fw4Z0xg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y-mb4Fw4Z0xg.npy", "labels": "/m/012f08,/m/07yv9,/m/09x0r,/m/0k4j,/t/dd00134", "caption": "Humming of a loud engine with people laughing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y404cD3bVXDc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y404cD3bVXDc.npy", "labels": "/m/09x0r,/t/dd00002", "caption": "An infant talking while a man speaks through a television speaker" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/YwoadpeAGHUQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YwoadpeAGHUQ.npy", "labels": "/m/012ndj,/m/03j1ly,/m/03kmc9", "caption": "An emergency siren sounding followed by water spraying and a man shouting as a truck engine runs idle in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part24/YVkbp8VmL3pM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YVkbp8VmL3pM.npy", "labels": "/m/0463cq4", "caption": "A baby crying and cooing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YKVAIaRPry24.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YKVAIaRPry24.npy", "labels": "/m/01h3n,/m/03vt0,/m/0h2mp", "caption": "Flying insects are buzzing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YrtgVoZCcBw8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YrtgVoZCcBw8.npy", "labels": "/m/03fwl,/m/09x0r,/m/0jbk", "caption": "A short, high pitched goat call in the distance followed by a slight pause, then a loud, high pitched and sustained scream close by" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part15/YGkb4f6yodPE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YGkb4f6yodPE.npy", "labels": "/m/01b82r,/m/07pdjhy,/m/083vt", "caption": "Sustained industrial sawing noise" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part24/YW4GEwnXc9tQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YW4GEwnXc9tQ.npy", "labels": "/m/09ld4", "caption": "Music is playing, people are talking and a frog croaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YJmWaRt8-u0s.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YJmWaRt8-u0s.npy", "labels": "/m/04_sv,/m/07yv9,/m/09x0r,/t/dd00066", "caption": "A motorcycle engine and talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YZ_smJ66Tb3c.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YZ_smJ66Tb3c.npy", "labels": "/m/015p6,/m/020bb7,/m/07r_25d,/m/0h0rv", "caption": "A man speaking as someone hisses while pigeons are cooing and bird wings are flapping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YrUq4w4EUSWA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YrUq4w4EUSWA.npy", "labels": "/m/01jt3m,/m/0838f", "caption": "A toilet flushing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part27/Y_w2pA1VeB40.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y_w2pA1VeB40.npy", "labels": "/m/01j3sz", "caption": "Continuous laughter" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part1/Y0AsXkZkqelg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y0AsXkZkqelg.npy", "labels": "/m/028ght", "caption": "A loud bang followed by an engine idling loudly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part24/YUXGzbBGbqAA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YUXGzbBGbqAA.npy", "labels": "/m/07ryjzk,/m/0dxrf", "caption": "Footsteps shuffling followed by fabric slapping a hard surface as a person heavily breathes" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3MoF8myFs8Y.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3MoF8myFs8Y.npy", "labels": "/m/034srq,/m/03m9d0z,/m/05kq4,/t/dd00092", "caption": "Wind blowing hard and waves crashing and splashing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3VHpLxtd498.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3VHpLxtd498.npy", "labels": "/m/015p6,/m/09x0r,/m/0h0rv", "caption": "Mechanical humming with pigeons cooing and a person speaking briefly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part19/YMdlEswBfZMQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YMdlEswBfZMQ.npy", "labels": "/m/07rgt08,/m/09x0r,/m/0ytgt,/t/dd00125", "caption": "A group of children talking as a woman laughs then speaks followed by a young boy talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part27/Y_w2pA1VeB40.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y_w2pA1VeB40.npy", "labels": "/m/01j3sz", "caption": "Continuous laughter and chuckling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part0/Y-EQByFLFqig.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y-EQByFLFqig.npy", "labels": "/m/06mb1,/m/0ngt1,/t/dd00038", "caption": "A man speaks as rain falls and distant thunder roars" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y1HCuBnPLMqQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1HCuBnPLMqQ.npy", "labels": "/m/07pqc89", "caption": "Plastic clanking followed by a person breathing aloud then liquid pouring into a container" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YkVYNXZd0MMY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YkVYNXZd0MMY.npy", "labels": "/m/01jwx6,/m/02mk9,/m/07yv9,/m/0k4j", "caption": "Vibrating and humming from an idling engine" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part9/Y8nUqSYC66mI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y8nUqSYC66mI.npy", "labels": "/m/0j6m2", "caption": "Several people cheer and scream and speak as water flows hard" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/Yy3-M1sonh3M.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yy3-M1sonh3M.npy", "labels": "/m/01jt3m", "caption": "Clinking followed by a toilet flushing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part7/Y5ye0X5saadg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y5ye0X5saadg.npy", "labels": "/m/09ct_,/m/09x0r", "caption": "A man speaks as helicopter blades spin followed by loud explosions" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YQARuiRtfy-k.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YQARuiRtfy-k.npy", "labels": "/m/01d380", "caption": "Drilling with music playing and a man speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/Yk4XyfaWVLEY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yk4XyfaWVLEY.npy", "labels": "/m/01bjv,/m/07yv9,/m/09x0r", "caption": "A loud engine is on as birds chirp and people are talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/Yg_P29ucKj78.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yg_P29ucKj78.npy", "labels": "/m/07yv9,/m/0k4j,/t/dd00134", "caption": "A race car accelerating and driving as plastic rattles" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YBoe3MeEpn_c.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBoe3MeEpn_c.npy", "labels": "/m/04brg2,/m/09x0r,/t/dd00125", "caption": "A man speaking, with the clinking of dishes in the background, following by the hiss of an oil mister spraying" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YC9NC7wJ7C3w.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YC9NC7wJ7C3w.npy", "labels": "/m/02qldy,/m/02zsn,/m/09x0r", "caption": "A woman speaking continuously" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y1DKLyH3FixM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1DKLyH3FixM.npy", "labels": "/m/015p6,/m/020bb7,/m/07pggtn", "caption": "Birds are chirping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/Yo3mZR8OvPko.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yo3mZR8OvPko.npy", "labels": "/m/07yv9,/m/0k4j,/m/0ltv,/t/dd00128", "caption": "A car accelerating and squealing on road" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YTSdAJWJ-tW0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YTSdAJWJ-tW0.npy", "labels": "/m/012f08,/m/07yv9,/m/0k4j,/t/dd00134", "caption": "Two vehicles drive by as a man is speaking in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YWmDe2xbnSY4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YWmDe2xbnSY4.npy", "labels": "/m/07qsvvw", "caption": "Bursts of video game gunfire and popping occur in rapid succession" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YWHRnyGXcdy8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YWHRnyGXcdy8.npy", "labels": "/t/dd00002", "caption": "A baby is crying" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YQt0_xTadAT0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YQt0_xTadAT0.npy", "labels": "/m/09ld4", "caption": "Frogs chirp loudly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YDn3buZWMzwY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YDn3buZWMzwY.npy", "labels": "/m/01d3sd,/m/09x0r", "caption": "A man and a kid laughing followed by another man speaking as a person snores" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/Yek9Fsmm3xqk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yek9Fsmm3xqk.npy", "labels": "/m/019jd,/m/03m9d0z,/m/056ks2,/m/07yv9", "caption": "Wind blows and water smashes against kayak" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YFXdoNvmrYxo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YFXdoNvmrYxo.npy", "labels": "/m/03vt0,/m/09x0r,/t/dd00129", "caption": "A child speaks followed by a man and child communicating as birds are tweeting" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YBZCEDkx37rI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBZCEDkx37rI.npy", "labels": "/m/02mk9,/m/07pb8fc,/t/dd00066,/t/dd00130", "caption": "A motor runs faintly in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/Yo_3MDLl_aH0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yo_3MDLl_aH0.npy", "labels": "/m/032s66,/m/0_1c", "caption": "Loud explosions and burst that echo" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3ndid3jni7M.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3ndid3jni7M.npy", "labels": "/m/01g50p,/m/0284vy3,/m/06d_3,/m/07jdr,/m/07rwm0c", "caption": "Distant bells followed by a horn honking and clanking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YAbplcXwXnvE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YAbplcXwXnvE.npy", "labels": "/m/09x0r,/t/dd00112", "caption": "Female speaking followed by crinkling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YR8bHTHnF8j4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YR8bHTHnF8j4.npy", "labels": "/m/07yv9,/m/09ct_,/m/0k5j", "caption": "A helicopter engine running idle" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/YpPLisQ_QXxw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YpPLisQ_QXxw.npy", "labels": "/m/07yv9,/m/0912c9,/m/0k4j", "caption": "A train whistle blowing twice as a muffled car engine runs followed by a kid talking quietly in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/Yy1a8PntuXYw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yy1a8PntuXYw.npy", "labels": "/m/01jt3m", "caption": "A toilet flushing as an air ventilation system runs and a woman yells in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part38/YuhSDBwVrEdo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YuhSDBwVrEdo.npy", "labels": "/m/01w250", "caption": "A person whistles with wind blowing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YSGaIvgwwWSE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YSGaIvgwwWSE.npy", "labels": "/m/06mb1,/m/0jb2l,/m/0ngt1", "caption": "Rain falling on a hard surface as thunder roars in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y6ukYSXzfEgQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y6ukYSXzfEgQ.npy", "labels": "/m/02jz0l,/m/0838f", "caption": "Metal clacking followed by water flowing and splashing into a container then draining down a pipe" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/YzoxFl3pddMg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YzoxFl3pddMg.npy", "labels": "/m/09ld4", "caption": "A frog chirping with distant speaking of a person" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YFeHndzYAUkg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YFeHndzYAUkg.npy", "labels": "/m/01d380,/m/07k1x,/m/0_ksk", "caption": "A sustained drilling noise as music plays in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YtTB0BK39JI8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YtTB0BK39JI8.npy", "labels": "/m/0395lw", "caption": "Bells ring followed by clanking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YJnSwRonB9wI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YJnSwRonB9wI.npy", "labels": "/m/019jd,/m/02rlv9,/m/034srq,/m/05kq4", "caption": "People laugh and scream as water splashes and wind blows" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YU90e2P9jy30.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YU90e2P9jy30.npy", "labels": "/m/07pqc89,/m/09x0r", "caption": "A man yelling in the distance as several basketballs bounce and shoes squeak on hardwood floors" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part27/YZsTZ7jqbd9M.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YZsTZ7jqbd9M.npy", "labels": "/m/01h3n,/m/09x0r", "caption": "Footsteps walking on dirt as a man is talking and birds chirp in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y1DKLyH3FixM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1DKLyH3FixM.npy", "labels": "/m/015p6,/m/020bb7,/m/07pggtn", "caption": "A group of birds call and chirp for a while" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YNmmbNqmsPaY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YNmmbNqmsPaY.npy", "labels": "/m/07pb8fc,/m/07yv9,/m/0k4j", "caption": "Car engine idling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9PN4gyxpH2M.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9PN4gyxpH2M.npy", "labels": "/m/09x0r,/t/dd00112", "caption": "A man and a woman talking as paper crumbles and crinkles" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y27HIamF8pKo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y27HIamF8pKo.npy", "labels": "/m/01g50p,/m/0284vy3,/m/06d_3,/m/07jdr,/m/07rwm0c", "caption": "Railroad tracks clickety-clack as a train horn blasts" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YBLMWD6fxhpo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBLMWD6fxhpo.npy", "labels": "/t/dd00018", "caption": "Footsteps on grass followed by a man grunting then bubbles popping proceeded by a pig oinking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/YfrOqlk0Wm5Y.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YfrOqlk0Wm5Y.npy", "labels": "/m/07pdjhy", "caption": "A man speaking with intermittent metal scraping." }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/Yl5KdHAWwJCw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yl5KdHAWwJCw.npy", "labels": "/m/07qjznl", "caption": "A clock ticking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YJsoBpL86R5U.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YJsoBpL86R5U.npy", "labels": "/m/03fwl,/m/07q0h5t,/m/09x0r,/m/0jbk", "caption": "A woman talking then a man talking followed by a goat baaing as a kid talks in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YTSdAJWJ-tW0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YTSdAJWJ-tW0.npy", "labels": "/m/012f08,/m/07yv9,/m/0k4j,/t/dd00134", "caption": "Some cars passing by with people murmuring in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/Yyrxa6_P2I80.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yyrxa6_P2I80.npy", "labels": "/m/015p6,/m/0h0rv,/t/dd00129", "caption": "Pigeons cooing and birds chirping with a series of metal tapping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/YhFCmq9pCBbM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YhFCmq9pCBbM.npy", "labels": "/m/09x0r,/t/dd00112", "caption": "A girl talking as plastic crinkles followed by plastic thumping on a hard surface" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/Yw_Utn3CwAXE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yw_Utn3CwAXE.npy", "labels": "/m/01jt3m,/m/0838f", "caption": "A toilet flushing with footsteps and door opening" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3iLGu2Omgrw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3iLGu2Omgrw.npy", "labels": "/m/02qldy,/m/05zppz,/m/09x0r", "caption": "An elderly man speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YnmLMLgWPmFM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YnmLMLgWPmFM.npy", "labels": "/m/09x0r,/m/0j6m2", "caption": "A motorboat engine running as water splashes and a man shouts followed by birds chirping in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YAtkD-3GjXMw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YAtkD-3GjXMw.npy", "labels": "/m/032s66,/m/04zjc", "caption": "As music plays in the foreground, faint machine gunfire occurs in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/YcNARVD02-tw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YcNARVD02-tw.npy", "labels": "/m/02jz0l,/m/09x0r", "caption": "A man and woman speak and then water runs" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YbUTOsLXYyxg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YbUTOsLXYyxg.npy", "labels": "/m/01j3sz,/m/09x0r", "caption": "Man speaking followed by group laughter" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3kBlVLkN0zo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3kBlVLkN0zo.npy", "labels": "/m/03fwl,/m/09x0r,/m/0ch8v,/m/0jbk", "caption": "Speech in the distance with a bleating sheep nearby" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YPO8Nu3F8mkA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YPO8Nu3F8mkA.npy", "labels": "/m/014zdl,/m/07qsvvw", "caption": "A pop occurs, followed by whooshing, combustion, and hissing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YR8bHTHnF8j4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YR8bHTHnF8j4.npy", "labels": "/m/07yv9,/m/09ct_,/m/0k5j", "caption": "An engine running and helicopter propellers spinning" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/Ysl_Pxpc7beo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ysl_Pxpc7beo.npy", "labels": "/m/07yv9,/m/0912c9,/t/dd00128", "caption": "A horn honking several times" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/YyfYNPWs7mWY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YyfYNPWs7mWY.npy", "labels": "/m/02dgv,/m/05zppz,/m/09x0r", "caption": "Male speech and then a door shutting" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YIhvXtS9-IxM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YIhvXtS9-IxM.npy", "labels": "/m/07yv9,/m/09ct_", "caption": "A high pitched engine idling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part15/YH7-orYrKBeo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YH7-orYrKBeo.npy", "labels": "/m/01bjv,/m/0463cq4,/m/07yv9,/m/09x0r", "caption": "A group of people talking as an infant cries while a muffled bus engine runs" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YPtW0cZVprJQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YPtW0cZVprJQ.npy", "labels": "/m/01d3sd,/m/09x0r", "caption": "A person snoring followed by a man talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/Yific_gRalg0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yific_gRalg0.npy", "labels": "/m/07swgks", "caption": "Metal clanking several times as water drains down a pipe followed by metal rattling and water trickling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YtwFypUcdgRc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YtwFypUcdgRc.npy", "labels": "/m/01bjv,/m/07yv9,/m/09x0r", "caption": "A man yelling as another man is laughing as wind blows heavily into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YkOYg4ZtKcAs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YkOYg4ZtKcAs.npy", "labels": "/m/01yrx,/m/068hy,/m/07qrkrw,/m/0jbk", "caption": "A small motor rumbling followed by a cat meowing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part24/YUV1kdjwpy6U.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YUV1kdjwpy6U.npy", "labels": "/m/01jwx6,/m/09x0r", "caption": "An engine vibrates followed by a man speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/YhpDltmawxIM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YhpDltmawxIM.npy", "labels": "/m/0130jx,/m/02jz0l,/m/0838f", "caption": "Tap water runs in sink with gurgling noises" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YbhlhcGONisM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YbhlhcGONisM.npy", "labels": "/m/0316dw,/m/09x0r", "caption": "A man speaking followed by rustling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YNeWW30WZjPc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YNeWW30WZjPc.npy", "labels": "/m/01z5f,/m/05tny_,/m/068hy,/m/07rc7d9,/m/0bt9lr,/m/0jbk,/t/dd00125", "caption": "A dog barking and growling as plastic shuffles on a hard surface" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part15/YGSHcgY6ATkQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YGSHcgY6ATkQ.npy", "labels": "/m/0316dw", "caption": "A man speaks followed by clicks on a computer keyboard" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/Ycz0FSQDVBMw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ycz0FSQDVBMw.npy", "labels": "/m/06wzb,/m/07rjwbb", "caption": "Hissing with people speaking and some rattling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/Ym8wV38lf2jg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ym8wV38lf2jg.npy", "labels": "/m/03j1ly,/m/03kmc9,/m/04qvtq,/m/07yv9,/m/09x0r,/m/0k4j", "caption": "A man speaking over an intercom as emergency sirens wail in the distance and grow louder as a vehicle engine runs" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part7/Y67BsqRkh-dU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y67BsqRkh-dU.npy", "labels": "/m/01jt3m,/m/0838f", "caption": "A flush occurs and suctioned water splashes and gurgles, while music plays in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YrJVXE6Axtrg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YrJVXE6Axtrg.npy", "labels": "/m/09x0r,/m/0llzx", "caption": "A man speaks followed by loud vibrations" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/Yorgwzt45ojE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yorgwzt45ojE.npy", "labels": "/m/015p6,/m/09x0r,/m/0h0rv,/t/dd00126", "caption": "A man speaks as pigeons coo and wings flap" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YWHRnyGXcdy8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YWHRnyGXcdy8.npy", "labels": "/t/dd00002", "caption": "A baby crying continuously" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YKOBkbROPv4c.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YKOBkbROPv4c.npy", "labels": "/m/07rknqz,/m/07yv9,/m/0h9mv,/m/0ltv", "caption": "A distant engine hums and gets louder as it approaches with squealing tires" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/YwNiYSYJXssA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YwNiYSYJXssA.npy", "labels": "/m/03k3r,/m/09x0r,/m/0jbk", "caption": "Two young girls speaks with distant clop-clops followed by a loud gasp from a crowd" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YriM7b5bJ9KQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YriM7b5bJ9KQ.npy", "labels": "/m/01j3sz,/m/09x0r", "caption": "Two men are laughing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YrvDcg9DoNKA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YrvDcg9DoNKA.npy", "labels": "/m/0ngt1", "caption": "Distant thunder with rain falling followed by a man speaking loudly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/YfWvWhLJ5Fow.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YfWvWhLJ5Fow.npy", "labels": "/m/07qlf79", "caption": "Running then spraying" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/YpHNMcX-9FDs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YpHNMcX-9FDs.npy", "labels": "/m/068hy,/m/0bt9lr,/m/0jbk,/t/dd00136", "caption": "A dog whimpering constantly then ultimately growls" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part7/Y5K1mISHwggI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y5K1mISHwggI.npy", "labels": "/m/02mk9,/m/07yv9,/m/09x0r", "caption": "Men speak with traffic passing in the distance with a honk of a horn" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YPO8Nu3F8mkA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YPO8Nu3F8mkA.npy", "labels": "/m/014zdl,/m/07qsvvw", "caption": "Several pops and bursts of fireworks exploding" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part15/YFlk-X0gwjF4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YFlk-X0gwjF4.npy", "labels": "/m/020bb7,/m/09x0r,/t/dd00129", "caption": "Birds are chirping and singing, rustling occurs and an adult male speaks briefly in the foreground, and an adult male speaks in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/Ym_U506sf9p4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ym_U506sf9p4.npy", "labels": "/m/07p9k1k,/m/07ptfmf,/m/0dxrf", "caption": "A woman speaks and food sizzles" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YAgh2EKINlSw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YAgh2EKINlSw.npy", "labels": "/m/06mb1,/t/dd00038", "caption": "Hard rain falls on a metal surface, then three adult males speak while soft rhythmic whooshing occurs" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part19/YMTIF_l_8d4Q.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YMTIF_l_8d4Q.npy", "labels": "/m/0463cq4,/m/09x0r", "caption": "An infant crying with another infant crying in the background followed by a woman speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YOTLtzk0W4zg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YOTLtzk0W4zg.npy", "labels": "/m/07yv9,/m/09x0r,/m/0k4j,/t/dd00128,/t/dd00130", "caption": "An engine running and then a male speaking while the engine continues running" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part24/YUjje3lSabsg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YUjje3lSabsg.npy", "labels": "/m/01d3sd", "caption": "Soft, rapid snoring is ongoing, and faint speech occurs in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/YhFCmq9pCBbM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YhFCmq9pCBbM.npy", "labels": "/m/09x0r,/t/dd00112", "caption": "A woman is speaking while plastic crinkling several times" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4YodC6RnplI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4YodC6RnplI.npy", "labels": "/m/01d3sd", "caption": "Snoring with some laughter" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/Yq1ivQ_2fddk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yq1ivQ_2fddk.npy", "labels": "/m/07qlf79,/m/09x0r,/t/dd00128", "caption": "Constant hissing with mean having conversation" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YLB6CZ0x-kns.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YLB6CZ0x-kns.npy", "labels": "/m/07r04,/m/07yv9,/t/dd00128", "caption": "A loud metal clank followed by pressurized air releasing as a truck engine runs idle before accelerating" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/Yyau2WIRkxb8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yyau2WIRkxb8.npy", "labels": "/m/09ct_", "caption": "A small engine whirring" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part9/Y8GHLfJ6y6zA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y8GHLfJ6y6zA.npy", "labels": "/m/01m2v,/m/0316dw,/m/09x0r", "caption": "A man talking with keyboard typing and computer mouse clicking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YajheseWZmmU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YajheseWZmmU.npy", "labels": "/m/01yrx,/m/07qrkrw,/m/0jbk", "caption": "A cat meowing and a person hums" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part15/YG0IsabU5hn4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YG0IsabU5hn4.npy", "labels": "/m/09t49,/t/dd00092", "caption": "Wind blowing heavily into a microphone as ocean waves crash and leaves rustle" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/YfWvWhLJ5Fow.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YfWvWhLJ5Fow.npy", "labels": "/m/07qlf79", "caption": "Footsteps running followed by air spraying" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/Ye2rScj9UyMs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ye2rScj9UyMs.npy", "labels": "/m/015p6,/m/0h0rv,/t/dd00125", "caption": "Pigeons cooing and bird wings flapping as footsteps shuffle on paper" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part38/Yu8bQf0SnCVI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yu8bQf0SnCVI.npy", "labels": "/m/0130jx,/m/02jz0l,/t/dd00125", "caption": "Some light banging followed by water flowing and splashing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y22L_3pBa1AI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y22L_3pBa1AI.npy", "labels": "/m/07yv9,/m/0k4j,/t/dd00134", "caption": "A car engine revs as it passes by" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y2ItTq2JShdU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y2ItTq2JShdU.npy", "labels": "/m/07rqsjt", "caption": "A toy train engine operating" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YNeZerAPXR-A.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YNeZerAPXR-A.npy", "labels": "/m/01j3sz,/m/09x0r,/t/dd00125", "caption": "A woman laughs and then a man laughs with her followed by a boy speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/Ye9MWXS34o48.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ye9MWXS34o48.npy", "labels": "/m/01hsr_", "caption": "A woman heavily breathing then sneezing and then sniffling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YZNEZLlDVgrE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YZNEZLlDVgrE.npy", "labels": "/m/01h3n,/m/03vt0,/m/0h2mp", "caption": "Bees buzz while a man speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9BukzlPNqC8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9BukzlPNqC8.npy", "labels": "/m/01d380,/m/09x0r", "caption": "A drilling noise with a man speaking in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part15/YGMP8m09j5vk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YGMP8m09j5vk.npy", "labels": "/m/015p6,/m/020bb7,/m/07pggtn", "caption": "A bird chirps loudly in the foreground, and birds chirp and thumping occurs in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YLVvS3s9dFKw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YLVvS3s9dFKw.npy", "labels": "/m/0130jx,/m/02jz0l,/m/0838f", "caption": "A man is talking as water is running along with tapping noises" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YBA-lFjpzad4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBA-lFjpzad4.npy", "labels": "/m/012f08,/m/04_sv,/m/07yv9,/m/09x0r,/t/dd00134", "caption": "A man laughing with music playing in the background as a motorcycle engine drives by and becomes louder" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YbIiiIo20PsY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YbIiiIo20PsY.npy", "labels": "/m/01h3n,/m/09x0r", "caption": "A man talking as a swarm of insects are buzzing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part1/Y0NGSrwioYjA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y0NGSrwioYjA.npy", "labels": "/m/03fwl,/m/068hy,/m/09ld4,/m/09x0r,/m/0jbk", "caption": "A man speaks and a small goat bleats" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YP12nvSpKXcs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YP12nvSpKXcs.npy", "labels": "/m/01h3n,/m/03vt0,/m/0h2mp", "caption": "Birds are calling and many bees are buzzing, then a child speaks briefly and rustling footfalls and rattling occur" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y4CAMv5nlr-0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4CAMv5nlr-0.npy", "labels": "/m/02qldy,/m/05zppz,/m/09x0r", "caption": "A man speaking followed by a crowd of people applauding and cheering" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/Yjj2RyNDj7no.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yjj2RyNDj7no.npy", "labels": "/m/01h3n,/m/03vt0,/m/0h2mp", "caption": "Birds chirping as insects buzzing followed by a man talking in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YHdxfbpnd2-8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YHdxfbpnd2-8.npy", "labels": "/m/01w250", "caption": "A man talking then whistling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YbLZFtoWXYTA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YbLZFtoWXYTA.npy", "labels": "/m/02jz0l", "caption": "Water pouring into a container followed by grain grinding and plastic tapping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part24/YV8A0VRGdgwM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YV8A0VRGdgwM.npy", "labels": "/m/03fwl,/m/07q0h5t,/m/0ch8v,/m/0jbk", "caption": "Rocks and gravel tapping against wooden surface as footsteps shuffle on dirt and gravel followed by a goat talking while a muffled animal moans" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/Yjlwe9jtu5Gw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yjlwe9jtu5Gw.npy", "labels": "/m/01w250", "caption": "Two bursts of whistling occur" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YAUJPx81qKtY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YAUJPx81qKtY.npy", "labels": "/m/01h3n,/m/03vt0,/m/0h2mp", "caption": "A man talks and insects buzz" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part15/YGE1aZSnPr2Q.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YGE1aZSnPr2Q.npy", "labels": "/m/01j3sz", "caption": "A person laughs" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part19/YMe4npKmtchA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YMe4npKmtchA.npy", "labels": "/m/07pqc89,/m/0838f,/m/09x0r", "caption": "Water spraying and gurgling as a man speaks and a crowd of people talk in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/Yo7jW6Suyfbs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yo7jW6Suyfbs.npy", "labels": "/m/012f08,/m/07yv9,/m/0k4j,/m/0ltv", "caption": "A man talking in the distance before several vehicles accelerate and driving by" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/YjjHIINDfE1c.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YjjHIINDfE1c.npy", "labels": "/m/07yv9,/m/0912c9,/t/dd00129", "caption": "A vehicle is in motion, and the horn sounds" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/YgW7s3YAthpI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YgW7s3YAthpI.npy", "labels": "/m/02jz0l,/m/0838f", "caption": "A person gulping followed by glass tapping then liquid shaking in a container proceeded by liquid pouring before plastic thumps on paper" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/Ysl_Pxpc7beo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ysl_Pxpc7beo.npy", "labels": "/m/07yv9,/m/0912c9,/t/dd00128", "caption": "A vehicle horn beeps" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/YfYTZVxQ8LJk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YfYTZVxQ8LJk.npy", "labels": "/m/09x0r,/m/0ytgt,/t/dd00125", "caption": "Woman speaking followed by child speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/YeqcdsdLz954.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YeqcdsdLz954.npy", "labels": "/m/014zdl,/m/07qsvvw", "caption": "A whoosh occurs, followed by an explosion, soft clattering, snapping and crackling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4_Cak7gvly4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4_Cak7gvly4.npy", "labels": "/m/07rqsjt", "caption": "A series of whooshing effects as a drum plays music" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part0/Y-mhFGevxLUg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y-mhFGevxLUg.npy", "labels": "/m/07rqsjt,/m/09x0r", "caption": "A man is speaking with people talking and whooshing noises in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YtB8TiiXwKmA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YtB8TiiXwKmA.npy", "labels": "/m/01d380,/m/07k1x,/m/0_ksk", "caption": "A drill running" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YWLzzpzOKtnY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YWLzzpzOKtnY.npy", "labels": "/m/01h3n,/m/09x0r", "caption": "Male speech and an insect buzzing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YD96OO7nYYsg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YD96OO7nYYsg.npy", "labels": "/m/07q2z82,/m/07yv9,/m/0k4j", "caption": "A mid-size motor vehicle engine is operating with a whine and accelerates, then it slows and switches gears" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y2JutOgAnqWA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y2JutOgAnqWA.npy", "labels": "/m/01d380,/m/07k1x,/m/0_ksk", "caption": "A tool motor is running while metal whirring, grinding and clattering occur, then the tool whirs to a stop" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YK03ydb1uaoQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YK03ydb1uaoQ.npy", "labels": "/m/01d3sd,/t/dd00125", "caption": "Continuous long snoring" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y7WkB6pflr6o.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y7WkB6pflr6o.npy", "labels": "/m/02qldy,/m/02zsn,/m/09x0r", "caption": "Adult female speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YZBtgrP4vU_w.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YZBtgrP4vU_w.npy", "labels": "/m/07p9k1k", "caption": "Meat sizzling with insect sounds in background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YJ0yeFeKvIt8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YJ0yeFeKvIt8.npy", "labels": "/m/09t49", "caption": "Wind blowing with some leaves rustling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/YyL3gKa6YLoM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YyL3gKa6YLoM.npy", "labels": "/m/01d3sd,/m/09x0r", "caption": "Two men speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y52IxrdTxGs4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y52IxrdTxGs4.npy", "labels": "/m/07qsvvw,/m/09x0r", "caption": "A loud burst followed by musical notes and a heartbeat followed by a man speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y1nUOGZgSzZo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1nUOGZgSzZo.npy", "labels": "/m/07swgks,/m/09x0r,/m/0j6m2", "caption": "Water is splashing and a man laughs" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part9/Y83j4GgHXTLE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y83j4GgHXTLE.npy", "labels": "/m/01j3sz,/m/09x0r,/m/0ytgt,/t/dd00125", "caption": "A kid laughing and screaming with a man chuckling and woman whispering" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YmlnUJH4BQnk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YmlnUJH4BQnk.npy", "labels": "/m/07pdjhy", "caption": "Female speech and scratching" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part9/Y7cHRSfbp7tc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y7cHRSfbp7tc.npy", "labels": "/m/02dgv,/m/07r4wb8,/m/09x0r", "caption": "A group of people talking as dishes clack followed by wood knocking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/Ykdflh3akyH8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ykdflh3akyH8.npy", "labels": "/m/0ghcn6,/m/0jbk,/t/dd00136", "caption": "Several puppies whimpering during cardboard scratching and rattling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YAagLJkfrFMk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YAagLJkfrFMk.npy", "labels": "/m/01jt3m", "caption": "Water hissing followed by a man breathing aloud then a toilet flushing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YJmWaRt8-u0s.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YJmWaRt8-u0s.npy", "labels": "/m/04_sv,/m/07yv9,/m/09x0r,/t/dd00066", "caption": "A motorcycle engine running idle while two men communicate with each other" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part19/YMVGhC-xB79s.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YMVGhC-xB79s.npy", "labels": "/m/015p6,/m/09x0r,/m/0h0rv,/t/dd00128", "caption": "A man talking while a child talks and a person whistles followed by pigeons cooing and metal tapping and rattling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part38/YvfNKduToki4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YvfNKduToki4.npy", "labels": "/m/07r04,/m/07yv9,/m/09x0r", "caption": "Whistling and humming with men speaking in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YU5ij0M7T-hk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YU5ij0M7T-hk.npy", "labels": "/m/02dgv,/m/09x0r", "caption": "Footsteps walking on a hard surface before a door slides open followed by a door creaking then a door slamming shut" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YBXxlqaDvdaA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBXxlqaDvdaA.npy", "labels": "/m/05kq4,/m/07yv9,/m/09x0r,/m/0hsrw,/m/0j6m2", "caption": "A man talking as water splashes and wind blows heavily into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part38/YuY4fe5DT1gI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YuY4fe5DT1gI.npy", "labels": "/m/01m2v,/m/0316dw", "caption": "Clicking on a computer keyboard" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/Yjs4dr5JusdM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yjs4dr5JusdM.npy", "labels": "/m/07cx4,/m/09x0r", "caption": "A woman and man talk on the phone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part4/Y350OCezayrk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y350OCezayrk.npy", "labels": "/m/02mk9,/m/07yv9,/m/0k4j,/t/dd00066,/t/dd00130", "caption": "An engine starting and running" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part4/Y350OCezayrk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y350OCezayrk.npy", "labels": "/m/02mk9,/m/07yv9,/m/0k4j,/t/dd00066,/t/dd00130", "caption": "An engine is being started up then idles" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YHqnSyliKTKA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YHqnSyliKTKA.npy", "labels": "/m/03k3r,/m/07q5rw0,/m/07rv9rh,/m/09x0r,/m/0jbk", "caption": "Humming of an engine with people speaking and a horse neighing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part38/YvfNKduToki4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YvfNKduToki4.npy", "labels": "/m/07r04,/m/07yv9,/m/09x0r", "caption": "A truck engine running while warning beeps sound followed by a man yelling then compressed air releasing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/YjYPU6aSDo88.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YjYPU6aSDo88.npy", "labels": "/m/014yck,/m/07yv9,/m/09x0r,/m/0k5j", "caption": "An aircraft flying with wind blowing into a microphone followed by a man talking in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part15/YGE1aZSnPr2Q.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YGE1aZSnPr2Q.npy", "labels": "/m/01j3sz", "caption": "Brief silence followed by a man laughing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part27/Y_oKXrY5Ff0g.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y_oKXrY5Ff0g.npy", "labels": "/m/01j3sz,/m/09x0r", "caption": "A group of people talking and laughing as paper crinkles" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/YpCQEWAFGEjc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YpCQEWAFGEjc.npy", "labels": "/m/06wzb,/m/07rjwbb", "caption": "A train moving down railroad tracks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YqPYwp1K4sZE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YqPYwp1K4sZE.npy", "labels": "/m/09x0r,/t/dd00112,/t/dd00125", "caption": "A small child speaks followed by crinkling and cracking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y2KEfkDO6hlA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y2KEfkDO6hlA.npy", "labels": "/m/012f08,/m/07yv9,/m/0k4j,/t/dd00134", "caption": "Vehicle accelerating" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part7/Y6NBPiArs2-w.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y6NBPiArs2-w.npy", "labels": "/m/032s66", "caption": "Continuous gunshots, a man grunts and more gunshots" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part24/YVeCSHwtkBZU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YVeCSHwtkBZU.npy", "labels": "/m/012n7d,/m/03j1ly,/m/03kmc9", "caption": "An emergency vehicle siren blares fives times then changes to a higher pitched siren" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part4/Y30D1tqNFHMc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y30D1tqNFHMc.npy", "labels": "/m/01jwx6,/m/0chx_", "caption": "A plastic clack followed by whistling in the distance as a motor engine loudly operates and steam hisses" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YQ0anPAIkfBE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YQ0anPAIkfBE.npy", "labels": "/m/0463cq4,/m/09x0r,/t/dd00002,/t/dd00125", "caption": "A baby crying and a female speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YYEYeQ0lIkBQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YYEYeQ0lIkBQ.npy", "labels": "/m/015p6,/m/09ddx,/m/09x0r", "caption": "A man talking then laughing as a ducks quack" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YK8-b0VtNOqA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YK8-b0VtNOqA.npy", "labels": "/m/03k3r,/m/09x0r,/m/0jbk", "caption": "Horses snorting then neighing as footsteps shuffle and people talk in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YJsoBpL86R5U.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YJsoBpL86R5U.npy", "labels": "/m/03fwl,/m/07q0h5t,/m/09x0r,/m/0jbk", "caption": "A woman talking then a child talking followed by a man talking then a goat yelling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YtIM-H2rdq8U.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YtIM-H2rdq8U.npy", "labels": "/m/032s66", "caption": "A series of gunshots firing followed by a person groaning and metal clanking then a man talking while a heart beats in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/Ya_Rjlu50TfA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ya_Rjlu50TfA.npy", "labels": "/m/01d3sd,/m/07q0yl5,/m/09x0r", "caption": "A sharp snorting snore" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YKel-hfZ_9h8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YKel-hfZ_9h8.npy", "labels": "/m/09x0r,/m/0ytgt,/t/dd00013", "caption": "A child laughing followed by a man talking as snow shuffles in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YETb9EIQOMAA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YETb9EIQOMAA.npy", "labels": "/m/02qldy,/m/02zsn,/m/09x0r", "caption": "A female speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YI_vN_BFUr0Y.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YI_vN_BFUr0Y.npy", "labels": "/m/01g50p,/m/0284vy3,/m/04zmvq,/m/06d_3,/m/07jdr,/m/07yv9", "caption": "A railroad car sounds train horn as it approaches" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part15/YH-vTZh81qAU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YH-vTZh81qAU.npy", "labels": "/m/01jwx6", "caption": "A click occurs and a low-pitched electronic vibration begins" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YCwxgQS3SXic.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YCwxgQS3SXic.npy", "labels": "/m/0llzx", "caption": "A sewing machine operating" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/Yb1PXsfgQw5w.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yb1PXsfgQw5w.npy", "labels": "/m/01j3sz,/m/07r660_,/m/09x0r", "caption": "A few people laughing and giggling followed by someone talking and more laughter" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YnLZeG9LaLgw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YnLZeG9LaLgw.npy", "labels": "/m/07yv9,/m/0k4j,/m/0ltv", "caption": "A vehicle engine accelerating and revving as wind is blowing into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part24/YUmNrhFKpWIY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YUmNrhFKpWIY.npy", "labels": "/m/07q2z82,/m/07yv9,/m/0k4j", "caption": "A vehicle accelerates and then slows, then speeds up, then stops" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y7_smJ8VbfSU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y7_smJ8VbfSU.npy", "labels": "/m/02qldy,/m/02zsn,/m/09x0r", "caption": "Female speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4xrL4TSgHwU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4xrL4TSgHwU.npy", "labels": "/m/02mk9,/m/07pb8fc,/m/07q2z82,/m/07yv9,/t/dd00066,/t/dd00130", "caption": "A vehicle engine stalling then starting up and running idle" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part4/Y2sZhC_mKeic.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y2sZhC_mKeic.npy", "labels": "/m/01yrx,/m/068hy,/m/07qrkrw", "caption": "A car meows and a woman speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YNeWW30WZjPc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YNeWW30WZjPc.npy", "labels": "/m/01z5f,/m/05tny_,/m/068hy,/m/07rc7d9,/m/0bt9lr,/m/0jbk,/t/dd00125", "caption": "A dog barks and rustles with some clicking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YL_CNz9Vrtkw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YL_CNz9Vrtkw.npy", "labels": "/m/028ght,/m/09x0r", "caption": "A man speaking followed by a crowd applauding and cheering" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YD2Xc_jZllDY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YD2Xc_jZllDY.npy", "labels": "/m/068hy,/m/07r_k2n,/m/07rc7d9,/m/09x0r,/m/0bt9lr,/m/0jbk", "caption": "A man talking as a dog barks in the distance while wind blows into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YIPfaRF76gVU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YIPfaRF76gVU.npy", "labels": "/m/012ndj,/m/03j1ly,/m/07r04,/m/07yv9,/m/09x0r", "caption": "A truck accelerating as emergency sirens wail during a crowd of people talking followed by a man speaking on an intercom" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YSQHYl2Kp5ww.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YSQHYl2Kp5ww.npy", "labels": "/m/07ptfmf,/m/0dxrf", "caption": "Frying and talking right after music starts" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part24/YUhCzD6EBJBU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YUhCzD6EBJBU.npy", "labels": "/m/01d380,/m/07k1x,/m/0_ksk", "caption": "A power tool drilling followed by metal clacking then a man talking proceeded by a door closing shut" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part24/YVeCSHwtkBZU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YVeCSHwtkBZU.npy", "labels": "/m/012n7d,/m/03j1ly,/m/03kmc9", "caption": "Police sirens going off" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YD96OO7nYYsg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YD96OO7nYYsg.npy", "labels": "/m/07q2z82,/m/07yv9,/m/0k4j", "caption": "A vehicle accelerating then revving" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part1/Y0On6-JiVwRs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y0On6-JiVwRs.npy", "labels": "/m/01yrx,/m/068hy,/m/09t49,/m/0jbk,/t/dd00128", "caption": "Cats meow as the wind blows" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YBrPFQDr99Gg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBrPFQDr99Gg.npy", "labels": "/m/02qldy,/m/05zppz,/m/09x0r", "caption": "A crowd cheers and a man speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/YptIksg9KEac.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YptIksg9KEac.npy", "labels": "/m/068hy,/m/07rc7d9,/m/0bt9lr,/m/0jbk,/t/dd00136", "caption": "A dog barks along with outdoor noises" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YKvrcRMfFzOE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YKvrcRMfFzOE.npy", "labels": "/m/07yv9,/m/09ct_,/m/0k5j", "caption": "A helicopter is taking flight with the blades slapping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part4/Y2UNuMbxz9ds.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y2UNuMbxz9ds.npy", "labels": "/m/012f08,/m/07yv9,/m/0k4j,/t/dd00134", "caption": "An engine revving and popping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YlTfNLKEy1RU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YlTfNLKEy1RU.npy", "labels": "/m/01d3sd,/m/0bt9lr,/m/0jbk", "caption": "Continuous snoring" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YK8-b0VtNOqA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YK8-b0VtNOqA.npy", "labels": "/m/03k3r,/m/09x0r,/m/0jbk", "caption": "A door banging, a loud squeal, and some low voices in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/YfrOqlk0Wm5Y.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YfrOqlk0Wm5Y.npy", "labels": "/m/07pdjhy", "caption": "Male speech and metal scraping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/Yc3nlaAkv9bA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yc3nlaAkv9bA.npy", "labels": "/m/03fwl,/m/068hy,/m/09x0r,/m/0ch8v,/m/0jbk", "caption": "A male voice talking and the bleat of a goat" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part19/YMPLZUg89y5U.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YMPLZUg89y5U.npy", "labels": "/m/07r04,/m/07yv9,/m/09x0r", "caption": "Two men talking as a truck engine runs idle and wind blows into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y6ZwYgzcN6Is.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y6ZwYgzcN6Is.npy", "labels": "/m/09x0r,/m/0j6m2,/t/dd00129", "caption": "Woman screaming and yelling to another person with loud wind and waves in background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YNlKlRKz8OKI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YNlKlRKz8OKI.npy", "labels": "/m/015p6,/m/020bb7,/m/07pggtn", "caption": "Female speech and laughter followed by birds chirping and rustling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part0/Y-BUWGM7qeUM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y-BUWGM7qeUM.npy", "labels": "/m/06mb1", "caption": "Rain is heard falling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YY3lNEe-ZGF0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YY3lNEe-ZGF0.npy", "labels": "/m/07qjznl,/m/07qjznt", "caption": "Continuous, quiet tick-tocking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/Ykx6Rj4MDIAw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ykx6Rj4MDIAw.npy", "labels": "/m/07rjwbb", "caption": "A cuckoo bird coos followed by a train running on railroad tracks as a bell dings in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/Yt4prXmPwthg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yt4prXmPwthg.npy", "labels": "/m/09x0r,/m/0llzx", "caption": "Vibrations from a running sewing machine with a woman speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YrN2rpLV3brs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YrN2rpLV3brs.npy", "labels": "/m/04brg2", "caption": "Dishes clanking as a man is talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YXIooZl1QdM4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YXIooZl1QdM4.npy", "labels": "/m/03q5_w", "caption": "A man burping followed by belching while wheezing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YHeEa1GZpUGI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YHeEa1GZpUGI.npy", "labels": "/m/032s66", "caption": "Several gunshots ring out with glass breaking and a few clicks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YHqndxoujCYI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YHqndxoujCYI.npy", "labels": "/m/07qjznl,/m/09x0r", "caption": "A bell chiming as a clock ticks while a man talks through a television speaker in the background followed by muffled a muffled bell chiming" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/Ynq0BF9zGkzg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ynq0BF9zGkzg.npy", "labels": "/m/09x0r,/t/dd00018", "caption": "Groaning followed by a bang and breaking glass followed by men speaking with seagulls cawing in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/YdYZSKX7vuRI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YdYZSKX7vuRI.npy", "labels": "/m/01d3sd,/m/09x0r", "caption": "Snoring, a man takes a deep breath and speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YZUmZgPL0ges.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YZUmZgPL0ges.npy", "labels": "/m/0395lw", "caption": "Multiple large bells are madly ringing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part38/Yvigslb0kClE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yvigslb0kClE.npy", "labels": "/m/03fwl,/m/09x0r,/m/0jbk", "caption": "Loud hissing together with speech, rustling and basing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YE6FH_xp3I54.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YE6FH_xp3I54.npy", "labels": "/m/07pggtn,/m/09x0r,/m/0jbk,/t/dd00129", "caption": "A man is speaking followed by birds chirping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3iLGu2Omgrw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3iLGu2Omgrw.npy", "labels": "/m/02qldy,/m/05zppz,/m/09x0r", "caption": "An elderly man speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YnaPgJvWTIY4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YnaPgJvWTIY4.npy", "labels": "/m/04_sv,/m/07yv9,/t/dd00066,/t/dd00128", "caption": "A motorcycle engine running idle then revving" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y1QNLMF-Kl_s.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1QNLMF-Kl_s.npy", "labels": "/m/02qldy,/m/02zsn,/m/09x0r", "caption": "A woman is giving a speech" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part4/Y32565FEuksc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y32565FEuksc.npy", "labels": "/m/02qldy,/m/02zsn,/m/09x0r", "caption": "A woman gives a speech and a crowd claps" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/YfGGYeXR_LS8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YfGGYeXR_LS8.npy", "labels": "/m/01w250,/m/09x0r", "caption": "Whistling with male speech" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YT9_ep-3BZDY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YT9_ep-3BZDY.npy", "labels": "/m/09x0r,/t/dd00112,/t/dd00125", "caption": "An adult female speaks, thumping occurs, and paper crinkles while in a quiet environment" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YmGa2JgAiKV8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YmGa2JgAiKV8.npy", "labels": "/m/07pqc89,/m/09x0r", "caption": "A male speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YLs2vrr9TamU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YLs2vrr9TamU.npy", "labels": "/m/083vt", "caption": "Crackling with an engine running" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YrN2rpLV3brs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YrN2rpLV3brs.npy", "labels": "/m/04brg2", "caption": "An adult male speaks as metal scrapes and clinks on a dish rapidly and liquid splashes" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part24/YVOXl8iR-HnI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YVOXl8iR-HnI.npy", "labels": "/m/014yck,/m/07yv9,/m/09x0r,/m/0cmf2,/m/0k5j", "caption": "Quiet speech and then and airplane flying away" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YYNDKuNINDOY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YYNDKuNINDOY.npy", "labels": "/m/012ndj,/m/03j1ly,/m/03kmc9", "caption": "An emergency siren ringing with car horn honking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/Ylq9RvAA4mqY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ylq9RvAA4mqY.npy", "labels": "/m/07ptfmf,/m/0dxrf", "caption": "Food sizzling and male speech" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YPkmpxrsidZM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YPkmpxrsidZM.npy", "labels": "/m/028ght,/m/09x0r", "caption": "Applause and female speech and laughter, whistling, and then throat clearing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YEYTz1LPDHsc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YEYTz1LPDHsc.npy", "labels": "/m/02dgv", "caption": "Birds chirping and then a door unlocking and then opening" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part7/Y6NBPiArs2-w.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y6NBPiArs2-w.npy", "labels": "/m/032s66", "caption": "Repetitive sounds of gunfire" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YKtinboYbmHQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YKtinboYbmHQ.npy", "labels": "/m/07rknqz,/m/07yv9,/m/0h9mv,/m/0k4j", "caption": "Tires squealing and an engine revving" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part38/Yu9px4Lwv9XI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yu9px4Lwv9XI.npy", "labels": "/m/07st88b,/m/09ld4", "caption": "Bongos play followed by tapping on paper as frogs croak and crickets chirp in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YJsoBpL86R5U.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YJsoBpL86R5U.npy", "labels": "/m/03fwl,/m/07q0h5t,/m/09x0r,/m/0jbk", "caption": "A goat bleating with people speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YCxaPpRJRkn0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YCxaPpRJRkn0.npy", "labels": "/m/01d3sd", "caption": "Footsteps shuffling as a person snores" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9hxFqltp3xw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9hxFqltp3xw.npy", "labels": "/m/07qlf79,/m/09x0r", "caption": "A woman speaking followed by spraying" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YI_8KqxP5xOA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YI_8KqxP5xOA.npy", "labels": "/m/07qlf79", "caption": "Compressed air releasing and scissors snipping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/YeXj9OAik5cc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YeXj9OAik5cc.npy", "labels": "/m/04_sv,/m/07yv9,/t/dd00128", "caption": "An idle motorbike engine running as a bird chirps in the background and wind blows into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/YhDMHIDJdfDA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YhDMHIDJdfDA.npy", "labels": "/m/01d3sd,/t/dd00125", "caption": "Loud snoring repeating" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YI4HpYGMMsz4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YI4HpYGMMsz4.npy", "labels": "/m/083vt,/m/09x0r", "caption": "A man speaks followed by slapping on a wooden surface as steam hisses in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YLB6CZ0x-kns.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YLB6CZ0x-kns.npy", "labels": "/m/07r04,/m/07yv9,/t/dd00128", "caption": "An engine hums followed by a hiss" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YLs1zyPjs3k8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YLs1zyPjs3k8.npy", "labels": "/m/02fs_r", "caption": "A bleeping noise followed by a static noise" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9ZZHvwaH-CU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9ZZHvwaH-CU.npy", "labels": "/m/032s66", "caption": "A person groaning followed by a series of gunshots and a high-pitched grunt then synthesized laser effects as music plays in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/YA0E_UiD-fR4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YA0E_UiD-fR4.npy", "labels": "/m/02fs_r", "caption": "Plastic tapping followed by an electronic beep then by a toy car motor revving and plastic scrapping against a wooden surface" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part27/Ya3GzZKxUTy8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ya3GzZKxUTy8.npy", "labels": "/m/015p6,/m/09ddx,/m/0bt9lr,/m/0jbk", "caption": "A duck quacking followed by a dog barking as birds chirp then plastic popping and a film reel rolling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YC_ga5m6nOhI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YC_ga5m6nOhI.npy", "labels": "/m/06hck5,/m/06wzb,/m/07rjwbb", "caption": "A train running on train tracks while a steam engine horn whistles" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YKel-hfZ_9h8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YKel-hfZ_9h8.npy", "labels": "/m/09x0r,/m/0ytgt,/t/dd00013", "caption": "A child laughs, a man speaks, and people laugh" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YUCy1BEx8jBE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YUCy1BEx8jBE.npy", "labels": "/m/0j6m2", "caption": "A man speaking as a stream of water sprays and splashes" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9b6RqajfAmw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9b6RqajfAmw.npy", "labels": "/m/015p6,/m/0h0rv,/t/dd00129", "caption": "Pigeons cooing and birds flapping wings as a plastic clicks multiple times" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3ejndVEAcmQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3ejndVEAcmQ.npy", "labels": "/m/01yrx,/m/068hy,/m/07qrkrw,/m/07r81j2,/m/0jbk", "caption": "A cat meows angrily, while speech is faintly present in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/Yz4MeV9IGVo0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yz4MeV9IGVo0.npy", "labels": "/m/01bjv,/m/07yv9,/m/09x0r", "caption": "An engine roars as someone is speaking over a machine" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YrBUCIK8JRLg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YrBUCIK8JRLg.npy", "labels": "/m/034srq,/m/03m9d0z,/m/05kq4,/t/dd00092", "caption": "Muffled water splashing and wind blowing followed by audio static and plastic clicking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YEcihYbSlyck.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YEcihYbSlyck.npy", "labels": "/m/01bjv,/m/07yv9,/m/09x0r", "caption": "Vehicles are moving, horns are sounding, the door alarm to a bus is beeping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/Yp_BB_rJaF7Q.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yp_BB_rJaF7Q.npy", "labels": "/m/09ld4", "caption": "Birds chirping as a man is speaking followed by an animal squeaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YbygBWUkpaC8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YbygBWUkpaC8.npy", "labels": "/m/020bb7,/m/07pggtn,/m/09x0r,/m/0jbk,/t/dd00129", "caption": "While birds chirp and the wind blows, an adult male speaks in the foreground and people talk in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YbLZFtoWXYTA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YbLZFtoWXYTA.npy", "labels": "/m/02jz0l", "caption": "Water pouring into a plastic container followed by sand grinding" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YPMMdAKZxI_I.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YPMMdAKZxI_I.npy", "labels": "/m/03q5_w,/m/09x0r", "caption": "Burping and laughing from girls with distant voices over a television" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YCfxWJ1Qoufg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YCfxWJ1Qoufg.npy", "labels": "/m/01jt3m,/m/09x0r", "caption": "A man speaks before a toilet flushes" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YXf5LjaE_JQ0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YXf5LjaE_JQ0.npy", "labels": "/m/07qlf79,/m/09x0r", "caption": "A man speaks as traffic passes in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y2ErfX6ZT5pM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y2ErfX6ZT5pM.npy", "labels": "/m/01jt3m", "caption": "A toilet flushes as music plays in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/YdYvL6uEMl6E.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YdYvL6uEMl6E.npy", "labels": "/m/019jd,/m/02rlv9,/m/034srq,/m/03m9d0z,/m/05kq4,/t/dd00092", "caption": "A helicopter flying followed by wind heavily blowing into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YlVr-PxhZo8s.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YlVr-PxhZo8s.npy", "labels": "/m/07pb8fc,/m/07yv9,/t/dd00126", "caption": "Car engine idling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y7bO0AJI-ihs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y7bO0AJI-ihs.npy", "labels": "/m/03k3r,/m/07rv9rh,/m/0jbk", "caption": "Horses trotting on a hard surface as a motor rumbles rapidly for a brief period in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/Yne2DpKCIr4Y.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yne2DpKCIr4Y.npy", "labels": "/m/034srq,/m/03m9d0z,/m/05kq4,/t/dd00092", "caption": "Wind blowing with waves crashing and people speaking in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YJC2ZrXzCX4Y.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YJC2ZrXzCX4Y.npy", "labels": "/m/01d3sd,/m/09x0r", "caption": "Loud snoring sounds as people speak in the background and man and woman talk" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/Yy-RSojxgkDo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yy-RSojxgkDo.npy", "labels": "/m/015p6,/m/068hy,/m/07pggtn", "caption": "A man talking followed by a bird squawking then a kid talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/Yc0V_HAul7rI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yc0V_HAul7rI.npy", "labels": "/m/01j3sz,/m/07rgt08,/m/09x0r", "caption": "A group of people laughing followed by a man talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YJZloTOdIY_c.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YJZloTOdIY_c.npy", "labels": "/m/03k3r,/m/07q5rw0,/m/07rv9rh,/m/0jbk", "caption": "Horses neighing then snorting and trotting on a dirt surface" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YXQxIXaX_7M0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YXQxIXaX_7M0.npy", "labels": "/m/09t49,/m/09x0r", "caption": "A stream of water rushing as a man shouts in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YPYP-r0nvbFk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YPYP-r0nvbFk.npy", "labels": "/m/07bgp,/m/07q0h5t,/m/09x0r", "caption": "Wind blows and a man speaks followed by a goat bleating" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YLB6CZ0x-kns.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YLB6CZ0x-kns.npy", "labels": "/m/07r04,/m/07yv9,/t/dd00128", "caption": "A vehicle engine whirring followed by some knocking and a release of brakes" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/Yii3Geza3hAU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yii3Geza3hAU.npy", "labels": "/m/0llzx", "caption": "Vibrations from a sewing machine" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part27/Ya3GzZKxUTy8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ya3GzZKxUTy8.npy", "labels": "/m/015p6,/m/09ddx,/m/0bt9lr,/m/0jbk", "caption": "A bird squawks followed by a dog whimpering" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3qTL7QRk-tg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3qTL7QRk-tg.npy", "labels": "/m/07swgks,/m/0j6m2", "caption": "Men are singing together with a gurgling background noise" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part15/YG3YO2unWz7k.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YG3YO2unWz7k.npy", "labels": "/m/04_sv,/m/07yv9,/t/dd00128", "caption": "Sputtering and humming of an engine" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part15/YH7-orYrKBeo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YH7-orYrKBeo.npy", "labels": "/m/01bjv,/m/0463cq4,/m/07yv9,/m/09x0r", "caption": "A baby cries with a humming engine and some faint clicking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part38/Yu9px4Lwv9XI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yu9px4Lwv9XI.npy", "labels": "/m/07st88b,/m/09ld4", "caption": "The pitter-patter of feet running" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4sb9jN0SgTM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4sb9jN0SgTM.npy", "labels": "/m/02mk9,/m/07pb8fc,/m/07q2z82,/m/07yv9,/m/09x0r,/m/0k4j,/t/dd00066", "caption": "A vehicle engine is accelerating followed by a man speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YOxUVcZmeiyI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YOxUVcZmeiyI.npy", "labels": "/m/07qjznl,/m/07qjznt", "caption": "A clock ticking followed by plastic clacking then cuckoo bird cooing before bells chiming" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YYQSuFyFm3Lc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YYQSuFyFm3Lc.npy", "labels": "/m/01g50p,/m/0284vy3,/m/06d_3,/m/07jdr", "caption": "A repeating train horn and warning bells get louder as a train approaches" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part24/YUjje3lSabsg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YUjje3lSabsg.npy", "labels": "/m/01d3sd", "caption": "Snoring with low whirring and speech in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YOFVzrakJhbw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YOFVzrakJhbw.npy", "labels": "/m/068hy,/m/07bgp,/m/07q0h5t,/m/0jbk", "caption": "A woman laughs with some wind blowing and sheep bleating" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YESjMIqrvRj4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YESjMIqrvRj4.npy", "labels": "/m/09t49,/t/dd00092", "caption": "Rain and thunder in a storm" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/Yr2djvq1vc68.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yr2djvq1vc68.npy", "labels": "/m/0130jx,/m/02jz0l,/m/0838f", "caption": "A faucet pouring water as water fills a container followed by scrubbing on a plastic surface and water splashing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part27/YaMhu5eMQAsI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YaMhu5eMQAsI.npy", "labels": "/m/07yv9,/m/0k5j,/t/dd00129", "caption": "An aircraft engine operating" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YP4qd8uodw_M.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YP4qd8uodw_M.npy", "labels": "/m/02fs_r,/m/09x0r", "caption": "Low speech from a man followed by machine making a beeping noise" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part24/YUhCzD6EBJBU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YUhCzD6EBJBU.npy", "labels": "/m/01d380,/m/07k1x,/m/0_ksk", "caption": "A small tool motor runs and whirs twice with metal clicking, an adult male speaks, a door shuts and clicks, and three thumps occur" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/Yc0V_HAul7rI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yc0V_HAul7rI.npy", "labels": "/m/01j3sz,/m/07rgt08,/m/09x0r", "caption": "A group of people laughing followed by a young man talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YBn4lc01q9vE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBn4lc01q9vE.npy", "labels": "/m/0130jx,/m/02jz0l,/m/03dnzn,/m/0838f", "caption": "Water splashes irregularly as a man speaks, then a woman calls loudly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YRNBoH2LHQEM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YRNBoH2LHQEM.npy", "labels": "/m/028ght", "caption": "A crowd of people applauding and cheering" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part9/Y7cHRSfbp7tc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y7cHRSfbp7tc.npy", "labels": "/m/02dgv,/m/07r4wb8,/m/09x0r", "caption": "A crowd of people talking as dinner plates and glasses clank followed by light knocking on wood" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YQvATUKXYFBs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YQvATUKXYFBs.npy", "labels": "/m/01g50p,/m/0284vy3,/m/06d_3,/m/07jdr,/m/07rwm0c", "caption": "Warning bells ring as a train approaches with a honking horn" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YXL8JV9qXGLE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YXL8JV9qXGLE.npy", "labels": "/m/0463cq4,/m/09x0r,/m/0ytgt,/t/dd00002,/t/dd00125", "caption": "An infant talking as a woman speaks while a group of people talk in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part19/YNDaVSIJaXVs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YNDaVSIJaXVs.npy", "labels": "/m/014yck,/m/07yv9,/m/0cmf2,/m/0k5j,/t/dd00128", "caption": "An aircraft engine operates" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/YjXkLS_QzUrI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YjXkLS_QzUrI.npy", "labels": "/m/068hy,/m/07qrkrw", "caption": "Hissing sounds and bird chirping." }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YPb6MqpdX5Jw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YPb6MqpdX5Jw.npy", "labels": "/m/0ngt1", "caption": "A light rain with gentle thunder" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/YfYTZVxQ8LJk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YfYTZVxQ8LJk.npy", "labels": "/m/09x0r,/m/0ytgt,/t/dd00125", "caption": "A woman is speaking, and a child speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part19/YMvHpNzDpC6Q.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YMvHpNzDpC6Q.npy", "labels": "/m/012f08,/m/03q5_w,/m/07yv9,/m/09x0r,/m/0k4j", "caption": "Two men talk followed by a person belching as a car drives" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y6eX6bJOFftA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y6eX6bJOFftA.npy", "labels": "/m/02rlv9,/m/07yv9,/m/09x0r", "caption": "Motor boat cruising over water people speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YT32kii824pA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YT32kii824pA.npy", "labels": "/m/083vt", "caption": "Male speech and metal clanking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part7/Y5t6tSW0yT40.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y5t6tSW0yT40.npy", "labels": "/m/07qlf79", "caption": "White noise followed by a consistent hissing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part0/Y-aYumc8KoXg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y-aYumc8KoXg.npy", "labels": "/m/07yv9,/m/0912c9,/m/0k4j", "caption": "A short horn followed by a car approaching with a longer horn" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part0/Y--0w1YA1Hm4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y--0w1YA1Hm4.npy", "labels": "/m/01bjv,/m/07yv9,/m/09x0r", "caption": "High pitched speaking and laughing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y0rSETXszQM0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y0rSETXszQM0.npy", "labels": "/m/028v0c,/m/04_sv,/m/07yv9,/t/dd00128", "caption": "Plastic clacking followed by a motorbike and a motorcycle engine starting up then accelerating" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/Yi1u_2eZYYlE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yi1u_2eZYYlE.npy", "labels": "/m/07pb8fc,/m/07r04,/m/07yv9", "caption": "An idle vehicle engine running" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/YA0E_UiD-fR4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YA0E_UiD-fR4.npy", "labels": "/m/02fs_r", "caption": "Loud beep followed by engine noise" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YAFgGoY8Ihhg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YAFgGoY8Ihhg.npy", "labels": "/m/03j1ly,/m/03kmc9,/m/04qvtq", "caption": "Wind blowing and a siren rings" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part27/Y_oKXrY5Ff0g.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y_oKXrY5Ff0g.npy", "labels": "/m/01j3sz,/m/09x0r", "caption": "A person speaking, followed by a number of people laughing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/YyL3gKa6YLoM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YyL3gKa6YLoM.npy", "labels": "/m/01d3sd,/m/09x0r", "caption": "A man talking as a person is snoring and a vehicle accelerates in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YNi3dIj90Oa4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YNi3dIj90Oa4.npy", "labels": "/m/032s66", "caption": "Loud gunshots followed by two men speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YD2Xc_jZllDY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YD2Xc_jZllDY.npy", "labels": "/m/068hy,/m/07r_k2n,/m/07rc7d9,/m/09x0r,/m/0bt9lr,/m/0jbk", "caption": "Dog barking with win and man speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YYQGW5AwDOIo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YYQGW5AwDOIo.npy", "labels": "/m/07yv9,/m/0k4j,/m/0ltv", "caption": "Someone in a crowd whistles while engines rev in cars going slowly by" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y7JWHbs3gu1w.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y7JWHbs3gu1w.npy", "labels": "/m/01g50p,/m/0284vy3,/m/06d_3,/m/07jdr,/m/07rwm0c", "caption": "A train running on railroad tracks drives by followed by a train whistle blowing and warning signals ringing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9zstu_IfAm4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9zstu_IfAm4.npy", "labels": "/m/07r04,/m/07yv9,/m/09x0r", "caption": "A truck is traveling on the road, and the driver is honking the horn" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part15/YGkb4f6yodPE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YGkb4f6yodPE.npy", "labels": "/m/01b82r,/m/07pdjhy,/m/083vt", "caption": "Thumping noise followed by a tool sawing wood" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y1ed87LLY97k.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1ed87LLY97k.npy", "labels": "/m/07rjwbb", "caption": "A fan sound and a tapping noise" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YC8kR19NvynA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YC8kR19NvynA.npy", "labels": "/m/02qldy,/m/05zppz,/m/09x0r", "caption": "A male speaking over a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/YxqtrbqDlz28.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YxqtrbqDlz28.npy", "labels": "/m/01hsr_", "caption": "A sneeze occurs followed by sniffling and the start of another sneeze, while a baby coos in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part4/Y2sZhC_mKeic.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y2sZhC_mKeic.npy", "labels": "/m/01yrx,/m/068hy,/m/07qrkrw", "caption": "A cat meowing followed by metal clacking as a water sprinkler sprays in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YHg6HxylRGDo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YHg6HxylRGDo.npy", "labels": "/m/012n7d,/m/03j1ly,/m/03kmc9", "caption": "Emergency sirens wailing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YJfaj4P3us9M.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YJfaj4P3us9M.npy", "labels": "/m/02c8p,/m/07cx4", "caption": "Dialing and clicking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YC4JwGJQ2dUA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YC4JwGJQ2dUA.npy", "labels": "/m/02qldy,/m/05zppz,/m/09x0r,/m/0brhx", "caption": "Male yelling loudly and forcefully" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YPkmpxrsidZM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YPkmpxrsidZM.npy", "labels": "/m/028ght,/m/09x0r", "caption": "Applause, a female speech and whistling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9PN4gyxpH2M.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9PN4gyxpH2M.npy", "labels": "/m/09x0r,/t/dd00112", "caption": "A man and a woman talking then the crinkling of paper" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/YjinJkonlrWc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YjinJkonlrWc.npy", "labels": "/m/09ct_,/m/09x0r", "caption": "A toy helicopter flying as a man speaks in the background while wind blows into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YlrKGCtSsAkA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YlrKGCtSsAkA.npy", "labels": "/m/09ct_", "caption": "A toy helicopter flying as wind blows into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YFc9pG54DDJM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YFc9pG54DDJM.npy", "labels": "/m/01jt3m,/m/0838f", "caption": "Toilet flushing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part9/Y7upINC4seBw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y7upINC4seBw.npy", "labels": "/m/019jd,/m/02rlv9,/m/07yv9,/m/09x0r", "caption": "A man talking as an idle motorboat engine runs and water trickles while wind is blowing into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y7XUt6sQS7nM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y7XUt6sQS7nM.npy", "labels": "/m/07bgp,/m/07q0h5t,/m/09x0r", "caption": "Sheep baaing with young female voice and wind gusts" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/Yc0IggDOisOo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yc0IggDOisOo.npy", "labels": "/m/0395lw,/m/09x0r", "caption": "Seagulls call and people talk while a bell rings" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YTSdAJWJ-tW0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YTSdAJWJ-tW0.npy", "labels": "/m/012f08,/m/07yv9,/m/0k4j,/t/dd00134", "caption": "People speak with passing traffic" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YmWqH2xwjkYA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YmWqH2xwjkYA.npy", "labels": "/m/01j3sz,/m/09x0r", "caption": "A baby laughs and women laugh and speak" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YlJayhiVzl_E.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YlJayhiVzl_E.npy", "labels": "/m/019jd,/m/02rlv9,/m/03m9d0z,/t/dd00092", "caption": "Motorboat motor and high winds" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YF-47fRplQEc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YF-47fRplQEc.npy", "labels": "/m/07bgp,/m/07q0h5t,/m/09x0r", "caption": "Different female voices speaking followed by sheep bleating from a distance and voices of young people shortly thereafter" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YriM7b5bJ9KQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YriM7b5bJ9KQ.npy", "labels": "/m/01j3sz,/m/09x0r", "caption": "Several people laughing continuously with brief clanking and speech" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YQTSKjweEWew.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YQTSKjweEWew.npy", "labels": "/m/03m9d0z,/m/09x0r,/t/dd00129", "caption": "Wind blowing followed by a man speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/YfBYDJWChe5c.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YfBYDJWChe5c.npy", "labels": "/m/01d3sd", "caption": "A person snoring at a rhythmic pace" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part0/Y-EaZ7EJJUl0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y-EaZ7EJJUl0.npy", "labels": "/m/023pjk,/m/04brg2", "caption": "A person speaks with distant humming and nearby clinking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part7/Y5QZ0NtdoKJ8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y5QZ0NtdoKJ8.npy", "labels": "/m/02fs_r,/m/07pp_mv,/m/09x0r", "caption": "A series of electronic beeping as a woman is talking and birds chirp in the background alongside a camera muffling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YPvWI4p74UOs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YPvWI4p74UOs.npy", "labels": "/m/019jd,/m/02rlv9,/m/07yv9,/m/09x0r", "caption": "A man laughing followed by a muffled boat motor running as a man shouts in the distance during water flowing gently and seagulls squawking alongside wind blowing into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part7/Y6CDl4CqOgMg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y6CDl4CqOgMg.npy", "labels": "/m/068hy,/m/0bt9lr,/m/0jbk,/t/dd00136", "caption": "A dog panting and some rustling of footsteps" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y2JutOgAnqWA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y2JutOgAnqWA.npy", "labels": "/m/01d380,/m/07k1x,/m/0_ksk", "caption": "A power tool with an electric motor is used for drilling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YPZBUdlKwX04.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YPZBUdlKwX04.npy", "labels": "/m/09x0r,/m/0j2kx,/m/0j6m2", "caption": "Water is falling, splashing and gurgling, a crowd of people talk in the background, and an adult male speaks in the foreground" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YndxkSQKxaak.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YndxkSQKxaak.npy", "labels": "/m/04_sv,/m/07yv9,/m/09x0r", "caption": "A motorcycle engine is running while a man is talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part27/Ya0yXS7PmVR0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ya0yXS7PmVR0.npy", "labels": "/m/07qlf79", "caption": "Ocean waves crashing as water trickles and splashes" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YJon_DEFqsfM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YJon_DEFqsfM.npy", "labels": "/m/020bb7,/m/06_y0by,/m/09ddx", "caption": "Birds are chirping, ducks are quacking and other bird whistling noises" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part9/Y8nUqSYC66mI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y8nUqSYC66mI.npy", "labels": "/m/0j6m2", "caption": "Yelling and water flowing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part38/YwAZrOPvul4Y.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YwAZrOPvul4Y.npy", "labels": "/m/09x0r,/t/dd00112", "caption": "A man is speaking with crinkling background noise" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YSL3wB5sDcdw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YSL3wB5sDcdw.npy", "labels": "/m/09t49,/m/0d31p", "caption": "Wind is blowing while a vacuum machine is in use" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part19/YMdlEswBfZMQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YMdlEswBfZMQ.npy", "labels": "/m/07rgt08,/m/09x0r,/m/0ytgt,/t/dd00125", "caption": "A group of children and a woman talking followed by a young girl talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YCBwXKOpJY_o.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YCBwXKOpJY_o.npy", "labels": "/m/01h8n0,/m/02zsn,/m/09x0r,/m/0ytgt", "caption": "A woman and child speak" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YC9NC7wJ7C3w.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YC9NC7wJ7C3w.npy", "labels": "/m/02qldy,/m/02zsn,/m/09x0r", "caption": "A woman speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y0rSETXszQM0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y0rSETXszQM0.npy", "labels": "/m/028v0c,/m/04_sv,/m/07yv9,/t/dd00128", "caption": "Starting a motorcycle" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/YwrQDkX0NbTA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YwrQDkX0NbTA.npy", "labels": "/m/019jd,/m/02rlv9,/m/07yv9", "caption": "A boat engine revving up" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3ndid3jni7M.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3ndid3jni7M.npy", "labels": "/m/01g50p,/m/0284vy3,/m/06d_3,/m/07jdr,/m/07rwm0c", "caption": "A train horn blows as a train approaches with warning bells ringing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YD96OO7nYYsg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YD96OO7nYYsg.npy", "labels": "/m/07q2z82,/m/07yv9,/m/0k4j", "caption": "A automobile running and then accelerating." }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YPWjEfOkb6ro.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YPWjEfOkb6ro.npy", "labels": "/m/07swgks,/m/09x0r", "caption": "Water trickling and dripping as a crowd of people talk in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part19/YMTaLknnq4wc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YMTaLknnq4wc.npy", "labels": "/m/01w250", "caption": "Whistling with some distant humming and a girl singing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3MoF8myFs8Y.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3MoF8myFs8Y.npy", "labels": "/m/034srq,/m/03m9d0z,/m/05kq4,/t/dd00092", "caption": "Wind blowing and waves crashing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part0/Y-FW109cbv0g.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y-FW109cbv0g.npy", "labels": "/m/01hsr_,/m/09x0r", "caption": "A man speaks followed by a sneeze and a laugh" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part9/Y7fmOlUlwoNg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y7fmOlUlwoNg.npy", "labels": "/m/09x0r,/m/0llzx,/t/dd00127", "caption": "A machine is making clicking sound as people talk in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YQHfyKaOHSz4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YQHfyKaOHSz4.npy", "labels": "/m/07st88b,/m/09ld4", "caption": "'An insect buzzing as hollow wood clanks twice followed by a person gulping and a frog croaking proceeded by another insect buzzing and guitar music begins playing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YCMNlIW6Lkwc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YCMNlIW6Lkwc.npy", "labels": "/m/014zdl,/m/07qsvvw,/m/09x0r", "caption": "Some men speeches low followed by an explosion, then the man speeches louder and laugh" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/YeqcdsdLz954.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YeqcdsdLz954.npy", "labels": "/m/014zdl,/m/07qsvvw", "caption": "A synthesized whooshing followed by an explosion and fire crackling while gusts of wind blow" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part9/Y8Zo30kV5aiI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y8Zo30kV5aiI.npy", "labels": "/m/012n7d,/m/03j1ly,/m/03kmc9", "caption": "An ambulance siren increases in intensity and then recedes as the ambulance drives away" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9xoYx3lTJ9I.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9xoYx3lTJ9I.npy", "labels": "/m/019jd,/m/02rlv9,/m/03m9d0z,/t/dd00092", "caption": "Wind gusts as a motorboat speeds by with water splashing, then people nearby speak" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YJhGp7HmRQxg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YJhGp7HmRQxg.npy", "labels": "/m/03k3r,/m/07q5rw0,/m/09x0r,/m/0jbk", "caption": "Wind blowing and metal bangs followed by a horse neigh" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YsJrFyjfrL-g.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YsJrFyjfrL-g.npy", "labels": "/m/0llzx", "caption": "A sewing machine lightly operating after a couple of metal clacks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YXrJcmftCY04.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YXrJcmftCY04.npy", "labels": "/m/028ght", "caption": "A crowd of people cheering and applauding" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/YwnqUgK_-fo4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YwnqUgK_-fo4.npy", "labels": "/m/07bgp,/m/09x0r,/m/0jbk", "caption": "Several clicks and pops with people cheering and yodeling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/YeYbFtxZmKL4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YeYbFtxZmKL4.npy", "labels": "/m/03k3r,/m/09x0r,/m/0jbk", "caption": "Clip-clops from a horse in the distant with some knocking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YKVAIaRPry24.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YKVAIaRPry24.npy", "labels": "/m/01h3n,/m/03vt0,/m/0h2mp", "caption": "Buzzing from a nearby insect" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YNtQiduPRiRg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YNtQiduPRiRg.npy", "labels": "/m/01j3sz,/m/09x0r", "caption": "A man and a young girl laughing as a power tool sands a hard surface." }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part7/Y5iTRKJqUIw8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y5iTRKJqUIw8.npy", "labels": "/m/07qjznl,/m/09x0r", "caption": "Bell dings while people talk and a horn blows" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YK2kIOBeCfuo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YK2kIOBeCfuo.npy", "labels": "/m/028ght,/m/09x0r", "caption": "Speaking and various laughter followed by laughter" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part1/Y0G7rb74R-2A.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y0G7rb74R-2A.npy", "labels": "/m/02qldy,/m/05zppz,/m/09x0r", "caption": "A man speaks as an audience laughs" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YJp64Whpr3BA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YJp64Whpr3BA.npy", "labels": "/m/0llzx", "caption": "A television plays in the distant background and then a sewing machine starts up" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part15/YG0IsabU5hn4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YG0IsabU5hn4.npy", "labels": "/m/09t49,/t/dd00092", "caption": "Wind blowing and ocean in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YFL8KTgMGrN4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YFL8KTgMGrN4.npy", "labels": "/m/06wzb,/m/07rjwbb", "caption": "Vacuum cleaner sucks something." }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YKtTLsveexOg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YKtTLsveexOg.npy", "labels": "/m/0llzx", "caption": "Slow humming and rustling along with quick sewing machine sounds" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/Ydxow2DcTrwk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ydxow2DcTrwk.npy", "labels": "/m/0ngt1", "caption": "A man talking followed by another man laughing as rain falls and thunder roars in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9BGLAUSF0sk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9BGLAUSF0sk.npy", "labels": "/m/01jwx6,/m/0chx_", "caption": "Humming of an idling engine" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YPWjEfOkb6ro.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YPWjEfOkb6ro.npy", "labels": "/m/07swgks,/m/09x0r", "caption": "Water running with distant speech in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3qTL7QRk-tg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3qTL7QRk-tg.npy", "labels": "/m/07swgks,/m/0j6m2", "caption": "Gurgling water with men singing in background metal scraping metal" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YHqndxoujCYI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YHqndxoujCYI.npy", "labels": "/m/07qjznl,/m/09x0r", "caption": "Clock chiming with a laughter in background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/Yek9Fsmm3xqk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yek9Fsmm3xqk.npy", "labels": "/m/019jd,/m/03m9d0z,/m/056ks2,/m/07yv9", "caption": "Wind blows as water splashes" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part4/Y2ceUOv8A3FE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y2ceUOv8A3FE.npy", "labels": "/m/01g50p,/m/0284vy3,/m/06d_3,/m/07jdr", "caption": "A train running on railroad tracks as a train horn blows several times alongside a child yelling in the distance followed by a man speaking then a child speaking in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YFf8bCCJfVX4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YFf8bCCJfVX4.npy", "labels": "/m/032s66", "caption": "An air gun firing rapidly followed by plastic rattling and a young boy talking while footsteps walk over grass" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YDc2WEiRk0rA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YDc2WEiRk0rA.npy", "labels": "/m/07qlf79", "caption": "High powered hissing and wind blowing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/Yo_3MDLl_aH0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yo_3MDLl_aH0.npy", "labels": "/m/032s66,/m/0_1c", "caption": "Artillery cannons firing several times with an echo" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part24/YV8A0VRGdgwM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YV8A0VRGdgwM.npy", "labels": "/m/03fwl,/m/07q0h5t,/m/0ch8v,/m/0jbk", "caption": "Goat bleating and making tickling noise" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YBQ-r9mEHssU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBQ-r9mEHssU.npy", "labels": "/m/03k3r,/m/07rv9rh,/m/09x0r,/m/0jbk", "caption": "A horse is clip-clopping with a woman is laughing in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y2KEfkDO6hlA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y2KEfkDO6hlA.npy", "labels": "/m/012f08,/m/07yv9,/m/0k4j,/t/dd00134", "caption": "Several motor vehicles accelerating" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YndxkSQKxaak.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YndxkSQKxaak.npy", "labels": "/m/04_sv,/m/07yv9,/m/09x0r", "caption": "A man speaking followed by another man speaking in the background as a motorcycle engine runs idle" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YK8-b0VtNOqA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YK8-b0VtNOqA.npy", "labels": "/m/03k3r,/m/09x0r,/m/0jbk", "caption": "A horse vocalizing and muffled speech" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YsqWyxUObwkw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YsqWyxUObwkw.npy", "labels": "/m/019jd,/m/02rlv9,/m/07yv9", "caption": "Water and rustling and then a motor starts" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part7/Y6OlHuvJR_Dk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y6OlHuvJR_Dk.npy", "labels": "/m/07yv9,/m/09ct_", "caption": "Helicopter flying overhead sounds" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/YxIztYnMIWUA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YxIztYnMIWUA.npy", "labels": "/m/01hnzm,/m/07cx4,/m/07pp8cl", "caption": "A telephone bell rings" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y7QN3lwOzfdg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y7QN3lwOzfdg.npy", "labels": "/m/07cx4,/m/09x0r", "caption": "A man and woman speak" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YkF1KWybdRpM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YkF1KWybdRpM.npy", "labels": "/m/014yck,/m/07yv9,/m/0cmf2,/m/0k5j", "caption": "An airplane is taking flight" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/Ygf6H_MWCqjw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ygf6H_MWCqjw.npy", "labels": "/m/015p6,/m/09ddx", "caption": "A duck quacking followed by camera muffling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YL6rnV0oNIII.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YL6rnV0oNIII.npy", "labels": "/m/07qjznl", "caption": "Digital beeping with some clicks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YW7OJevEgq7w.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YW7OJevEgq7w.npy", "labels": "/m/05tny_,/m/068hy,/m/07rc7d9,/m/0bt9lr,/m/0jbk", "caption": "A dog is panting in a very fast tempo while barking few times" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3IScngdQA4I.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3IScngdQA4I.npy", "labels": "/m/02dgv,/m/09x0r", "caption": "A woman talking as a door closes shut followed by another woman talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y7D7xgd4WJ50.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y7D7xgd4WJ50.npy", "labels": "/m/0395lw", "caption": "Several bells are ringing together" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/YhxbmDeNSO6Q.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YhxbmDeNSO6Q.npy", "labels": "/m/09x0r,/m/0llzx", "caption": "A sewing machine sews followed by a man talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/YpHNMcX-9FDs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YpHNMcX-9FDs.npy", "labels": "/m/068hy,/m/0bt9lr,/m/0jbk,/t/dd00136", "caption": "Whimpering of several small dogs" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YR8bHTHnF8j4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YR8bHTHnF8j4.npy", "labels": "/m/07yv9,/m/09ct_,/m/0k5j", "caption": "Vibrations and wind with loud humming of an engine" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part15/YG0IsabU5hn4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YG0IsabU5hn4.npy", "labels": "/m/09t49,/t/dd00092", "caption": "Heavy, continuous wind" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YBrPFQDr99Gg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBrPFQDr99Gg.npy", "labels": "/m/02qldy,/m/05zppz,/m/09x0r", "caption": "Clapping and cheering and then a male speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YmSF_FqBtRPs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YmSF_FqBtRPs.npy", "labels": "/m/01hnzm,/m/07cx4", "caption": "A telephone ringing loudly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/Yg_P29ucKj78.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yg_P29ucKj78.npy", "labels": "/m/07yv9,/m/0k4j,/t/dd00134", "caption": "Humming and vibrations from a speeding car" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/Yne2DpKCIr4Y.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yne2DpKCIr4Y.npy", "labels": "/m/034srq,/m/03m9d0z,/m/05kq4,/t/dd00092", "caption": "Ocean waves crashing as wind blows into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YQ3vkJMVMbC8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YQ3vkJMVMbC8.npy", "labels": "/m/01jt3m", "caption": "A toilet flushes twice and a child speaks." }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part7/Y6Pywt0f_NFY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y6Pywt0f_NFY.npy", "labels": "/m/02jz0l,/m/03dnzn,/m/0838f", "caption": "Water trickling as a machine motor hums followed by water spraying from a shower" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/Yt4prXmPwthg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yt4prXmPwthg.npy", "labels": "/m/09x0r,/m/0llzx", "caption": "Loud vibrations from a sewing machine followed by a woman speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YLvMA1Wcgu3w.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YLvMA1Wcgu3w.npy", "labels": "/m/09ld4", "caption": "Several frogs chirping near and far with men speaking and some banging" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/Yz1ax0QPpd14.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yz1ax0QPpd14.npy", "labels": "/m/015p6,/m/09ddx", "caption": "A large duck quacks and small ducks chirp" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/Yp9qRTh4BmSE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yp9qRTh4BmSE.npy", "labels": "/m/032s66,/m/04zjc", "caption": "Adult males shout in the distance and an adult male shout close by, two adult males speak in the foreground, and gunfire erupts" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YHZ9O6sc7cLA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YHZ9O6sc7cLA.npy", "labels": "/m/05tny_,/m/07rc7d9,/m/0bt9lr", "caption": "A woman speaks and continues to do so as a dog starts barking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/Yq46VXJ6JN9M.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yq46VXJ6JN9M.npy", "labels": "/m/07qlf79", "caption": "Birds tweeting followed by spraying" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YQt0_xTadAT0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YQt0_xTadAT0.npy", "labels": "/m/09ld4", "caption": "High pitched croaking of frogs with some rustling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part4/Y2RjqBRzmxaM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y2RjqBRzmxaM.npy", "labels": "/m/06mb1,/m/07r10fb,/t/dd00038", "caption": "Music with rain falling and a woman speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/YhVUmQfBIYe8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YhVUmQfBIYe8.npy", "labels": "/m/02dgv", "caption": "Some rustling with distant birds chirping and wind blowing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YOmmPaIAXN0s.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YOmmPaIAXN0s.npy", "labels": "/m/03k3r,/m/07rv9rh,/m/09x0r,/m/0jbk", "caption": "A man speaks followed by clicking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/Ygr5Zss89yLQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ygr5Zss89yLQ.npy", "labels": "/m/01bjv,/m/07yv9,/m/09x0r", "caption": "Bus pulling up then woman speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YrINmxSXMR-s.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YrINmxSXMR-s.npy", "labels": "/m/07qdb04,/m/09ddx,/m/0jbk", "caption": "Water splashing as duck quacks followed by brief laughter" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/Yy1a8PntuXYw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yy1a8PntuXYw.npy", "labels": "/m/01jt3m", "caption": "Mechanical humming followed by a flushing toilet" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y1nUOGZgSzZo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1nUOGZgSzZo.npy", "labels": "/m/07swgks,/m/09x0r,/m/0j6m2", "caption": "A man giggles as the wind blows, and water splashes with people speaking in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YrvtA7c1I4xo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YrvtA7c1I4xo.npy", "labels": "/m/07rqsjt", "caption": "Whooshing of wind followed by a man speaking with sneakers squeaking on hardwood" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YsI7_ycEYzAY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YsI7_ycEYzAY.npy", "labels": "/m/07qjznl,/m/07qjznt", "caption": "A clock ticks repeatedly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YOFVzrakJhbw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YOFVzrakJhbw.npy", "labels": "/m/068hy,/m/07bgp,/m/07q0h5t,/m/0jbk", "caption": "A woman laughing followed by the bleating of sheep and a soft breeze" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YS0SQyFXbqF8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YS0SQyFXbqF8.npy", "labels": "/m/09ld4", "caption": "A child talking then laughing with a man as an animal gurgles" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part4/Y30D1tqNFHMc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y30D1tqNFHMc.npy", "labels": "/m/01jwx6,/m/0chx_", "caption": "A loud white noise and then some beeping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YB-gTt3_rceQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YB-gTt3_rceQ.npy", "labels": "/m/09x0r,/m/0ytgt,/t/dd00125", "caption": "A child talking followed by a group of people talking then a man talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YQKHpSAAjakY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YQKHpSAAjakY.npy", "labels": "/m/04_sv,/m/07yv9,/m/09x0r,/t/dd00128", "caption": "A man talking followed by an idle motorbike engine running" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YZY4aGEniU_E.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YZY4aGEniU_E.npy", "labels": "/m/07p9k1k", "caption": "Food and oil sizzling followed by steam hissing as a man talks while music plays in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YQTSKjweEWew.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YQTSKjweEWew.npy", "labels": "/m/03m9d0z,/m/09x0r,/t/dd00129", "caption": "A wind blows as a man speaks outside" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4lv9aLXtud0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4lv9aLXtud0.npy", "labels": "/m/03q5_w,/m/09x0r,/t/dd00125", "caption": "A man shouting before and after someone belching" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y2KEfkDO6hlA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y2KEfkDO6hlA.npy", "labels": "/m/012f08,/m/07yv9,/m/0k4j,/t/dd00134", "caption": "Car engine accelerates and shifts gears" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YXplKBvZaHXA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YXplKBvZaHXA.npy", "labels": "/m/04_sv,/m/07yv9,/m/09x0r,/t/dd00129", "caption": "A motorbike engine driving then accelerating as a man is talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YOr7umk40TZA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YOr7umk40TZA.npy", "labels": "/m/01jwx6", "caption": "Vibrations from a humming engine" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YJmWaRt8-u0s.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YJmWaRt8-u0s.npy", "labels": "/m/04_sv,/m/07yv9,/m/09x0r,/t/dd00066", "caption": "Motorcycles running with men talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part24/YUjje3lSabsg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YUjje3lSabsg.npy", "labels": "/m/01d3sd", "caption": "A person snoring" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YYIqpIjjee00.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YYIqpIjjee00.npy", "labels": "/m/01jt3m", "caption": "A toilet flushing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/YfPqj3nnwQOI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YfPqj3nnwQOI.npy", "labels": "/m/0j6m2", "caption": "Ocean waves crashing and water trickling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/Yhrv6fwnmBkY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yhrv6fwnmBkY.npy", "labels": "/m/068hy,/m/07rc7d9,/m/09b5t,/m/09x0r,/m/0bt9lr,/m/0jbk,/t/dd00136", "caption": "A rooster clucking followed by a dog whimpering proceeded by a man laughing then talking before a dog barks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part0/Y--0w1YA1Hm4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y--0w1YA1Hm4.npy", "labels": "/m/01bjv,/m/07yv9,/m/09x0r", "caption": "Humming of an engine with a woman and men speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YmUGmCSNETcg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YmUGmCSNETcg.npy", "labels": "/m/07ptfmf,/m/0dxrf", "caption": "Frying food with the click tap of stirring" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part27/Y_z-bidQYVao.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y_z-bidQYVao.npy", "labels": "/m/07qjznl,/m/09x0r", "caption": "Male rapping and screaming" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YEY4p0_NJVQs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YEY4p0_NJVQs.npy", "labels": "/m/02qldy,/m/02zsn,/m/09x0r", "caption": "A woman is performing a speech" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/YhGWarNR6xmg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YhGWarNR6xmg.npy", "labels": "/m/06wzb,/m/07rjwbb", "caption": "Rain pitter-patters and wind blows" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YD2Xc_jZllDY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YD2Xc_jZllDY.npy", "labels": "/m/068hy,/m/07r_k2n,/m/07rc7d9,/m/09x0r,/m/0bt9lr,/m/0jbk", "caption": "A man talking as a dog is barking in the distance and wind blows into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y7P6lcyeDKNI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y7P6lcyeDKNI.npy", "labels": "/m/0199g,/m/04_sv,/m/07yv9,/m/09x0r", "caption": "A bicycle peddling on dirt and gravel followed by a man speaking then laughing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YWUyeFOyKIg0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YWUyeFOyKIg0.npy", "labels": "/m/07yv9,/m/09x0r,/m/0k4j,/m/0ltv,/t/dd00129", "caption": "A race car engine hums in the distance as wind blows into a microphone and a crowd of people talk followed by a race car speeding by" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y7P0N61TVOxE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y7P0N61TVOxE.npy", "labels": "/m/034srq,/m/03m9d0z,/m/05kq4,/m/085jw", "caption": "A motorboat engine running and water splashing then fading away as instrumental music plays and a crowd of people talk" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YrvDcg9DoNKA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YrvDcg9DoNKA.npy", "labels": "/m/0ngt1", "caption": "Thunder crashes and rain splashes, during which two adult males speak" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YLbken4JCr94.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YLbken4JCr94.npy", "labels": "/m/06mb1,/m/0jb2l,/m/0ngt1", "caption": "Rain falling with thunder in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part1/Y0On6-JiVwRs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y0On6-JiVwRs.npy", "labels": "/m/01yrx,/m/068hy,/m/09t49,/m/0jbk,/t/dd00128", "caption": "A cat meowing as wind blows into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YLvMA1Wcgu3w.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YLvMA1Wcgu3w.npy", "labels": "/m/09ld4", "caption": "A man speaking as frogs croak and crickets chirp while a motorboat engine runs alongside several plastic clacks and clanging" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part19/YMtK8L8gXRrI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YMtK8L8gXRrI.npy", "labels": "/m/01jt3m", "caption": "A toilet is flushing followed by a cat meowing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part9/Y8VOibo9Q_Dc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y8VOibo9Q_Dc.npy", "labels": "/m/09ddx,/m/09x0r,/m/0jbk", "caption": "Chirping and water splashing lightly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YXPebkNzsnRI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YXPebkNzsnRI.npy", "labels": "/m/01w250,/m/09x0r", "caption": "A person is whistling and baby is laughing followed by a man talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YNeZerAPXR-A.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YNeZerAPXR-A.npy", "labels": "/m/01j3sz,/m/09x0r,/t/dd00125", "caption": "Laughter and speech and a clap" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part15/YGSHcgY6ATkQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YGSHcgY6ATkQ.npy", "labels": "/m/0316dw", "caption": "A man is talking as a person types on a keyboard" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/Yc6YJgZ3qzOw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yc6YJgZ3qzOw.npy", "labels": "/m/09ct_", "caption": "High frequency humming and vibrations" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/Ye2rScj9UyMs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ye2rScj9UyMs.npy", "labels": "/m/015p6,/m/0h0rv,/t/dd00125", "caption": "Pigeons coo with some light rustling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YBwnGxJD9xh8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBwnGxJD9xh8.npy", "labels": "/m/03fwl,/m/068hy,/m/07bgp,/m/0jbk", "caption": "A man speaks, and a goat bleats" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part38/Yv7BaYF0kagM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yv7BaYF0kagM.npy", "labels": "/m/07yv9,/m/0k5j,/t/dd00129", "caption": "Aircraft engine running constantly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/Yq4YFJA5pFXc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yq4YFJA5pFXc.npy", "labels": "/m/09ct_,/t/dd00129", "caption": "A helicopter engine whines as it starts" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YUE3XnVFodMI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YUE3XnVFodMI.npy", "labels": "/m/028ght,/m/09x0r", "caption": "A static distortion followed by a woman talking while a crowd of people applaud and cheer" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part24/YVZLZ08k3YeA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YVZLZ08k3YeA.npy", "labels": "/m/01d3sd,/m/09x0r", "caption": "A man talking as a person snores" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YDn3buZWMzwY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YDn3buZWMzwY.npy", "labels": "/m/01d3sd,/m/09x0r", "caption": "A person snores as a man talks and a person laughs" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/YxUWSHYoslPQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YxUWSHYoslPQ.npy", "labels": "/m/04brg2,/m/09x0r", "caption": "A man is speaking with tapping noises and dishes being moved" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part0/Y-BUWGM7qeUM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y-BUWGM7qeUM.npy", "labels": "/m/06mb1", "caption": "Heavy rain pouring on a surface as wind blows into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/YwBs02amFGXs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YwBs02amFGXs.npy", "labels": "/m/015p6,/m/0h0rv,/t/dd00125,/t/dd00129", "caption": "Birds are making noises and flapping wings, and a rooster crows" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y1IoHRTUp86c.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1IoHRTUp86c.npy", "labels": "/m/07yv9,/m/0k5j,/t/dd00129", "caption": "An aircraft engine humming as a woman speaks over an intercom followed by an aircraft engine accelerating" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YtTB0BK39JI8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YtTB0BK39JI8.npy", "labels": "/m/0395lw", "caption": "A bell sounds the horn" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YlX3k5p2I_g0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YlX3k5p2I_g0.npy", "labels": "/m/014yck,/m/02mk9,/m/07yv9,/m/09x0r,/m/0cmf2,/m/0k5j", "caption": "Men speak followed by vibrations and hissing with passing traffic in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part24/YUV1kdjwpy6U.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YUV1kdjwpy6U.npy", "labels": "/m/01jwx6,/m/09x0r", "caption": "A rattling motor slowly comes to a stop" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YWWkhzcmx3VE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YWWkhzcmx3VE.npy", "labels": "/m/09ddx", "caption": "A duck quacking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YtTB0BK39JI8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YtTB0BK39JI8.npy", "labels": "/m/0395lw", "caption": "Wood clacking and scrapping as bells chime while a muffled clock ticks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YIhvXtS9-IxM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YIhvXtS9-IxM.npy", "labels": "/m/07yv9,/m/09ct_", "caption": "A helicopter running" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y7MLERaOgK_Y.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y7MLERaOgK_Y.npy", "labels": "/m/0llzx", "caption": "A girl sings while a sewing machine stitches and then speaks when it stops" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part1/Y0G7rb74R-2A.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y0G7rb74R-2A.npy", "labels": "/m/02qldy,/m/05zppz,/m/09x0r", "caption": "A man speaking on a microphone as a crowd of people laugh followed by dinner plates clacking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YSZ6CcXINiiE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YSZ6CcXINiiE.npy", "labels": "/m/014zdl,/m/07qsvvw,/m/09x0r", "caption": "A man talking as music is playing in the background followed by a popping explosion then a man laughing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YErxgH5g3Kx0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YErxgH5g3Kx0.npy", "labels": "/m/03k3r,/m/07rv9rh,/m/0jbk", "caption": "Hissing and buzzing of insects with a horse neigh and clip clops" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part0/Y-NrFeH-kBSM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y-NrFeH-kBSM.npy", "labels": "/m/032s66", "caption": "A gun cocking then firing as metal clinks on the ground alongside footsteps shuffling then a man talking with a synthesized slide whistle" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YrJVXE6Axtrg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YrJVXE6Axtrg.npy", "labels": "/m/09x0r,/m/0llzx", "caption": "A man speaking as a sewing machine rapidly operates followed by another man speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YKVAIaRPry24.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YKVAIaRPry24.npy", "labels": "/m/01h3n,/m/03vt0,/m/0h2mp", "caption": "Buzzing and scratching with some light banging" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part9/Y8GHLfJ6y6zA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y8GHLfJ6y6zA.npy", "labels": "/m/01m2v,/m/0316dw,/m/09x0r", "caption": "Some whooshing followed by a man speaking and clicking on a computer" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/Ylq9RvAA4mqY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ylq9RvAA4mqY.npy", "labels": "/m/07ptfmf,/m/0dxrf", "caption": "A man talking then clearing his throat as food sizzles and a metal pot clangs" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part19/YNDaVSIJaXVs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YNDaVSIJaXVs.npy", "labels": "/m/014yck,/m/07yv9,/m/0cmf2,/m/0k5j,/t/dd00128", "caption": "A jet engine idles as the wind blows" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/Ylq9RvAA4mqY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ylq9RvAA4mqY.npy", "labels": "/m/07ptfmf,/m/0dxrf", "caption": "A man speaks as food sizzles" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YAgaiowyYt88.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YAgaiowyYt88.npy", "labels": "/m/02dgv", "caption": "A door pounding and rattling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YKnsKf9KoNds.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YKnsKf9KoNds.npy", "labels": "/m/07cx4,/m/09x0r", "caption": "A man speaking followed by another man speaking through a telephone speaker" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/YfGGYeXR_LS8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YfGGYeXR_LS8.npy", "labels": "/m/01w250,/m/09x0r", "caption": "A man talking as another person whistles while water trickles on a hard surface in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YBzHTqyX69pI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBzHTqyX69pI.npy", "labels": "/m/07pdjhy,/m/083vt", "caption": "A rasping sound on wood along with some pigeons cooing followed a woman speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YPkmpxrsidZM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YPkmpxrsidZM.npy", "labels": "/m/028ght,/m/09x0r", "caption": "A crowd applauds followed by a woman and a man speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YE6FH_xp3I54.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YE6FH_xp3I54.npy", "labels": "/m/07pggtn,/m/09x0r,/m/0jbk,/t/dd00129", "caption": "A man speaks followed by chirping birds" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YbhlhcGONisM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YbhlhcGONisM.npy", "labels": "/m/0316dw,/m/09x0r", "caption": "A man speaks followed by thumps and clicks with some faint grunts" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YIJ6pm5Kns8A.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YIJ6pm5Kns8A.npy", "labels": "/m/03q5_w,/m/09x0r", "caption": "Clicking followed by a burp and laughing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y1slvoNgzBLE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1slvoNgzBLE.npy", "labels": "/m/01g50p,/m/06d_3,/m/07jdr,/m/07yv9,/m/0912c9", "caption": "Subway train blowing its horn." }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YD1Sy7kRoaR8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YD1Sy7kRoaR8.npy", "labels": "/m/03k3r,/m/07rv9rh,/m/09x0r,/m/0jbk", "caption": "A woman speaking, followed by a child yelling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YJsoBpL86R5U.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YJsoBpL86R5U.npy", "labels": "/m/03fwl,/m/07q0h5t,/m/09x0r,/m/0jbk", "caption": "A man baaing followed by a goat baaing as a child and a woman talk while metal pots clank in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YNeWW30WZjPc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YNeWW30WZjPc.npy", "labels": "/m/01z5f,/m/05tny_,/m/068hy,/m/07rc7d9,/m/0bt9lr,/m/0jbk,/t/dd00125", "caption": "A dog barking and growling as plastic rattles and clanks against a hard surface" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4pf-PIymDhU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4pf-PIymDhU.npy", "labels": "/m/01d380,/m/07k1x,/m/0_ksk", "caption": "A power tool is in use" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y6TO9PEGpZcQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y6TO9PEGpZcQ.npy", "labels": "/m/012n7d,/m/012ndj,/m/03j1ly,/m/03kmc9", "caption": "Sirens of an ambulance and fire truck traveling and an engine idling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part38/Yv7BaYF0kagM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yv7BaYF0kagM.npy", "labels": "/m/07yv9,/m/0k5j,/t/dd00129", "caption": "An engine running" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YnD1K1Zo0qrM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YnD1K1Zo0qrM.npy", "labels": "/m/032s66,/m/04zjc", "caption": "Humming and rattling with rapid fire gunshots and loud bursts" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/YgW7s3YAthpI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YgW7s3YAthpI.npy", "labels": "/m/02jz0l,/m/0838f", "caption": "Glass placed on table, a container with liquid is shaken and then poured into the glass" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YJp64Whpr3BA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YJp64Whpr3BA.npy", "labels": "/m/0llzx", "caption": "Rustling and then a sewing machine sewing rapidly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YD2Xc_jZllDY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YD2Xc_jZllDY.npy", "labels": "/m/068hy,/m/07r_k2n,/m/07rc7d9,/m/09x0r,/m/0bt9lr,/m/0jbk", "caption": "A man talking with a dog barking in the distance as wind blows into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part9/Y8o-Y4QP8LWs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y8o-Y4QP8LWs.npy", "labels": "/m/023pjk,/m/04brg2", "caption": "Some clanking and banging and a man speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YB4SZwi9Ce3o.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YB4SZwi9Ce3o.npy", "labels": "/m/07q2z82,/m/07yv9,/m/09x0r,/m/0k4j", "caption": "A man speaks with a revving engine and clicking that stops" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y13CBvjHZhOA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y13CBvjHZhOA.npy", "labels": "/m/012f08,/m/07yv9,/m/0k4j,/t/dd00134", "caption": "Knocking sounds as race cars pass by" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/YeqcdsdLz954.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YeqcdsdLz954.npy", "labels": "/m/014zdl,/m/07qsvvw", "caption": "A synthesized explosion followed by a popping explosion and fire crackling then gusts of wind blowing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YXz56Q2Q5j5c.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YXz56Q2Q5j5c.npy", "labels": "/m/07k1x,/m/083vt", "caption": "Wood being scraped along with mechanical sounds" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/Yp9qRTh4BmSE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yp9qRTh4BmSE.npy", "labels": "/m/032s66,/m/04zjc", "caption": "Men speak followed by rapid gunshots" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YLVvS3s9dFKw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YLVvS3s9dFKw.npy", "labels": "/m/0130jx,/m/02jz0l,/m/0838f", "caption": "A man speaking while water runs in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4KObP7cREWw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4KObP7cREWw.npy", "labels": "/m/02mk9,/m/07yv9,/m/0k4j", "caption": "A mid-size motor vehicle engine is running and accelerates, and random knocks and whizzes occur" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/Yy93cZqNCtks.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yy93cZqNCtks.npy", "labels": "/m/032s66,/m/04zjc", "caption": "A man shouting as another man talks in the background while a series of gunshots fire and footsteps running on concrete followed by guns cocking and a dog growling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y1vCYiVvZ7VE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1vCYiVvZ7VE.npy", "labels": "/m/02qldy,/m/02zsn,/m/09x0r", "caption": "A woman is speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YQ0anPAIkfBE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YQ0anPAIkfBE.npy", "labels": "/m/0463cq4,/m/09x0r,/t/dd00002,/t/dd00125", "caption": "A baby sobs and then a woman speaks followed a woman laughing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YAR8-MVl_Mf8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YAR8-MVl_Mf8.npy", "labels": "/m/02dgv,/m/07rjzl8,/m/09x0r", "caption": "A man screaming followed by a loud metal object slamming shut then a series of thuds and a man speaking with audio static at the end" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YBA-lFjpzad4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBA-lFjpzad4.npy", "labels": "/m/012f08,/m/04_sv,/m/07yv9,/m/09x0r,/t/dd00134", "caption": "A man laughing as a motorcycle is accelerating followed by a person chuckling while music plays in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/YxBZnvfniA1c.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YxBZnvfniA1c.npy", "labels": "/m/09x0r,/m/0ytgt,/t/dd00125", "caption": "A man talking while a man talks over an intercom followed by a girl talking then a woman and group of men laughing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YRp4Ct_TQvAM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YRp4Ct_TQvAM.npy", "labels": "/m/06mb1,/m/09x0r", "caption": "Rain falling and male speech" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/Ys_EWjoiVfzo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ys_EWjoiVfzo.npy", "labels": "/m/0llzx", "caption": "A sewing machine operating and metal clanking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/YeXj9OAik5cc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YeXj9OAik5cc.npy", "labels": "/m/04_sv,/m/07yv9,/t/dd00128", "caption": "An idle motorbike engine running as a bird chirps in the background and wind blows into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/Yo_3MDLl_aH0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yo_3MDLl_aH0.npy", "labels": "/m/032s66,/m/0_1c", "caption": "A series of cannons firing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/Yn-JyOqYSLQM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yn-JyOqYSLQM.npy", "labels": "/m/07qlf79", "caption": "Metal clattering and rattling is ongoing, along with brief hissing, while many people talk in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4fz0-Kx2oNs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4fz0-Kx2oNs.npy", "labels": "/m/0dxrf", "caption": "Food and oil sizzling followed by a person snapping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YAJtNitYMa1I.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YAJtNitYMa1I.npy", "labels": "/m/07p9k1k,/m/0dxrf", "caption": "Food and oil sizzling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YFJkvAMLmejY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YFJkvAMLmejY.npy", "labels": "/m/0912c9,/m/09x0r,/t/dd00125", "caption": "People are whispering, and a horn sounds followed by laughter" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/YinSvboaSRwA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YinSvboaSRwA.npy", "labels": "/m/07k1x,/m/083vt,/m/09x0r", "caption": "A man talking as a machine motor hums followed by electronic buzzing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3wrdPAeqjVI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3wrdPAeqjVI.npy", "labels": "/m/083vt,/m/09x0r", "caption": "A man speaks followed by some ringing and footsteps" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/YpI_kPedctoo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YpI_kPedctoo.npy", "labels": "/m/04_sv,/m/07yv9,/m/09x0r", "caption": "A motorcycle engine is revving with low speech in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/YxqtrbqDlz28.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YxqtrbqDlz28.npy", "labels": "/m/01hsr_", "caption": "A sneeze occurs, followed by sniffling and a child babbling in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9XqkKuTqEOM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9XqkKuTqEOM.npy", "labels": "/m/02dgv", "caption": "Continuous clanking and rustling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YCMNlIW6Lkwc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YCMNlIW6Lkwc.npy", "labels": "/m/014zdl,/m/07qsvvw,/m/09x0r", "caption": "Camera muffling followed by a popping explosion as a group of people talk and silverware clacks in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YbA5zPFSFZAA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YbA5zPFSFZAA.npy", "labels": "/m/07rqsjt", "caption": "Static and beeping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part24/YVMsbrcHPBfk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YVMsbrcHPBfk.npy", "labels": "/m/03fwl", "caption": "A man mimics a goat bleating" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4_Cak7gvly4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4_Cak7gvly4.npy", "labels": "/m/07rqsjt", "caption": "Percussion music playing alongside a series of whooshes followed by a motor humming" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/Yt3VFlDiEKgY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yt3VFlDiEKgY.npy", "labels": "/m/03vt0,/m/09f96,/m/0h2mp", "caption": "An insect buzzing and quiet male speech" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9vZDsGjyh5M.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9vZDsGjyh5M.npy", "labels": "/m/07r04,/m/07yv9,/m/0k4j", "caption": "An engine running" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YnlC4UI4hZ60.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YnlC4UI4hZ60.npy", "labels": "/m/012f08,/m/02mk9,/m/07yv9,/m/0k4j", "caption": "An engine being turned over" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YPYP-r0nvbFk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YPYP-r0nvbFk.npy", "labels": "/m/07bgp,/m/07q0h5t,/m/09x0r", "caption": "Wind and a goat bleating while a man speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part0/Y-Sz4z0QwEuM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y-Sz4z0QwEuM.npy", "labels": "/m/03q5_w", "caption": "Someone belches very loudly two times" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YYqYCDis3EUA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YYqYCDis3EUA.npy", "labels": "/m/01h3n,/m/03vt0,/m/0h2mp", "caption": "Insects buzzing as wind blows into a microphone and birds chirp in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y7P0N61TVOxE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y7P0N61TVOxE.npy", "labels": "/m/034srq,/m/03m9d0z,/m/05kq4,/m/085jw", "caption": "A boat engine running as water splashes then cuts off while a group of people talk in the background alongside music playing proceeded by glass clanking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/Yjf4iyQPJSvk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yjf4iyQPJSvk.npy", "labels": "/m/07pqc89,/m/0838f,/m/0j2kx,/t/dd00129", "caption": "A stream of water trickling onto a hard surface and splashing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/Yy1a8PntuXYw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yy1a8PntuXYw.npy", "labels": "/m/01jt3m", "caption": "A toilet is flushed" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YXz56Q2Q5j5c.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YXz56Q2Q5j5c.npy", "labels": "/m/07k1x,/m/083vt", "caption": "Rustling and scraping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/Yh0M4RS8p_mo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yh0M4RS8p_mo.npy", "labels": "/m/01j3sz,/m/0463cq4", "caption": "Wicked laughter followed by a baby crying" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3Sml1wHcuxo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3Sml1wHcuxo.npy", "labels": "/m/01g50p,/m/0284vy3,/m/06d_3,/m/07jdr,/m/07rwm0c", "caption": "A train horn blasts as railroad rails go clickety-clack" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y6dLkgq9EKPE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y6dLkgq9EKPE.npy", "labels": "/m/01bjv,/m/07yv9,/m/09x0r", "caption": "A man is giving a speech" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YJZloTOdIY_c.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YJZloTOdIY_c.npy", "labels": "/m/03k3r,/m/07q5rw0,/m/07rv9rh,/m/0jbk", "caption": "Horses neighing and stomping on the ground" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YmW1EpJYcy_E.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YmW1EpJYcy_E.npy", "labels": "/m/04_sv,/m/07yv9,/t/dd00128", "caption": "A motorbike accelerating and revving as it drives by with wind blowing into a microphone and birds chirping in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part38/Yu8bQf0SnCVI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yu8bQf0SnCVI.npy", "labels": "/m/0130jx,/m/02jz0l,/t/dd00125", "caption": "Someone moving around followed by sink water running" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part0/Y-AheI8Epim4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y-AheI8Epim4.npy", "labels": "/m/07qsvvw,/m/09x0r", "caption": "Plastic crinkling followed by footsteps on concrete as metal clanging and a group of people talk in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part38/YvruDH_YLaPI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YvruDH_YLaPI.npy", "labels": "/m/032s66", "caption": "Gunshots are ongoing, and intermittent metal clinks are occurring" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YErxgH5g3Kx0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YErxgH5g3Kx0.npy", "labels": "/m/03k3r,/m/07rv9rh,/m/0jbk", "caption": "Clip clops with a distant neigh of a horse and repetitive high pitched vibrations" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YPtW0cZVprJQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YPtW0cZVprJQ.npy", "labels": "/m/01d3sd,/m/09x0r", "caption": "Snoring is ongoing, and an adult male speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/YeNG6fEiAE8c.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YeNG6fEiAE8c.npy", "labels": "/m/07bgp,/m/07q0h5t,/m/09x0r", "caption": "A man is laughing followed by a sheep bleating then man continues to talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YCMUuelJFJ7Q.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YCMUuelJFJ7Q.npy", "labels": "/m/07qjznl,/m/07qjznt", "caption": "A bell ringing followed by a clock ticking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/Yg_P29ucKj78.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yg_P29ucKj78.npy", "labels": "/m/07yv9,/m/0k4j,/t/dd00134", "caption": "Slight rattling is ongoing while a mid-size motor vehicle engine runs fast and accelerates, and then gears shift downward" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/Yq1ivQ_2fddk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yq1ivQ_2fddk.npy", "labels": "/m/07qlf79,/m/09x0r,/t/dd00128", "caption": "A young man talking and a man laughing in the background with a spraying sound." }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YSCow4mpBsGY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YSCow4mpBsGY.npy", "labels": "/m/01d3sd", "caption": "A person is snoring" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/YdP5DbAzTl5M.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YdP5DbAzTl5M.npy", "labels": "/m/019jd,/m/02rlv9,/m/07yv9,/m/09x0r", "caption": "A motorboat engine is running, and a man speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part15/YGMP8m09j5vk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YGMP8m09j5vk.npy", "labels": "/m/015p6,/m/020bb7,/m/07pggtn", "caption": "Birds chirping in the foreground and background as a dog barks in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YEvZ3jOMYWxk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YEvZ3jOMYWxk.npy", "labels": "/m/02qldy,/m/02zsn,/m/09x0r", "caption": "A woman is speaking in a quiet environment" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YrjUrB1WUpcI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YrjUrB1WUpcI.npy", "labels": "/m/07swgks", "caption": "A water faucet flowing then stopping followed by water draining down a pipe" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y5G6b_QWL3nY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y5G6b_QWL3nY.npy", "labels": "/m/07p9k1k,/m/0dxrf", "caption": "An adult female speaks as a pan sizzles" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y1Og2TJ3bXW0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1Og2TJ3bXW0.npy", "labels": "/m/07yv9,/m/0cmf2,/m/0k5j,/t/dd00128", "caption": "The whir of an aircraft engine" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YlVr-PxhZo8s.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YlVr-PxhZo8s.npy", "labels": "/m/07pb8fc,/m/07yv9,/t/dd00126", "caption": "A loud engine idling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/YdJYO3RbBabE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YdJYO3RbBabE.npy", "labels": "/m/02fs_r", "caption": "A digital beep followed by a man speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YBMayJId0X1s.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBMayJId0X1s.npy", "labels": "/m/0463cq4,/m/09x0r", "caption": "A man talking as a baby is crying" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YDjKGzOe_COc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YDjKGzOe_COc.npy", "labels": "/m/02qldy,/m/02zsn,/m/09x0r", "caption": "A young girl giving a speech" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YJHhEjsAkZoc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YJHhEjsAkZoc.npy", "labels": "/m/01g50p,/m/0284vy3,/m/06d_3,/m/07jdr,/m/07rwm0c", "caption": "Horns blowing of a passing train" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YAizmnCDlXos.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YAizmnCDlXos.npy", "labels": "/m/07qjznl,/m/07qjznt", "caption": "A bell chiming as a clock is ticking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YkVYNXZd0MMY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YkVYNXZd0MMY.npy", "labels": "/m/01jwx6,/m/02mk9,/m/07yv9,/m/0k4j", "caption": "Humming of an idling engine" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YKVbmN9ZRg5Q.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YKVbmN9ZRg5Q.npy", "labels": "/m/01g50p,/m/0284vy3,/m/06d_3,/m/07jdr,/m/07rwm0c", "caption": "A train horn gets louder as train approaches and passes by" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part19/YMSziND26UTA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YMSziND26UTA.npy", "labels": "/m/01h3n,/m/03vt0,/m/0h2mp", "caption": "Insects buzz faintly with distant chirps of birds and blowing wind" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YAFgGoY8Ihhg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YAFgGoY8Ihhg.npy", "labels": "/m/03j1ly,/m/03kmc9,/m/04qvtq", "caption": "Police sirens wailing as wind blows heavily into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YQv1HXaT-28U.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YQv1HXaT-28U.npy", "labels": "/m/07qsvvw", "caption": "A child giggling as something hits the ground and splatters" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YBn4lc01q9vE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBn4lc01q9vE.npy", "labels": "/m/0130jx,/m/02jz0l,/m/03dnzn,/m/0838f", "caption": "Water splashing with a woman speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YLVvS3s9dFKw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YLVvS3s9dFKw.npy", "labels": "/m/0130jx,/m/02jz0l,/m/0838f", "caption": "A man is talking as water is running and a surface is tapped" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/Yram-QPKSQYc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yram-QPKSQYc.npy", "labels": "/m/09ct_", "caption": "Helicopter flying away" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/Yy3-M1sonh3M.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yy3-M1sonh3M.npy", "labels": "/m/01jt3m", "caption": "Some rustling followed by a toilet flush" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/Yy_OyLW9lBXU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yy_OyLW9lBXU.npy", "labels": "/m/09x0r,/t/dd00002", "caption": "A lady laughing while a baby cries, then the lady speaks and a couple men also talk as well" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YRNBoH2LHQEM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YRNBoH2LHQEM.npy", "labels": "/m/028ght", "caption": "A crowd applauds" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YRrmBGjJqlEo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YRrmBGjJqlEo.npy", "labels": "/m/0316dw", "caption": "Clicks followed by a man speaking then typing on a keyboard" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YtIM-H2rdq8U.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YtIM-H2rdq8U.npy", "labels": "/m/032s66", "caption": "A gun firing several times followed by a revolver chamber spinning and metal clanking as a man talks and a person grunts" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part38/YvruDH_YLaPI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YvruDH_YLaPI.npy", "labels": "/m/032s66", "caption": "Several gunshots in quick succession" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/Ytpm5IOD5d4o.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ytpm5IOD5d4o.npy", "labels": "/m/01w250", "caption": "A woman talking before clapping followed by a bird whistling then a woman whistling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9z2OwpftxUE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9z2OwpftxUE.npy", "labels": "/m/0ngt1", "caption": "Thunder roaring in the distance as rain falls" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YZUmZgPL0ges.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YZUmZgPL0ges.npy", "labels": "/m/0395lw", "caption": "Multiple bells ringing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4pv3w--cRrA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4pv3w--cRrA.npy", "labels": "/m/09t49", "caption": "Crickets chirping during plastic scrapping and an electric device humming" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YAI1OweEW8C0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YAI1OweEW8C0.npy", "labels": "/m/06mb1,/m/07r10fb,/m/0jb2l,/m/0ngt1", "caption": "Light rain and water dripping followed by thunder" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YlfAFQ0-wDJU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YlfAFQ0-wDJU.npy", "labels": "/m/034srq,/m/03m9d0z", "caption": "Sounds of waves and strong winds" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part27/Y_w2pA1VeB40.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y_w2pA1VeB40.npy", "labels": "/m/01j3sz", "caption": "A group of people laughing followed by a person farting" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YPMMkPq5jJXY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YPMMkPq5jJXY.npy", "labels": "/m/03q5_w,/m/09x0r", "caption": "A person belching several times as a group of people laugh" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y7-HCqJFwHoI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y7-HCqJFwHoI.npy", "labels": "/m/01m2v,/m/0316dw", "caption": "A person types on a keyboard at varying speeds" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YbhlhcGONisM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YbhlhcGONisM.npy", "labels": "/m/0316dw,/m/09x0r", "caption": "A man speaking with a series of thumping and rubbing on cloth followed by plastic clicking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/Ye4ph6bIC5zc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ye4ph6bIC5zc.npy", "labels": "/m/012f08,/m/07yv9,/m/0k4j,/m/0ltv", "caption": "People are talking while a motor vehicle engine is revving" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/Yo7-X8DAToGc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yo7-X8DAToGc.npy", "labels": "/m/012f08,/m/07yv9,/m/0ltv,/t/dd00134", "caption": "An engine running" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YITlqMkR5alY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YITlqMkR5alY.npy", "labels": "/m/03fwl,/m/09x0r,/m/0ch8v,/m/0jbk", "caption": "A goat vocalizing softly and then screaming loudly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YcFoXRmGgIME.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YcFoXRmGgIME.npy", "labels": "/m/01g50p,/m/0284vy3,/m/04zmvq,/m/06d_3,/m/07jdr,/m/07yv9", "caption": "A train horn honking as a train is running on a railroad track and wind is blowing into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y7_smJ8VbfSU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y7_smJ8VbfSU.npy", "labels": "/m/02qldy,/m/02zsn,/m/09x0r", "caption": "A female speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4YodC6RnplI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4YodC6RnplI.npy", "labels": "/m/01d3sd", "caption": "An adult female laugh while snoring is occurring, and an adult male speaks in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part27/Y_YS5uKWoB6g.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y_YS5uKWoB6g.npy", "labels": "/m/09x0r,/t/dd00002", "caption": "A child crying and a car door closing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part15/YGOD8Bt5LfDE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YGOD8Bt5LfDE.npy", "labels": "/m/07jdr,/m/09x0r,/m/0ytgt", "caption": "A train chugging, a child speaking, and then a female speaking and laughter" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part19/YMVGhC-xB79s.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YMVGhC-xB79s.npy", "labels": "/m/015p6,/m/09x0r,/m/0h0rv,/t/dd00128", "caption": "A baby talking and a male speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YnmLMLgWPmFM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YnmLMLgWPmFM.npy", "labels": "/m/09x0r,/m/0j6m2", "caption": "An engine running with some birds near the end" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YFeHndzYAUkg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YFeHndzYAUkg.npy", "labels": "/m/01d380,/m/07k1x,/m/0_ksk", "caption": "A power tool drilling as rock music plays" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4eyY1w2QyM0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4eyY1w2QyM0.npy", "labels": "/m/0j6m2", "caption": "Water rushing and rippling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4_Cak7gvly4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4_Cak7gvly4.npy", "labels": "/m/07rqsjt", "caption": "Music playing and whooshing is happening" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4_DjmCg8Ra8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4_DjmCg8Ra8.npy", "labels": "/m/032s66,/m/0_1c", "caption": "Gunfire with shouting in background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YHg6HxylRGDo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YHg6HxylRGDo.npy", "labels": "/m/012n7d,/m/03j1ly,/m/03kmc9", "caption": "An emergency siren wailing as a motorcycle drives by" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YAUmY0YRAFQE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YAUmY0YRAFQE.npy", "labels": "/m/04qvtq,/m/07yv9,/m/0k4j,/t/dd00134", "caption": "A police car with siren blaring approaches and then recedes" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YbygBWUkpaC8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YbygBWUkpaC8.npy", "labels": "/m/020bb7,/m/07pggtn,/m/09x0r,/m/0jbk,/t/dd00129", "caption": "A man speaking with light wind followed by brief silence then birds chirping." }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YCwxgQS3SXic.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YCwxgQS3SXic.npy", "labels": "/m/0llzx", "caption": "Vibrations from a sewing machine" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part1/Y0UJtGcoPYa0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y0UJtGcoPYa0.npy", "labels": "/m/07jdr,/m/07yv9,/m/0912c9,/t/dd00128", "caption": "An generator motor buzzing followed by a train horn honking proceeded by a group of men groaning aloud" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part19/YMTaLknnq4wc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YMTaLknnq4wc.npy", "labels": "/m/01w250", "caption": "A woman whistles and sings" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part24/YVE6Ku0-ucUM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YVE6Ku0-ucUM.npy", "labels": "/m/07qsvvw,/m/09x0r", "caption": "A man talking followed by a popping burst then a man screaming proceeded by a crowd of people laughing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YTWOgvDaDqlU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YTWOgvDaDqlU.npy", "labels": "/m/083vt", "caption": "A power tool drilling followed by a large motor running as wood is being sawed" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YnU-AI3Cmc3M.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YnU-AI3Cmc3M.npy", "labels": "/m/015p6,/m/0h0rv,/t/dd00129", "caption": "Pigeons cooing followed by bird wings flapping as wind lightly blows into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YQ3vkJMVMbC8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YQ3vkJMVMbC8.npy", "labels": "/m/01jt3m", "caption": "A toilet flushes" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y77nElZGi5NU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y77nElZGi5NU.npy", "labels": "/m/07qsvvw,/m/09x0r", "caption": "A loud explosion is followed by laughter and several people cheering and speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y7_smJ8VbfSU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y7_smJ8VbfSU.npy", "labels": "/m/02qldy,/m/02zsn,/m/09x0r", "caption": "A woman speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YszkiW0GXEOI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YszkiW0GXEOI.npy", "labels": "/m/015p6,/m/01w250", "caption": "A person whistling while birds chirp" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part15/YGIOApFAWDOc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YGIOApFAWDOc.npy", "labels": "/m/015p6,/m/020bb7,/m/07pggtn", "caption": "Birds chirping and rustling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YB3O476LeuXY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YB3O476LeuXY.npy", "labels": "/m/07pb8fc,/t/dd00130", "caption": "An idle motorbike engine running" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/YoZaEHkfh5Eg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YoZaEHkfh5Eg.npy", "labels": "/m/07yv9,/m/0912c9,/m/0k4j", "caption": "Digital beeping with a horn honking twice" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part1/Y0Rpjl1AO-P0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y0Rpjl1AO-P0.npy", "labels": "/m/07yv9,/m/0k4j,/t/dd00134", "caption": "A vehicle driving then accelerating alongside a series of plastic clicks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YkagkXkAVPNo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YkagkXkAVPNo.npy", "labels": "/m/07yv9,/m/0912c9,/m/09x0r,/m/0k4j", "caption": "Group of cars are honking their horns and some people are murmuring at the end" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YsqsI2UyrcBQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YsqsI2UyrcBQ.npy", "labels": "/m/07q2z82,/m/07yv9,/m/0k4j", "caption": "A vehicle engine revving several times" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YFf8bCCJfVX4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YFf8bCCJfVX4.npy", "labels": "/m/032s66", "caption": "Compressed air releasing and metal repeatedly clacking followed by plastic rattling and a young boy talking and then footsteps on grass" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YPWjEfOkb6ro.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YPWjEfOkb6ro.npy", "labels": "/m/07swgks,/m/09x0r", "caption": "Water trickling and pouring as a man speaks in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YIsUG5SKWNZA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YIsUG5SKWNZA.npy", "labels": "/m/09x0r,/t/dd00002", "caption": "A woman whispering then talking normally after an infant cries followed by a man shouting" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/Yg5l3Bz6lWnc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yg5l3Bz6lWnc.npy", "labels": "/m/01h3n,/m/03vt0", "caption": "Wood lightly shuffling as insects buzz and birds chirp in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YrN2rpLV3brs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YrN2rpLV3brs.npy", "labels": "/m/04brg2", "caption": "A man speaking while beating eggs" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part4/Y35b9BSmN5JM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y35b9BSmN5JM.npy", "labels": "/m/07q2z82,/m/07yv9,/m/0k4j", "caption": "An engine running" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YsJrFyjfrL-g.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YsJrFyjfrL-g.npy", "labels": "/m/0llzx", "caption": "Metal clicking and clacking as a sewing machine slowly operates" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9b6RqajfAmw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9b6RqajfAmw.npy", "labels": "/m/015p6,/m/0h0rv,/t/dd00129", "caption": "Birds chirping together with rustling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YPO8Nu3F8mkA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YPO8Nu3F8mkA.npy", "labels": "/m/014zdl,/m/07qsvvw", "caption": "A distant explosion followed by steam hissing and fire igniting then a person speaking in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/YyLu4b01t53k.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YyLu4b01t53k.npy", "labels": "/m/012f08,/m/07pb8fc,/m/07yv9", "caption": "A mid-size motor vehicle engine is idling and vibrating" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/Ygbi6MxPf3hA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ygbi6MxPf3hA.npy", "labels": "/m/034srq,/m/03m9d0z,/m/05kq4,/t/dd00092", "caption": "Winds and ocean waves crashing while a chime instrument briefly plays a melody" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YqF72bT878gw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YqF72bT878gw.npy", "labels": "/m/019jd,/m/02rlv9,/m/07yv9", "caption": "Boat motor buzzes while operating at high throttle" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YHeEa1GZpUGI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YHeEa1GZpUGI.npy", "labels": "/m/032s66", "caption": "Continuous gunfire and shells hitting the ground" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YXZTt1xdK8uQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YXZTt1xdK8uQ.npy", "labels": "/m/07swgks", "caption": "An engine chugging away with some splashes of water" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/Ym_NCf-q4Gn0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ym_NCf-q4Gn0.npy", "labels": "/m/04_sv,/m/07qnq_y,/m/07yv9,/t/dd00128", "caption": "An idle motorcycle engine running with plastic clacking twice" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YkagkXkAVPNo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YkaYPLHXgkXkAVPNo.npy", "labels": "/m/07yv9,/m/0912c9,/m/09x0r,/m/0k4j", "caption": "A truck engine running and revving as several vehicle horns honk while a group of people talk in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/Ypaf0nyjg1Js.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ypaf0nyjg1Js.npy", "labels": "/m/0dxrf", "caption": "A woman is speaking with sizzling background noise" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YCwxgQS3SXic.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YCwxgQS3SXic.npy", "labels": "/m/0llzx", "caption": "Clicking and vibrations from a sewing machine" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YDn3buZWMzwY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YDn3buZWMzwY.npy", "labels": "/m/01d3sd,/m/09x0r", "caption": "Someone snores and others speak and laugh" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/YeRU-rABp8nk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YeRU-rABp8nk.npy", "labels": "/m/04_sv,/m/07yv9,/m/09x0r", "caption": "Men are communicating as a motorcycle engine idles" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YZ3wDry8nnJs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YZ3wDry8nnJs.npy", "labels": "/m/09x0r,/m/0ytgt,/t/dd00125", "caption": "A child speaks followed by scrubbing and spitting" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YUCy1BEx8jBE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YUCy1BEx8jBE.npy", "labels": "/m/0j6m2", "caption": "Humming and rustling with a man speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YXIooZl1QdM4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YXIooZl1QdM4.npy", "labels": "/m/03q5_w", "caption": "A man burping then inhaling followed by another burp while wheezing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y2EsxcKe1A4w.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y2EsxcKe1A4w.npy", "labels": "/m/068hy,/m/07rc7d9,/m/09x0r,/m/0bt9lr,/m/0jbk", "caption": "A dog barking while wind blows into a microphone followed by a man speaking in the distance proceeded by a bicycle pedaling alongside leaves rustling and a camera muffling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/Yz1ax0QPpd14.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yz1ax0QPpd14.npy", "labels": "/m/015p6,/m/09ddx", "caption": "Bird cheeping is ongoing, intermittent soft clucking and trilling is present, and a crow caws once" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YDNtF_mGzQes.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YDNtF_mGzQes.npy", "labels": "/m/07r04,/m/07yv9,/m/09x0r", "caption": "A vehicle engine running and children speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YQRtuOWWya30.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YQRtuOWWya30.npy", "labels": "/m/0dxrf", "caption": "Food and oil sizzling followed by metal rattling as a man is talking while guitar music plays and water trickles in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YUAmDLPjNyMg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YUAmDLPjNyMg.npy", "labels": "/m/07yv9,/m/0cmf2,/m/0k5j", "caption": "An aircraft running as wind blows into a microphone as a person sniffles" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part4/Y2RjqBRzmxaM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y2RjqBRzmxaM.npy", "labels": "/m/06mb1,/m/07r10fb,/t/dd00038", "caption": "A female speech, music and rainfall" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y7XUt6sQS7nM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y7XUt6sQS7nM.npy", "labels": "/m/07bgp,/m/07q0h5t,/m/09x0r", "caption": "Sheep baaing as wind is blowing into a microphone while a crowd of people talk in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y5I8lmN8rwDM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y5I8lmN8rwDM.npy", "labels": "/m/01d380,/m/07k1x,/t/dd00125", "caption": "A machine motor buzzing and humming" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/Ym_U506sf9p4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ym_U506sf9p4.npy", "labels": "/m/07p9k1k,/m/07ptfmf,/m/0dxrf", "caption": "A woman is speaking as food is sizzling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YKnsKf9KoNds.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YKnsKf9KoNds.npy", "labels": "/m/07cx4,/m/09x0r", "caption": "A man speaks nearby and another speaks over the phone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9dLLsZVRSZI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9dLLsZVRSZI.npy", "labels": "/m/07r04,/m/07yv9,/t/dd00129", "caption": "A truck engine running followed by a truck horn honking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YPg2cWEnEEvc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YPg2cWEnEEvc.npy", "labels": "/m/03q5_w", "caption": "A series of burping and farting" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/YeXj9OAik5cc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YeXj9OAik5cc.npy", "labels": "/m/04_sv,/m/07yv9,/t/dd00128", "caption": "An idle motorbike engine running while birds chirp in the background and wind blows into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YIFRmbxWK8u0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YIFRmbxWK8u0.npy", "labels": "/m/07qjznl", "caption": "A clock ticking and gears cranking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YBlbGXalLNVU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBlbGXalLNVU.npy", "labels": "/m/07pqc89", "caption": "Water moving with male voices soft in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part4/Y2msevPMQB4M.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y2msevPMQB4M.npy", "labels": "/m/01d380,/m/07k1x", "caption": "A machine is drilling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/YeUecAF626A8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YeUecAF626A8.npy", "labels": "/m/07yv9,/m/09x0r,/m/0k4j,/m/0ltv", "caption": "Cars humming and rumbling as they rev and idle" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y1j5NMuq1X30.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1j5NMuq1X30.npy", "labels": "/m/07qlf79", "caption": "Music plays in the background as a machine motor hums and liquid is being sprayed" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YCMUuelJFJ7Q.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YCMUuelJFJ7Q.npy", "labels": "/m/07qjznl,/m/07qjznt", "caption": "A bell ringing followed by a clock ticking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/Yp_BB_rJaF7Q.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yp_BB_rJaF7Q.npy", "labels": "/m/09ld4", "caption": "A man talking while birds chirp in the background followed by a frog squeaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YWLzzpzOKtnY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YWLzzpzOKtnY.npy", "labels": "/m/01h3n,/m/09x0r", "caption": "Two men communicating with each other as an insect buzzes by while wind blows into a microphone and birds chirp in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y0fMXnvD38zI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y0fMXnvD38zI.npy", "labels": "/m/019jd,/m/034srq,/m/03m9d0z,/m/05kq4,/t/dd00092", "caption": "Water flows and wind flows with seagulls in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/YgwQMkQmBITE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YgwQMkQmBITE.npy", "labels": "/m/083vt,/m/09x0r,/t/dd00125", "caption": "Wood thumping and rubbing as a man is talking followed by footsteps on a wooden surface" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/YgQMTOKsCIyk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YgQMTOKsCIyk.npy", "labels": "/m/015p6,/m/07qwf61,/m/09ddx,/m/09x0r", "caption": "Ducks quacking and man speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YJTHMXLC9YRs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YJTHMXLC9YRs.npy", "labels": "/m/09ddx,/m/0jbk", "caption": "Faint quacking of a duck with some light clicks and rustling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/YpaetCbEqp2w.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YpaetCbEqp2w.npy", "labels": "/m/0463cq4", "caption": "Some light tapping on a computer keyboard and a baby crying" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part19/YMjSegUnQXr4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YMjSegUnQXr4.npy", "labels": "/m/015p6,/m/0h0rv,/t/dd00125", "caption": "Rattling is followed by pigeon wing flapping and vocalization" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YE9zN3-C64KE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YE9zN3-C64KE.npy", "labels": "/m/09x0r,/t/dd00018", "caption": "Scratching noises accompanied by a female voice" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/YyLu4b01t53k.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YyLu4b01t53k.npy", "labels": "/m/012f08,/m/07pb8fc,/m/07yv9", "caption": "Humming of an idling engine" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YqPYwp1K4sZE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YqPYwp1K4sZE.npy", "labels": "/m/09x0r,/t/dd00112,/t/dd00125", "caption": "Clicking and crinkling with people speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/Yk4XyfaWVLEY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yk4XyfaWVLEY.npy", "labels": "/m/01bjv,/m/07yv9,/m/09x0r", "caption": "A vehicle engine is idling along with low crinkling noises and birds are chirping from a distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/YjXkLS_QzUrI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YjXkLS_QzUrI.npy", "labels": "/m/068hy,/m/07qrkrw", "caption": "Mechanical humming followed by meowing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4UPOUGVMlEs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4UPOUGVMlEs.npy", "labels": "/t/dd00018", "caption": "A pig snorting as dogs are growling and breathing heavily while grass and leaves rustle" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YAf4a-9rcnP0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YAf4a-9rcnP0.npy", "labels": "/m/07qsvvw", "caption": "Loud pops followed by rustling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YrvtA7c1I4xo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YrvtA7c1I4xo.npy", "labels": "/m/07rqsjt", "caption": "A whoosh and some humming followed by feet squeaking and men speaking in the distance with a man speaking nearby" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/YptIksg9KEac.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YptIksg9KEac.npy", "labels": "/m/068hy,/m/07rc7d9,/m/0bt9lr,/m/0jbk,/t/dd00136", "caption": "A dog barks quickly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9b6RqajfAmw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9b6RqajfAmw.npy", "labels": "/m/015p6,/m/0h0rv,/t/dd00129", "caption": "Many pigeons cooing and flapping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4_DjmCg8Ra8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4_DjmCg8Ra8.npy", "labels": "/m/032s66,/m/0_1c", "caption": "Loud bursts and pops with men speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YErxgH5g3Kx0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YErxgH5g3Kx0.npy", "labels": "/m/03k3r,/m/07rv9rh,/m/0jbk", "caption": "Clip clops of a horse with buzzing and a neigh" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/YpHNMcX-9FDs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YpHNMcX-9FDs.npy", "labels": "/m/068hy,/m/0bt9lr,/m/0jbk,/t/dd00136", "caption": "Dogs whimpering then a bark and a growl" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YAgh2EKINlSw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YAgh2EKINlSw.npy", "labels": "/m/06mb1,/t/dd00038", "caption": "A man talking followed by a vehicle accelerating then two men talking as rain falls on a surface" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/YxYwpABpZed4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YxYwpABpZed4.npy", "labels": "/m/07ptfmf,/m/0dxrf", "caption": "A woman is speaking while food being fried is sizzling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YbX2vDaHL26U.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YbX2vDaHL26U.npy", "labels": "/m/07rknqz,/m/07yv9,/m/0k4j,/m/0ltv", "caption": "A race car is racing and skidding" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/Yn4VktYihtJU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yn4VktYihtJU.npy", "labels": "/m/07swgks,/m/09x0r", "caption": "Heavy wind followed by yelling and cheering" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/Yc3nlaAkv9bA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yc3nlaAkv9bA.npy", "labels": "/m/03fwl,/m/068hy,/m/09x0r,/m/0ch8v,/m/0jbk", "caption": "A man talking followed by goats baaing then a cow mooing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YJhGp7HmRQxg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YJhGp7HmRQxg.npy", "labels": "/m/03k3r,/m/07q5rw0,/m/09x0r,/m/0jbk", "caption": "A metal clack followed by a horse neighing as gusts of wind blow and birds chirp in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9_YfTz8cnFY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9_YfTz8cnFY.npy", "labels": "/m/06hck5,/m/06wzb,/m/07rjwbb", "caption": "Steam hissing followed by a train whistle blowing and a group of people talking in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/Yhzn_wGlzGpU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yhzn_wGlzGpU.npy", "labels": "/m/07yv9,/m/0k4j,/m/0ltv", "caption": "Race car engine slows while whining" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/YwOFBldBFRNk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YwOFBldBFRNk.npy", "labels": "/m/0395lw", "caption": "Church bells tolling as wind blows into a microphone and rain falls on a surface" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part7/Y63KW_EQ72yU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y63KW_EQ72yU.npy", "labels": "/m/014zdl,/m/07qsvvw", "caption": "Loud banging followed by one louder bang with some static" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YY3lNEe-ZGF0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YY3lNEe-ZGF0.npy", "labels": "/m/07qjznl,/m/07qjznt", "caption": "Repeated ticking culminates in a sliding click" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/YpTJKJxaheI8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YpTJKJxaheI8.npy", "labels": "/m/07qjznl,/m/07qjznt", "caption": "Ticking of a clock" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YQ0anPAIkfBE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YQ0anPAIkfBE.npy", "labels": "/m/0463cq4,/m/09x0r,/t/dd00002,/t/dd00125", "caption": "A baby cries followed by a woman speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YQOmV7O9mFwg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YQOmV7O9mFwg.npy", "labels": "/m/01bjv,/m/07yv9,/m/09x0r", "caption": "People laugh on a bus while brakes squeal" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/Yi2yhbckq3p0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yi2yhbckq3p0.npy", "labels": "/m/012f08,/m/04_sv,/m/07yv9,/m/0k4j", "caption": "A motorbike engine running as multiple car horns honk and a car alarm rings in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YnlC4UI4hZ60.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YnlC4UI4hZ60.npy", "labels": "/m/012f08,/m/02mk9,/m/07yv9,/m/0k4j", "caption": "A vehicle motor stuttering before starting as metal rapidly rattles" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/Yazh_-OkQ-uI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yazh_-OkQ-uI.npy", "labels": "/m/07bgp,/m/07q0h5t,/m/09x0r", "caption": "Female talking follow by the bleating of a sheep" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part24/YVkbp8VmL3pM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YVkbp8VmL3pM.npy", "labels": "/m/0463cq4", "caption": "An infant crying as clothes rustle" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part4/Y2ymiXjImwGs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y2ymiXjImwGs.npy", "labels": "/m/012ndj,/m/01bjv,/m/09x0r", "caption": "Emergency vehicle driving with siren on" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/Yf8WPf5F22xI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yf8WPf5F22xI.npy", "labels": "/m/01hsr_", "caption": "Sneezing followed by a ticking clock and a man speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/Yhzn_wGlzGpU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yhzn_wGlzGpU.npy", "labels": "/m/07yv9,/m/0k4j,/m/0ltv", "caption": "A vehicle driving as gusts of wind blows and an emergency sirens sounds in the distance followed by fiberglass clanking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YSE_3nszEw7o.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YSE_3nszEw7o.npy", "labels": "/m/06wzb,/m/07rjwbb", "caption": "A steam engine running on railroad tracks as steam releases and hissing while a man talks in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YXz56Q2Q5j5c.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YXz56Q2Q5j5c.npy", "labels": "/m/07k1x,/m/083vt", "caption": "A motor humming as wood is being scrapped and sanded" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YBMayJId0X1s.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBMayJId0X1s.npy", "labels": "/m/0463cq4,/m/09x0r", "caption": "A baby cries while an adult male speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/Yhrv6fwnmBkY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yhrv6fwnmBkY.npy", "labels": "/m/068hy,/m/07rc7d9,/m/09b5t,/m/09x0r,/m/0bt9lr,/m/0jbk,/t/dd00136", "caption": "A dog whimpering followed by laughing and barking." }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YTSnq6n8tElo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YTSnq6n8tElo.npy", "labels": "/m/0242l,/m/04brg2", "caption": "Metal clinks five times, a coin drops, knocking on glass occurs, a coin drops again, and a small child speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YI4HpYGMMsz4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YI4HpYGMMsz4.npy", "labels": "/m/083vt,/m/09x0r", "caption": "A man speaking with slapping on a wooden surface as compressed air hisses in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YI4HpYGMMsz4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YI4HpYGMMsz4.npy", "labels": "/m/083vt,/m/09x0r", "caption": "Hissing is ongoing while an adult male speaks, and two thumps occur" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YBoe3MeEpn_c.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBoe3MeEpn_c.npy", "labels": "/m/04brg2,/m/09x0r,/t/dd00125", "caption": "A woman is speaking as dishes tap a surface followed by a spray hissing sound" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YmJ6ZO3xEcgw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YmJ6ZO3xEcgw.npy", "labels": "/m/01hsr_", "caption": "A woman coughing and sneezing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YDjKGzOe_COc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YDjKGzOe_COc.npy", "labels": "/m/02qldy,/m/02zsn,/m/09x0r", "caption": "A young girl speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9ucb5HYO8ps.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9ucb5HYO8ps.npy", "labels": "/m/03q5_w,/m/09x0r", "caption": "A burp followed by laughter and speech" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/YiOCpICiu4LA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YiOCpICiu4LA.npy", "labels": "/m/01h3n,/m/03l9g,/m/03vt0,/m/0h2mp", "caption": "Insects buzzing and birds chirping as a man talks followed by a loud plastic popping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/Yii3Geza3hAU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yii3Geza3hAU.npy", "labels": "/m/0llzx", "caption": "Sewing machine running then slowing to a stop followed by starting again" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YEbpOXac13yo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YEbpOXac13yo.npy", "labels": "/m/01bjv,/m/07yv9,/m/09x0r", "caption": "A vehicle engine and speech" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YEcihYbSlyck.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YEcihYbSlyck.npy", "labels": "/m/01bjv,/m/07yv9,/m/09x0r", "caption": "Horns honking repeatedly and a beeping sound" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YmlnUJH4BQnk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YmlnUJH4BQnk.npy", "labels": "/m/07pdjhy", "caption": "Female speech and rubbing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part15/YFi4-IqJo2xQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YFi4-IqJo2xQ.npy", "labels": "/m/02mk9,/m/07rqsjt,/m/07yv9,/m/0k4j", "caption": "An engine revving" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/Ye2rScj9UyMs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ye2rScj9UyMs.npy", "labels": "/m/015p6,/m/0h0rv,/t/dd00125", "caption": "Light footsteps and doves cooing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YCefFMA3klxk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YCefFMA3klxk.npy", "labels": "/m/012f08,/m/07r04,/m/07yv9,/m/0912c9", "caption": "A horn and then an engine revving" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part1/Y0_K6OKtoBBU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y0_K6OKtoBBU.npy", "labels": "/m/01yrx,/m/068hy,/m/07qrkrw,/m/0jbk", "caption": "A cat meows and a door creaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part7/Y5eSRL3PRHzo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y5eSRL3PRHzo.npy", "labels": "/m/028ght,/m/03qtwd", "caption": "Loud, continuous applause" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/Yt1hj7se76wQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yt1hj7se76wQ.npy", "labels": "/m/0316dw,/m/07qn4z3,/m/0c2wf", "caption": "Rapid typing and then a bell ringing one time" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/Ym_NCf-q4Gn0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ym_NCf-q4Gn0.npy", "labels": "/m/04_sv,/m/07qnq_y,/m/07yv9,/t/dd00128", "caption": "A vehicle is making a thudding noise" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y1e98HeU9Vrg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1e98HeU9Vrg.npy", "labels": "/m/034srq,/m/03m9d0z,/m/05kq4", "caption": "Waves crash on a beach while the wind blows" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part27/Y_BSmz3SEW1w.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y_BSmz3SEW1w.npy", "labels": "/m/015p6,/m/0h0rv,/t/dd00125,/t/dd00129", "caption": "A group of pigeons cooing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YkEP-BwMarf8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YkEP-BwMarf8.npy", "labels": "/m/09x0r,/t/dd00112", "caption": "A woman speaks quietly during a louder, sharp crinkling sound" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YAUmY0YRAFQE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YAUmY0YRAFQE.npy", "labels": "/m/04qvtq,/m/07yv9,/m/0k4j,/t/dd00134", "caption": "Sirens blaring passes by and then diminishes in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YLs1zyPjs3k8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YLs1zyPjs3k8.npy", "labels": "/m/02fs_r", "caption": "Digital humming and buzzing followed by scratching" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/Yyau2WIRkxb8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yyau2WIRkxb8.npy", "labels": "/m/09ct_", "caption": "A helicopter is in motion" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y77nElZGi5NU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y77nElZGi5NU.npy", "labels": "/m/07qsvvw,/m/09x0r", "caption": "People start cheering and hollering once a gun shot is fired" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YKnsKf9KoNds.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YKnsKf9KoNds.npy", "labels": "/m/07cx4,/m/09x0r", "caption": "A man speaking on the phone to another person" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part0/Y-SkjbQVgJ0M.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y-SkjbQVgJ0M.npy", "labels": "/m/07yv9,/m/09x0r,/m/0k4j,/t/dd00134", "caption": "A man talking as a vehicle drives by as rain patters on a hard surface" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y2JV3emH50XU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y2JV3emH50XU.npy", "labels": "/m/07yv9,/m/0k4j,/m/0ltv", "caption": "A mid-size motor vehicle engine is running and accelerating, tires squeal, and hissing occurs" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part9/Y7cHRSfbp7tc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y7cHRSfbp7tc.npy", "labels": "/m/02dgv,/m/07r4wb8,/m/09x0r", "caption": "People talk and rustle then knocking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part38/Yv59uHr-B1no.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yv59uHr-B1no.npy", "labels": "/m/09ld4", "caption": "Frogs croak near and far with chirping distant bugs" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/Ybgbnu5YKTDg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ybgbnu5YKTDg.npy", "labels": "/m/032s66", "caption": "A man speaking through an intercom while a helicopter is flying before and after a series of gunshots firing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/YwOFBldBFRNk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YwOFBldBFRNk.npy", "labels": "/m/0395lw", "caption": "Large metal bells are clanging in different tones, and each ring pattern is echoed once" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part9/Y83j4GgHXTLE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y83j4GgHXTLE.npy", "labels": "/m/01j3sz,/m/09x0r,/m/0ytgt,/t/dd00125", "caption": "Clanking together with childbearing hollering and speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part7/Y5ORpSk5CIWc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y5ORpSk5CIWc.npy", "labels": "/m/09ct_", "caption": "Humming of a small engine passing by" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YFfUqv0Vv3ME.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YFfUqv0Vv3ME.npy", "labels": "/m/03k3r,/m/09x0r,/m/0jbk", "caption": "Rustling and adult male speech and footsteps" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/YfPqj3nnwQOI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YfPqj3nnwQOI.npy", "labels": "/m/0j6m2", "caption": "Water flowing and splashing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/YzEM94PH29VQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YzEM94PH29VQ.npy", "labels": "/m/09x0r,/t/dd00002", "caption": "A young child cries as people speak" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part15/YGkb4f6yodPE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YGkb4f6yodPE.npy", "labels": "/m/01b82r,/m/07pdjhy,/m/083vt", "caption": "Hard planks click together and an electric saw cuts material" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YmaVYiednkSg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YmaVYiednkSg.npy", "labels": "/m/07qlf79,/m/09x0r", "caption": "An electronic motor rumbling followed by a man talking and pressurized air spraying then a louder electronic motor rumbling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/YfmEft49sPfE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YfmEft49sPfE.npy", "labels": "/m/05zppz,/m/09t49,/m/09x0r", "caption": "A man speaking as wind blows through foliage and on a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YYNDKuNINDOY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YYNDKuNINDOY.npy", "labels": "/m/012ndj,/m/03j1ly,/m/03kmc9", "caption": "A fire truck engine runs and the siren is blowing but stops, traffic is present, the fire truck horn honks twice, and the siren begins again" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YYQSuFyFm3Lc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YYQSuFyFm3Lc.npy", "labels": "/m/01g50p,/m/0284vy3,/m/06d_3,/m/07jdr", "caption": "Clattering of a train is ongoing, a railroad crossing bell rings, and a train horn blows" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/YfBYDJWChe5c.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YfBYDJWChe5c.npy", "labels": "/m/01d3sd", "caption": "A person snoring" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YBUAPM4D3-h8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBUAPM4D3-h8.npy", "labels": "/m/015p6,/m/020bb7,/m/07pggtn", "caption": "A woman and child speak while birds call" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part7/Y6Nvu6EcpdE8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y6Nvu6EcpdE8.npy", "labels": "/m/07pb8fc,/m/07yv9,/m/09x0r,/t/dd00130", "caption": "A main is smoothly speaking over a loud faint noise" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YaZAXO2WZn84.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YaZAXO2WZn84.npy", "labels": "/m/06wzb,/m/07rjwbb", "caption": "A train engine running as bells chime followed by a lawn mower running then a steam engine running while a steam whistle blows and a crowd of people talk in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y1e98HeU9Vrg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1e98HeU9Vrg.npy", "labels": "/m/034srq,/m/03m9d0z,/m/05kq4", "caption": "Ocean waves are repeatedly splashing on shore, and a gentle wind is blowing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/Yific_gRalg0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yific_gRalg0.npy", "labels": "/m/07swgks", "caption": "Metal clacking sharply several times as water drains down a pipe followed by metal rattling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YHkbCUN4V3TU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YHkbCUN4V3TU.npy", "labels": "/m/09x0r,/m/0ytgt,/t/dd00125", "caption": "A child screaming and laughing as a woman talks and giggles followed by thumping on a wooden surface" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YDAN1t9ukkg0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YDAN1t9ukkg0.npy", "labels": "/m/01m2v,/m/0316dw", "caption": "Computer keyboard clicks as typing occurs" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part0/Y-JP1GqPEKtw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y-JP1GqPEKtw.npy", "labels": "/m/07k1x,/m/083vt,/m/09x0r", "caption": "A man talking as a power tool motor runs followed by the buzzing of an electric sanding machine" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3n05BjV7r7M.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3n05BjV7r7M.npy", "labels": "/m/02dgv,/m/02y_763", "caption": "Metallic clanging occurs as door slides" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/YhJtOGmN_KVw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YhJtOGmN_KVw.npy", "labels": "/m/09x0r,/t/dd00112,/t/dd00125", "caption": "Plastic crumpling and crinkling are ongoing, and an adult male speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y27HIamF8pKo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y27HIamF8pKo.npy", "labels": "/m/01g50p,/m/0284vy3,/m/06d_3,/m/07jdr,/m/07rwm0c", "caption": "A train engine is operating, rhythmic vibrating, clacking and clattering are ongoing, and a train whistle blows three times" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part38/YuY4fe5DT1gI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YuY4fe5DT1gI.npy", "labels": "/m/01m2v,/m/0316dw", "caption": "Typing on a computer keyboard" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part1/Y-oy0BkpMGAk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y-oy0BkpMGAk.npy", "labels": "/m/012f08,/m/07rknqz,/m/07yv9,/m/0k4j,/t/dd00134", "caption": "A vehicle driving and revving several times as tires skid and wind blows into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/Ygbi6MxPf3hA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ygbi6MxPf3hA.npy", "labels": "/m/034srq,/m/03m9d0z,/m/05kq4,/t/dd00092", "caption": "Music plays briefly and wind blows and birds sing in background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YSNIaYhri76w.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YSNIaYhri76w.npy", "labels": "/m/05tny_,/m/07rc7d9,/m/09x0r,/m/0bt9lr,/m/0ghcn6,/m/0jbk,/t/dd00129", "caption": "Oinking pig and barking dog followed by man speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/YxYwpABpZed4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YxYwpABpZed4.npy", "labels": "/m/07ptfmf,/m/0dxrf", "caption": "An adult female speaks in the foreground, while sizzling is ongoing and metal thumps occur" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YLVvS3s9dFKw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YLVvS3s9dFKw.npy", "labels": "/m/0130jx,/m/02jz0l,/m/0838f", "caption": "A man talking as metal pots clang while water pours from a faucet followed by water trickling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4UPOUGVMlEs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4UPOUGVMlEs.npy", "labels": "/t/dd00018", "caption": "Snorting and breathing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/YeNG6fEiAE8c.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YeNG6fEiAE8c.npy", "labels": "/m/07bgp,/m/07q0h5t,/m/09x0r", "caption": "Laughing and speech with a sheep bleat" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part27/Y_9mgOkzm-xg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y_9mgOkzm-xg.npy", "labels": "/m/09x0r,/m/0dxrf,/t/dd00125", "caption": "A man is talking, and food is frying" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part27/Y_BSmz3SEW1w.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y_BSmz3SEW1w.npy", "labels": "/m/015p6,/m/0h0rv,/t/dd00125,/t/dd00129", "caption": "Pigeons are making grunting sounds and snapping beaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YFfUqv0Vv3ME.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YFfUqv0Vv3ME.npy", "labels": "/m/03k3r,/m/09x0r,/m/0jbk", "caption": "Male speech and footsteps" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/Ykx6Rj4MDIAw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ykx6Rj4MDIAw.npy", "labels": "/m/07rjwbb", "caption": "Railroad rail clicky-clack, metallic vibration, and steam hissing occur" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part7/Y5ORpSk5CIWc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y5ORpSk5CIWc.npy", "labels": "/m/09ct_", "caption": "A drone flying near and far" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/YfsBR7e_X_0Y.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YfsBR7e_X_0Y.npy", "labels": "/m/09x0r,/m/0ytgt,/t/dd00125", "caption": "A young boy talking as a baby is yelling with several slaps on a hard surface" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YOFVzrakJhbw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YOFVzrakJhbw.npy", "labels": "/m/068hy,/m/07bgp,/m/07q0h5t,/m/0jbk", "caption": "A woman speaks with distant goats bleating and wind blowing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YSQHYl2Kp5ww.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YSQHYl2Kp5ww.npy", "labels": "/m/07ptfmf,/m/0dxrf", "caption": "Music plays while two men speak each other with dishes clanking and food sizzling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YrUq4w4EUSWA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YrUq4w4EUSWA.npy", "labels": "/m/01jt3m,/m/0838f", "caption": "An electronic device buzzing followed by paper tearing and then crumpling as a bell rings before a toilet flushes" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/Yp9qRTh4BmSE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yp9qRTh4BmSE.npy", "labels": "/m/032s66,/m/04zjc", "caption": "A man talking as people yell in the distance followed by a man shouting loudly then a series of gunshots firing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part7/Y5xC4hkAWiao.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y5xC4hkAWiao.npy", "labels": "/m/012f08,/m/02mk9,/m/07yv9", "caption": "An engine running and then revving" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YbAqgL5dCQOE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YbAqgL5dCQOE.npy", "labels": "/m/06mb1,/m/07r10fb,/t/dd00038", "caption": "Rain pouring on a solid surface followed by a vehicle driving by in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3XuyGJqaXv8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3XuyGJqaXv8.npy", "labels": "/m/068hy,/m/07rc7d9,/m/09x0r,/m/0bt9lr,/m/0jbk", "caption": "A man speaking over an intercom as a crowd of people talk followed by a dog barking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YS_3aeOvniZc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YS_3aeOvniZc.npy", "labels": "/m/07yv9,/m/0k4j,/m/0ltv", "caption": "A car accelerates in order to drive, a screech occurs as the wheels spin before taking off" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YZNEZLlDVgrE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YZNEZLlDVgrE.npy", "labels": "/m/01h3n,/m/03vt0,/m/0h2mp", "caption": "Insects buzzing followed by a man talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/Yjlwe9jtu5Gw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yjlwe9jtu5Gw.npy", "labels": "/m/01w250", "caption": "A person whistling followed by metal rattling in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YQv1HXaT-28U.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YQv1HXaT-28U.npy", "labels": "/m/07qsvvw", "caption": "A pop and rattle occurs and then a child giggles" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part38/Yvigslb0kClE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yvigslb0kClE.npy", "labels": "/m/03fwl,/m/09x0r,/m/0jbk", "caption": "A goat vocalizing and male speech" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/YelztUCeNQvQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YelztUCeNQvQ.npy", "labels": "/m/0195fx,/m/01g50p,/m/0284vy3,/m/06d_3,/m/07jdr", "caption": "A train horn honking followed by a train running on railroad tracks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part0/Y-EQByFLFqig.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y-EQByFLFqig.npy", "labels": "/m/06mb1,/m/0ngt1,/t/dd00038", "caption": "Man speaking, rain, thunder" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YEcihYbSlyck.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YEcihYbSlyck.npy", "labels": "/m/01bjv,/m/07yv9,/m/09x0r", "caption": "Vibrations and rattling with distant hums and honks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YqZEIs6tS5vk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YqZEIs6tS5vk.npy", "labels": "/m/07r04,/m/07rknqz,/m/07yv9", "caption": "A truck engine revving followed by tires skidding as a crowd of people talk in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YAWGnTI0e2Fs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YAWGnTI0e2Fs.npy", "labels": "/m/09ct_", "caption": "A toy helicopter flying then powering down before powering up" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YJTHMXLC9YRs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YJTHMXLC9YRs.npy", "labels": "/m/09ddx,/m/0jbk", "caption": "A person heavily breathing as wood creaks and ducks quack" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/YgkWd1HugK2w.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YgkWd1HugK2w.npy", "labels": "/m/015p6,/m/0h0rv,/t/dd00129", "caption": "Pigeons coo and flap their wings" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YLs1zyPjs3k8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YLs1zyPjs3k8.npy", "labels": "/m/02fs_r", "caption": "A mechanical beeping tone followed by static, then the return of the beeping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YARFFw0e_jig.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YARFFw0e_jig.npy", "labels": "/m/03q5_w", "caption": "A series of distorted burps followed by non-distorted burps" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YljrL7Cb-jr8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YljrL7Cb-jr8.npy", "labels": "/m/07qlf79", "caption": "Humming and vibrating of engines" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YEp72tyiL3as.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YEp72tyiL3as.npy", "labels": "/m/0ngt1", "caption": "Thunder crashes followed by silence" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YBz9Y5nZK3eo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBz9Y5nZK3eo.npy", "labels": "/m/01m2v,/m/0316dw", "caption": "Fast and loud typing on computer keyboard" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part24/YVOXl8iR-HnI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YVOXl8iR-HnI.npy", "labels": "/m/014yck,/m/07yv9,/m/09x0r,/m/0cmf2,/m/0k5j", "caption": "Humming of a distant jet engine passing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/YoN0IcZaHD_8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YoN0IcZaHD_8.npy", "labels": "/m/01d380,/m/07k1x,/m/083vt,/m/09x0r,/t/dd00125", "caption": "A man briefly talks followed by a drilling sound on wood" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/YjYPU6aSDo88.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YjYPU6aSDo88.npy", "labels": "/m/014yck,/m/07yv9,/m/09x0r,/m/0k5j", "caption": "Wind blowing with the distant humming of a jet engine" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YZ0IrCa4MvOA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YZ0IrCa4MvOA.npy", "labels": "/m/0130jx,/m/02jz0l,/m/07pqc89,/m/0838f", "caption": "Water flowing through pipes" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YJmWaRt8-u0s.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YJmWaRt8-u0s.npy", "labels": "/m/04_sv,/m/07yv9,/m/09x0r,/t/dd00066", "caption": "An engine chugging with muffled speech" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part7/Y5QZ0NtdoKJ8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y5QZ0NtdoKJ8.npy", "labels": "/m/02fs_r,/m/07pp_mv,/m/09x0r", "caption": "A two-tone electronic alarm is ongoing, while an adult female is speaking in the foreground and birds are chirping in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part0/Y--0w1YA1Hm4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y--0w1YA1Hm4.npy", "labels": "/m/01bjv,/m/07yv9,/m/09x0r", "caption": "People talking with the dull roar of a vehicle on the road" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YE3D_z0aoUEg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YE3D_z0aoUEg.npy", "labels": "/m/07st88b,/m/09ld4", "caption": "Ambient horror music plays as birds chirp and frogs croak" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4bUL_ttiOdw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4bUL_ttiOdw.npy", "labels": "/t/dd00002", "caption": "A baby is crying" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YLKhokVsJhN0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YLKhokVsJhN0.npy", "labels": "/m/07bgp,/m/0ch8v,/m/0jbk", "caption": "A flock of sheep baaing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part9/Y8GHLfJ6y6zA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y8GHLfJ6y6zA.npy", "labels": "/m/01m2v,/m/0316dw,/m/09x0r", "caption": "A slide whistle followed by typing on a computer keyboard and a computer mouse clicking as a man is talking while woodwind music plays in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YAI1OweEW8C0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YAI1OweEW8C0.npy", "labels": "/m/06mb1,/m/07r10fb,/m/0jb2l,/m/0ngt1", "caption": "Rain is falling, splashing on a surface and gurgling, and thunder crashes" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part15/YH7rd9bZtbgc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YH7rd9bZtbgc.npy", "labels": "/m/0395lw", "caption": "Several church bells ringing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part15/YGuizRlAQ8qQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YGuizRlAQ8qQ.npy", "labels": "/m/01d380", "caption": "High pitched continuous drilling that slows down" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YXQxIXaX_7M0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YXQxIXaX_7M0.npy", "labels": "/m/09t49,/m/09x0r", "caption": "Water rushing loudly while a man yells in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y0yETgW44MZU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y0yETgW44MZU.npy", "labels": "/m/01g50p,/m/0284vy3,/m/04zmvq,/m/06d_3,/m/07jdr,/m/07yv9,/t/dd00129", "caption": "A loud, continuous horn followed by brief clanking and more horn honking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YWUyeFOyKIg0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YWUyeFOyKIg0.npy", "labels": "/m/07yv9,/m/09x0r,/m/0k4j,/m/0ltv,/t/dd00129", "caption": "A racing vehicle driving in the distance then driving by as a crowd of people talk in the background followed by a horn honking while wind blows into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/YxqtrbqDlz28.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YxqtrbqDlz28.npy", "labels": "/m/01hsr_", "caption": "A woman sneezes and then sniffles several times" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YUE3XnVFodMI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YUE3XnVFodMI.npy", "labels": "/m/028ght,/m/09x0r", "caption": "Applause with distant speech and cheering" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YRtenf2XSXRc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YRtenf2XSXRc.npy", "labels": "/m/07q2z82,/m/07yv9,/m/0k4j", "caption": "Low humming of an idling and accelerating engine" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/Yorgwzt45ojE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yorgwzt45ojE.npy", "labels": "/m/015p6,/m/09x0r,/m/0h0rv,/t/dd00126", "caption": "A man speaks while birds flap" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/Yhmd6pa2e_rs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yhmd6pa2e_rs.npy", "labels": "/m/01bjv,/m/07yv9,/m/09x0r", "caption": "A bus engine accelerating followed by a man talking then a woman speaking in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y40cuHrYfaqA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y40cuHrYfaqA.npy", "labels": "/m/068hy,/m/07rc7d9,/m/09x0r,/m/0bt9lr,/m/0jbk,/t/dd00136", "caption": "A dog barking and growling followed by a man talking in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YCM49C3RkzV8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YCM49C3RkzV8.npy", "labels": "/m/02qldy,/m/02zsn,/m/09x0r", "caption": "A woman is speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YLWng-4PDzPM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YLWng-4PDzPM.npy", "labels": "/m/01w250", "caption": "A rustling followed by a soulful whistling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YmVjub3o_IxE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YmVjub3o_IxE.npy", "labels": "/m/02jz0l,/m/09x0r,/t/dd00125", "caption": "A man talking as a kid talks in the distance while machine squeaks in the background." }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YS0SQyFXbqF8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YS0SQyFXbqF8.npy", "labels": "/m/09ld4", "caption": "Young child speaking with giggling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YndxkSQKxaak.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YndxkSQKxaak.npy", "labels": "/m/04_sv,/m/07yv9,/m/09x0r", "caption": "Engine sounds with a man speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9ucb5HYO8ps.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9ucb5HYO8ps.npy", "labels": "/m/03q5_w,/m/09x0r", "caption": "Burping and laughing from girls who then speak" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YArHiac57pVk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YArHiac57pVk.npy", "labels": "/m/07qjznl,/m/09x0r", "caption": "A male speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YTwR8BA6buMI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YTwR8BA6buMI.npy", "labels": "/m/07qjznl", "caption": "Two piano notes and percussion are repeating rhythmically to imitate a ticktock" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YmVjub3o_IxE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YmVjub3o_IxE.npy", "labels": "/m/02jz0l,/m/09x0r,/t/dd00125", "caption": "A man speaking followed by a woman talking in the distance as a faucet pours water and birds chirp in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YnLtNjMimLE0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YnLtNjMimLE0.npy", "labels": "/m/07pqc89,/m/0838f", "caption": "Water trickling several times" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part15/YH7-orYrKBeo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YH7-orYrKBeo.npy", "labels": "/m/01bjv,/m/0463cq4,/m/07yv9,/m/09x0r", "caption": "A child cries continually, while a motor vehicle engine runs quietly and several adult females and adult males speak" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YF7QtqKtllK0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YF7QtqKtllK0.npy", "labels": "/m/01d3sd", "caption": "Repeated snoring and then a gasp" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YDc2WEiRk0rA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YDc2WEiRk0rA.npy", "labels": "/m/07qlf79", "caption": "Continuous spray" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YXWw7ZM1c_QA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YXWw7ZM1c_QA.npy", "labels": "/m/07qjznl,/m/09x0r", "caption": "Rustling and soft speech and then a clock chimes" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9HVgYs8OOLc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9HVgYs8OOLc.npy", "labels": "/m/015p6,/m/09x0r,/m/0h0rv,/t/dd00125", "caption": "A man talking then a young boy talking followed by a loud pop as pigeons coo and bird wings flap" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4lv9aLXtud0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4lv9aLXtud0.npy", "labels": "/m/03q5_w,/m/09x0r,/t/dd00125", "caption": "A man shouting before and after a person belches" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YLbken4JCr94.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YLbken4JCr94.npy", "labels": "/m/06mb1,/m/0jb2l,/m/0ngt1", "caption": "Rain and thunder" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y6aWnK1GyeJY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y6aWnK1GyeJY.npy", "labels": "/m/0463cq4,/m/09x0r", "caption": "Crying and then a sneeze and speech" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part9/Y83j4GgHXTLE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y83j4GgHXTLE.npy", "labels": "/m/01j3sz,/m/09x0r,/m/0ytgt,/t/dd00125", "caption": "A man laughing followed by a child screaming then another child laughing before a kid talks proceeded by a man shushing and talking softly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part24/YUQtBt6CQpwg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YUQtBt6CQpwg.npy", "labels": "/m/09x0r,/m/0llzx", "caption": "A gurgling noise followed by a sewing machine sewing material" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YsI7_ycEYzAY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YsI7_ycEYzAY.npy", "labels": "/m/07qjznl,/m/07qjznt", "caption": "Humming noise with clock tick-tocking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YJBWJQCS4SvA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YJBWJQCS4SvA.npy", "labels": "/m/034srq,/m/03m9d0z,/m/05kq4,/t/dd00092", "caption": "Wind blows and birds chirp with ocean waves in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YQ3vkJMVMbC8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YQ3vkJMVMbC8.npy", "labels": "/m/01jt3m", "caption": "A toilet flushes followed by another toilet flushing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YL8dA-2Lu2hY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YL8dA-2Lu2hY.npy", "labels": "/m/01w250", "caption": "A person whistling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YEvZ3jOMYWxk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YEvZ3jOMYWxk.npy", "labels": "/m/02qldy,/m/02zsn,/m/09x0r", "caption": "A woman is performing a speech" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YEBCH7TPgiPc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YEBCH7TPgiPc.npy", "labels": "/m/07q2z82,/m/07yv9,/m/0k4j", "caption": "An engine revving" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part0/Y-R69Fa-mCaY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y-R69Fa-mCaY.npy", "labels": "/m/01j4z9,/m/083vt", "caption": "A chainsaw running and crackling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part4/Y2ymiXjImwGs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y2ymiXjImwGs.npy", "labels": "/m/012ndj,/m/01bjv,/m/09x0r", "caption": "A siren with people talking in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/Ylh801oHGtD4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ylh801oHGtD4.npy", "labels": "/m/01d380,/m/09x0r", "caption": "An electric motor buzzing as a man is talking followed by a door closing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YrINmxSXMR-s.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YrINmxSXMR-s.npy", "labels": "/m/07qdb04,/m/09ddx,/m/0jbk", "caption": "Water splashing followed by a duck quacking then a person laughing as water splashes" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YrjUrB1WUpcI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YrjUrB1WUpcI.npy", "labels": "/m/07swgks", "caption": "Water running and then stopping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part1/Y0AsXkZkqelg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y0AsXkZkqelg.npy", "labels": "/m/028ght", "caption": "An engine idles loudly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YXi6V0LGvqoo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YXi6V0LGvqoo.npy", "labels": "/m/01z5f,/m/068hy,/m/07rc7d9,/m/0bt9lr,/m/0jbk", "caption": "A dog whimpering followed by footsteps shuffling and tapping then a dog growling as a motor hums in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/YcN-oYKd-M4E.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YcN-oYKd-M4E.npy", "labels": "/m/07bgp,/m/0ch8v,/m/0jbk", "caption": "Two plastic clicks followed by sheep baaing as birds chirp in the distance and wind blows into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y0ury8KHQdL4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y0ury8KHQdL4.npy", "labels": "/m/01m2v,/m/0316dw,/m/09x0r", "caption": "Typing on a keyboard as a man is talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/YA61Mry8zBwE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YA61Mry8zBwE.npy", "labels": "/m/07rv9rh,/m/09x0r,/m/0jbk", "caption": "A crowd of people talking then applauding as a man speaks over an intercom" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y59VP93Tzjmg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y59VP93Tzjmg.npy", "labels": "/m/01g50p,/m/0284vy3,/m/06d_3,/m/07jdr", "caption": "A train blows its horn several times" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/YjjHIINDfE1c.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YjjHIINDfE1c.npy", "labels": "/m/07yv9,/m/0912c9,/t/dd00129", "caption": "Humming of a passing vehicle with a honking engine and wind blowing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/YhxbmDeNSO6Q.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YhxbmDeNSO6Q.npy", "labels": "/m/09x0r,/m/0llzx", "caption": "A sewing machine running then stopping as a man talks followed by a metal click then a soft electronic beep and another metal click" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4bUL_ttiOdw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4bUL_ttiOdw.npy", "labels": "/t/dd00002", "caption": "A baby cries continuously" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part15/YH-vTZh81qAU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YH-vTZh81qAU.npy", "labels": "/m/01jwx6", "caption": "Faint low vibrations and humming" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YrvDcg9DoNKA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YrvDcg9DoNKA.npy", "labels": "/m/0ngt1", "caption": "Thunder roaring in the distance as rain lightly pours and a man yells followed by another man humming" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YXi6V0LGvqoo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YXi6V0LGvqoo.npy", "labels": "/m/01z5f,/m/068hy,/m/07rc7d9,/m/0bt9lr,/m/0jbk", "caption": "A dog whimpering followed by a dog growling and barking as metal jingles and footsteps squeak on hard surface" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/YwFiCblfZ-vg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YwFiCblfZ-vg.npy", "labels": "/m/07pqc89,/m/09x0r", "caption": "A man speaking with intermittent second man voice and white noise." }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/Yt1hj7se76wQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yt1hj7se76wQ.npy", "labels": "/m/0316dw,/m/07qn4z3,/m/0c2wf", "caption": "Typing on a typewriter followed by a bell chiming" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part19/YMTIF_l_8d4Q.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YMTIF_l_8d4Q.npy", "labels": "/m/0463cq4,/m/09x0r", "caption": "An infant crying followed by a child speaking in the background then a young woman talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part15/YGPj8h-WcjWs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YGPj8h-WcjWs.npy", "labels": "/m/01bjv,/m/07yv9,/m/09x0r", "caption": "A muffled bus engine running as a woman speaks over an intercom" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YHxZADVzNIqs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YHxZADVzNIqs.npy", "labels": "/m/015p6,/m/020bb7,/m/07pggtn", "caption": "Water is trickling as birds chirp, and soft beats of a bass drum begin to occur" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YYQSuFyFm3Lc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YYQSuFyFm3Lc.npy", "labels": "/m/01g50p,/m/0284vy3,/m/06d_3,/m/07jdr", "caption": "Humming and rattling followed by distant warning bells and the horn of an oncoming train" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/Yjj2RyNDj7no.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yjj2RyNDj7no.npy", "labels": "/m/01h3n,/m/03vt0,/m/0h2mp", "caption": "Bees buzz and birds call followed by man speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/YgW7s3YAthpI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YgW7s3YAthpI.npy", "labels": "/m/02jz0l,/m/0838f", "caption": "Glass clanking followed by liquid shaking in a plastic container then liquid pouring and filling a container proceeded by plastic rattling as someone chews a loud" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y2JV3emH50XU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y2JV3emH50XU.npy", "labels": "/m/07yv9,/m/0k4j,/m/0ltv", "caption": "A vehicle passes by" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part4/Y31WGUPOYS5g.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y31WGUPOYS5g.npy", "labels": "/m/012ndj,/m/03j1ly,/m/03kmc9", "caption": "A child shouts, and adult male speaks, and an emergency vehicle siren sounds and the horn blows" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y1GgEpRZDWN0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1GgEpRZDWN0.npy", "labels": "/m/01h8n0,/m/02zsn,/m/09x0r", "caption": "Man and woman talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part1/Y0G7rb74R-2A.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y0G7rb74R-2A.npy", "labels": "/m/02qldy,/m/05zppz,/m/09x0r", "caption": "An adult male speaking through a microphone on a stage while an audience laughs at him" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YAUJPx81qKtY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YAUJPx81qKtY.npy", "labels": "/m/01h3n,/m/03vt0,/m/0h2mp", "caption": "A man talking as a swam of insects buzz" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/YpTJKJxaheI8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YpTJKJxaheI8.npy", "labels": "/m/07qjznl,/m/07qjznt", "caption": "White noise and slow tick locking with brief coughing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part24/YUQtBt6CQpwg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YUQtBt6CQpwg.npy", "labels": "/m/09x0r,/m/0llzx", "caption": "Short rapid vibrations of a sewing machine" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YZ0IrCa4MvOA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YZ0IrCa4MvOA.npy", "labels": "/m/0130jx,/m/02jz0l,/m/07pqc89,/m/0838f", "caption": "Water flows and splashes" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YqWYncqPSy9A.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YqWYncqPSy9A.npy", "labels": "/m/03vt0,/m/09f96,/m/0h2mp", "caption": "A woman talks followed by a buzzing bee right before a man and woman take turns talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YD9GHUPGWsV0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YD9GHUPGWsV0.npy", "labels": "/m/07bgp,/m/07q0h5t,/m/09x0r", "caption": "An adult female and adult male speak in the foreground, slight clattering is occurring, and an animal bleats in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y7MLERaOgK_Y.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y7MLERaOgK_Y.npy", "labels": "/m/0llzx", "caption": "A child singing with consistent clanking followed by silence then tapping and speech" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/Yjf4iyQPJSvk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yjf4iyQPJSvk.npy", "labels": "/m/07pqc89,/m/0838f,/m/0j2kx,/t/dd00129", "caption": "Water trickles down continuously" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/YoN0IcZaHD_8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YoN0IcZaHD_8.npy", "labels": "/m/01d380,/m/07k1x,/m/083vt,/m/09x0r,/t/dd00125", "caption": "A man speaks followed by a tools drilling wood" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YsCzRVvu9XeY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YsCzRVvu9XeY.npy", "labels": "/m/01w250", "caption": "An upbeat whistling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YNwoBDrTlbTI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YNwoBDrTlbTI.npy", "labels": "/t/dd00018", "caption": "An animal makes squeaking noises with buzzing background sounds, and a dog barks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part24/YVMsbrcHPBfk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YVMsbrcHPBfk.npy", "labels": "/m/03fwl", "caption": "A goat baaing normally before and after a goat screaming" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YTgxst7Ft9js.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YTgxst7Ft9js.npy", "labels": "/m/02p01q,/m/07pdjhy", "caption": "Sanding and scraping followed by a man speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y6ukYSXzfEgQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y6ukYSXzfEgQ.npy", "labels": "/m/02jz0l,/m/0838f", "caption": "Tapping followed by water running" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YHdxfbpnd2-8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YHdxfbpnd2-8.npy", "labels": "/m/01w250", "caption": "A man speaking then whistling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part0/Y-NsC63dA01g.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y-NsC63dA01g.npy", "labels": "/m/01yrx,/m/068hy,/m/07qrkrw,/m/09x0r,/m/0jbk", "caption": "Woman speaking to meowing cat" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YBDpU2Qh77NE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBDpU2Qh77NE.npy", "labels": "/m/015p6,/m/020bb7,/m/07pggtn", "caption": "Birds chirping in the distance followed by people speaking and a camera click" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/YzEaGx6an4es.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YzEaGx6an4es.npy", "labels": "/m/01d380,/m/07k1x", "caption": "A tool motor is humming, and metal whirring and grinding are occurring" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part4/Y2sZhC_mKeic.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y2sZhC_mKeic.npy", "labels": "/m/01yrx,/m/068hy,/m/07qrkrw", "caption": "A cat meows and thumps occur twice, while talking is present in the far background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YIdBDl9Wr51A.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YIdBDl9Wr51A.npy", "labels": "/m/07rqsjt", "caption": "Male speaking with sword clanging followed by a females giggle" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/YzEaGx6an4es.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YzEaGx6an4es.npy", "labels": "/m/01d380,/m/07k1x", "caption": "A saw blade blaring" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/YcN-oYKd-M4E.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YcN-oYKd-M4E.npy", "labels": "/m/07bgp,/m/0ch8v,/m/0jbk", "caption": "Sheep vocalizing nearby and in the distance." }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y6pssFJ0m-kU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y6pssFJ0m-kU.npy", "labels": "/m/015p6,/m/020bb7,/m/07pggtn", "caption": "Hissing occurs, a bird chirps and sings, and people speak briefly in the far distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part38/YvruDH_YLaPI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YvruDH_YLaPI.npy", "labels": "/m/032s66", "caption": "Semiautomatic gunfire occurs with slight echo" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YPO8Nu3F8mkA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YPO8Nu3F8mkA.npy", "labels": "/m/014zdl,/m/07qsvvw", "caption": "A distant explosion followed by steam hissing and fire igniting with a person talking in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YPvWI4p74UOs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YPvWI4p74UOs.npy", "labels": "/m/019jd,/m/02rlv9,/m/07yv9,/m/09x0r", "caption": "A man laughing followed by another man yelling in the distance then wind blowing in a microphone as a motor hums and birds chirp in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/Ygr5Zss89yLQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ygr5Zss89yLQ.npy", "labels": "/m/01bjv,/m/07yv9,/m/09x0r", "caption": "An engine running and a female speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YniwgMbB6tpQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YniwgMbB6tpQ.npy", "labels": "/m/01d3sd", "caption": "Plastic clicking and clacking followed by a woman snoring" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/YfWvWhLJ5Fow.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YfWvWhLJ5Fow.npy", "labels": "/m/07qlf79", "caption": "Footsteps running on dirt followed by compressed air spraying as wind blows in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YLBe33dw9ezg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YLBe33dw9ezg.npy", "labels": "/m/09ct_,/m/09x0r", "caption": "A small motor is running and whirring is occurring, music is ongoing in the background, and an adult female speaks briefly in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YPuLuZ_TXv-0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YPuLuZ_TXv-0.npy", "labels": "/m/0316dw,/m/0c2wf", "caption": "Typing repeatedly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YBa92IrXFvJo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBa92IrXFvJo.npy", "labels": "/m/019jd,/m/02rlv9,/m/07yv9", "caption": "An engine running" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y27HIamF8pKo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y27HIamF8pKo.npy", "labels": "/m/01g50p,/m/0284vy3,/m/06d_3,/m/07jdr,/m/07rwm0c", "caption": "Clickety clanking followed by a horn honking loudly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/YyhDw7PZje3g.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YyhDw7PZje3g.npy", "labels": "/m/01h3n,/m/09x0r,/t/dd00129", "caption": "A man is speaking outside with wind noise" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YRfGapDlAYoQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YRfGapDlAYoQ.npy", "labels": "/m/01w250", "caption": "A person whistles as wind blows into a microphone and a crowd of people talk in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part7/Y6CDl4CqOgMg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y6CDl4CqOgMg.npy", "labels": "/m/068hy,/m/0bt9lr,/m/0jbk,/t/dd00136", "caption": "Audio feedback followed by an animal breathing then camera muffling and footsteps shuffling on a hard surface" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y2KR0C5ysO8o.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y2KR0C5ysO8o.npy", "labels": "/m/02mk9,/m/07pb8fc,/m/07q2z82,/m/07yv9,/m/09x0r,/t/dd00066", "caption": "Vibrations of an idling and revving engine" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/Yi2yhbckq3p0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yi2yhbckq3p0.npy", "labels": "/m/012f08,/m/04_sv,/m/07yv9,/m/0k4j", "caption": "A car horn honks once shortly and then two long honks while another car honks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3XcIVh40pTI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3XcIVh40pTI.npy", "labels": "/m/01d3sd", "caption": "A person snoring" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part24/YUV1kdjwpy6U.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YUV1kdjwpy6U.npy", "labels": "/m/01jwx6,/m/09x0r", "caption": "An engine running and ticking and then speech" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/YdZDgJzGtLLU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YdZDgJzGtLLU.npy", "labels": "/m/07pqc89", "caption": "Water rushing and bubbling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part7/Y5OM3tJh51pE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y5OM3tJh51pE.npy", "labels": "/m/02qldy,/m/02zsn,/m/09x0r", "caption": "A woman speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/Yj0KvrVE_Oww.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yj0KvrVE_Oww.npy", "labels": "/m/0912c9,/m/09x0r,/t/dd00125", "caption": "A door shutting followed by a couple of men talking then a horn honking and wood clanking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part24/YVE6Ku0-ucUM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YVE6Ku0-ucUM.npy", "labels": "/m/07qsvvw,/m/09x0r", "caption": "Men speak followed by a small burst and people laughing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YawxrHOpt-sE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YawxrHOpt-sE.npy", "labels": "/m/03fwl,/m/09x0r,/m/0ch8v,/m/0jbk", "caption": "A crowd of people talking and laughing with a motorbike engine running followed by a goat screaming then a person clicking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/YcNARVD02-tw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YcNARVD02-tw.npy", "labels": "/m/02jz0l,/m/09x0r", "caption": "A man and a woman talking followed by water pouring and draining down a pipe" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/YfYTZVxQ8LJk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YfYTZVxQ8LJk.npy", "labels": "/m/09x0r,/m/0ytgt,/t/dd00125", "caption": "A woman talking followed by a young girl talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YBGEMgl1xjac.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBGEMgl1xjac.npy", "labels": "/m/03vt0,/m/06hps,/m/09xqv", "caption": "Rhythmic clicking and simulated squeaking are ongoing, crickets chirp, a bird of prey repeatedly screeches" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/YoiIi6H83Y38.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YoiIi6H83Y38.npy", "labels": "/m/04_sv,/m/07yv9,/m/09x0r", "caption": "An engine revving inconsistently" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part1/Y0NGSrwioYjA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y0NGSrwioYjA.npy", "labels": "/m/03fwl,/m/068hy,/m/09ld4,/m/09x0r,/m/0jbk", "caption": "A man talking as a sheep baas" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/YwbPmnxCLoRQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YwbPmnxCLoRQ.npy", "labels": "/m/0395lw", "caption": "Several bells ringing followed by a single bell ringing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3Sml1wHcuxo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3Sml1wHcuxo.npy", "labels": "/m/01g50p,/m/0284vy3,/m/06d_3,/m/07jdr,/m/07rwm0c", "caption": "A train horn goes off loudly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4YMXgLFcR94.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4YMXgLFcR94.npy", "labels": "/m/02qldy,/m/05zppz,/m/09x0r", "caption": "A man speaks, and an audience applauds" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YCefFMA3klxk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YCefFMA3klxk.npy", "labels": "/m/012f08,/m/07r04,/m/07yv9,/m/0912c9", "caption": "Roadway noise and a horn beep" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YbUTOsLXYyxg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YbUTOsLXYyxg.npy", "labels": "/m/01j3sz,/m/09x0r", "caption": "A man is speaking followed by another male voice followed by laughter" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YSoO1HhaEc9Q.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YSoO1HhaEc9Q.npy", "labels": "/m/09x0r,/t/dd00018", "caption": "Birds chirping, oinking, and then male speech" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YHdPSebdDxe4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YHdPSebdDxe4.npy", "labels": "/m/03q5_w", "caption": "A male speaking and then growling followed by more male speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YmSF_FqBtRPs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YmSF_FqBtRPs.npy", "labels": "/m/01hnzm,/m/07cx4", "caption": "A telephone ringing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y1L_OyngNZMA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1L_OyngNZMA.npy", "labels": "/m/01j3sz,/m/07p6fty,/m/09x0r", "caption": "Echoing male speech, laughter and applause" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/YhxbmDeNSO6Q.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YhxbmDeNSO6Q.npy", "labels": "/m/09x0r,/m/0llzx", "caption": "Vibrations from a sewing machine with a man speaking with several clicks and beeps" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3IScngdQA4I.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3IScngdQA4I.npy", "labels": "/m/02dgv,/m/09x0r", "caption": "A woman whispers and then another woman speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y79XDcI6xZm0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y79XDcI6xZm0.npy", "labels": "/m/02qldy,/m/05zppz,/m/09x0r", "caption": "Over a smattering of applause, the amplified speech of an older man is met with a shouted response" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/YinQOrxc_oZo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YinQOrxc_oZo.npy", "labels": "/t/dd00018", "caption": "Oinking and squealing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part27/Y_GI7meqlYZk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y_GI7meqlYZk.npy", "labels": "/m/01yrx,/m/068hy,/m/07qrkrw,/m/09x0r,/m/0jbk", "caption": "A cat meows and hisses and a child speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YOVQMFBeCHq0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YOVQMFBeCHq0.npy", "labels": "/m/012n7d,/m/03j1ly,/m/03kmc9", "caption": "An emergency vehicle two-tone siren is blaring and fades, and hissing is present" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/YpPLisQ_QXxw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YpPLisQ_QXxw.npy", "labels": "/m/07yv9,/m/0912c9,/m/0k4j", "caption": "A car horn blows amid constant road noise" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YtB8TiiXwKmA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YtB8TiiXwKmA.npy", "labels": "/m/01d380,/m/07k1x,/m/0_ksk", "caption": "A power tool is turned on and off several times" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part4/Y2UNuMbxz9ds.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y2UNuMbxz9ds.npy", "labels": "/m/012f08,/m/07yv9,/m/0k4j,/t/dd00134", "caption": "A vehicle engine revving then sharply accelerating as tires skid as leather whips against fiberglass three times" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/YA2mcp0N__7U.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YA2mcp0N__7U.npy", "labels": "/m/07qlf79,/m/09x0r", "caption": "Mid frequency of multiple people in the distance talking and yelling, followed by coughing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YNtQiduPRiRg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YNtQiduPRiRg.npy", "labels": "/m/01j3sz,/m/09x0r", "caption": "A man laughing followed by a girl laughing as a power tool device operates" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/YeUecAF626A8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YeUecAF626A8.npy", "labels": "/m/07yv9,/m/09x0r,/m/0k4j,/m/0ltv", "caption": "A vehicle engine running idle then revving as a crowd of people talk in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/Yf8WPf5F22xI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yf8WPf5F22xI.npy", "labels": "/m/01hsr_", "caption": "A person sneezing then speaking followed by someone chuckles as a clock ticks in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/YjjfUaMQaG1A.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YjjfUaMQaG1A.npy", "labels": "/m/01d380,/m/09x0r", "caption": "A man speaking together with intermittent, brief drill operating" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4abZbau8tZo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4abZbau8tZo.npy", "labels": "/m/07swgks,/m/09x0r", "caption": "A man talking as rain falls on a hard surface as vehicles drive by followed by a child talking in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9PN4gyxpH2M.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9PN4gyxpH2M.npy", "labels": "/m/09x0r,/t/dd00112", "caption": "A man and woman speaks with some rustling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YWmDe2xbnSY4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YWmDe2xbnSY4.npy", "labels": "/m/07qsvvw", "caption": "A series of bursting and popping sound effects" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/Yir1XTdyt4IY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yir1XTdyt4IY.npy", "labels": "/m/014zdl,/m/07qsvvw,/m/09x0r", "caption": "Steam hissing followed by a loud burst proceeded by warning sirens then a man laughing followed by another man talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/YpaetCbEqp2w.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YpaetCbEqp2w.npy", "labels": "/m/0463cq4", "caption": "Clicking followed by crying and a nose being blown" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YEfk5kdn9lR8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YEfk5kdn9lR8.npy", "labels": "/m/02dgv,/m/02y_763,/m/09x0r", "caption": "A young girl speaking followed by a loud bang and a scream" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part24/YW4GEwnXc9tQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YW4GEwnXc9tQ.npy", "labels": "/m/09ld4", "caption": "A woman speaks an frog croaks followed by wind blowing as others speak" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part19/YMtK8L8gXRrI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YMtK8L8gXRrI.npy", "labels": "/m/01jt3m", "caption": "Footsteps shuffling followed by a cat meowing and then a toilet flushing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y7QN3lwOzfdg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y7QN3lwOzfdg.npy", "labels": "/m/07cx4,/m/09x0r", "caption": "A woman speaks then a man speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YAgh2EKINlSw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YAgh2EKINlSw.npy", "labels": "/m/06mb1,/t/dd00038", "caption": "A man talking followed by two men talking then a vehicle accelerating as rain falls on a surface" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YCYUlLTKoa1Y.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YCYUlLTKoa1Y.npy", "labels": "/m/09x0r,/m/0llzx", "caption": "Humming followed by a woman speaking and slow clicks of a sewing machine" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YD1Sy7kRoaR8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YD1Sy7kRoaR8.npy", "labels": "/m/03k3r,/m/07rv9rh,/m/09x0r,/m/0jbk", "caption": "A woman talking over an intercom speaker as a crowd of people talk in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/Yq1ivQ_2fddk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yq1ivQ_2fddk.npy", "labels": "/m/07qlf79,/m/09x0r,/t/dd00128", "caption": "Men are communicating with a hissing noise in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YrbO727iF03I.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YrbO727iF03I.npy", "labels": "/m/03q5_w,/m/09x0r", "caption": "Burping and then various speech and laughing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part9/Y8o-Y4QP8LWs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y8o-Y4QP8LWs.npy", "labels": "/m/023pjk,/m/04brg2", "caption": "A man speaking as plastic and glass clanks followed by a glass clanging then heavy liquid being poured" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part0/Y-R69Fa-mCaY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y-R69Fa-mCaY.npy", "labels": "/m/01j4z9,/m/083vt", "caption": "A saw running continuously" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y1vCYiVvZ7VE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1vCYiVvZ7VE.npy", "labels": "/m/02qldy,/m/02zsn,/m/09x0r", "caption": "A woman speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YbUTOsLXYyxg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YbUTOsLXYyxg.npy", "labels": "/m/01j3sz,/m/09x0r", "caption": "A man talking then another man talking followed by a group of people laughing then another man talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YZUmZgPL0ges.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YZUmZgPL0ges.npy", "labels": "/m/0395lw", "caption": "Several large bells ring" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YE9zN3-C64KE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YE9zN3-C64KE.npy", "labels": "/m/09x0r,/t/dd00018", "caption": "A woman talking followed by a pig oinking then fabric rustling and a camera muffle" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part38/Yv7BaYF0kagM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yv7BaYF0kagM.npy", "labels": "/m/07yv9,/m/0k5j,/t/dd00129", "caption": "An engine running consistently" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YAxd__X2rixk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YAxd__X2rixk.npy", "labels": "/m/03k3r,/m/07rv9rh,/m/0jbk", "caption": "Clip clops from a horse" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y6cyKp3EDm-0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y6cyKp3EDm-0.npy", "labels": "/m/015p6,/m/09x0r,/m/0h0rv", "caption": "Birds are flapping wings and making noises, and a man talks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/YdlsiellSFf0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YdlsiellSFf0.npy", "labels": "/m/019jd,/m/02rlv9,/m/07yv9", "caption": "Water splashing and something buzzing by" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9HVgYs8OOLc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9HVgYs8OOLc.npy", "labels": "/m/015p6,/m/09x0r,/m/0h0rv,/t/dd00125", "caption": "A man talking followed by pigeons cooing and bird wings flapping then a young man talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/Yjid4t-FzUn0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yjid4t-FzUn0.npy", "labels": "/m/03fwl,/m/07s04w4,/m/09x0r", "caption": "A man speaks followed by a goat bleat" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YLvhvAA11oxE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YLvhvAA11oxE.npy", "labels": "/m/07yv9,/m/09x0r,/m/0h9mv,/m/0ltv,/t/dd00128", "caption": "Loud bustle and screech of traffic, with some voices in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YR91bUbtKrRs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YR91bUbtKrRs.npy", "labels": "/m/09x0r,/t/dd00002", "caption": "Rustling with woman speaking and a baby crying" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YEYTz1LPDHsc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YEYTz1LPDHsc.npy", "labels": "/m/02dgv", "caption": "A vehicle door opening as birds chirp and vehicles pass by in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YsqWyxUObwkw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YsqWyxUObwkw.npy", "labels": "/m/019jd,/m/02rlv9,/m/07yv9", "caption": "Some rustling followed by humming of an engine" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YD9GHUPGWsV0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YD9GHUPGWsV0.npy", "labels": "/m/07bgp,/m/07q0h5t,/m/09x0r", "caption": "A woman and young man are speaking over bleating sheep" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YnlC4UI4hZ60.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YnlC4UI4hZ60.npy", "labels": "/m/012f08,/m/02mk9,/m/07yv9,/m/0k4j", "caption": "An engine being turned over" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y2ABngPM3raQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y2ABngPM3raQ.npy", "labels": "/m/09ld4,/m/09x0r,/m/0jbk", "caption": "An adult male speaks, a tapping sound occurs, and frogs croak" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/YyRoKi7rhSRo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YyRoKi7rhSRo.npy", "labels": "/m/01jt3m,/m/0838f", "caption": "A toilet is flushed" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YkLYCjD6vWI4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YkLYCjD6vWI4.npy", "labels": "/m/06wzb,/m/07rjwbb", "caption": "Hissing of a steam engine train" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YBUAPM4D3-h8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBUAPM4D3-h8.npy", "labels": "/m/015p6,/m/020bb7,/m/07pggtn", "caption": "A child speaks followed by a woman speaking and birds tweeting" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y1HCuBnPLMqQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1HCuBnPLMqQ.npy", "labels": "/m/07pqc89", "caption": "Gurgling and splashing water" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YFKaJsvcyHTk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YFKaJsvcyHTk.npy", "labels": "/t/dd00002", "caption": "A baby cries repeatedly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/Yl5KdHAWwJCw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yl5KdHAWwJCw.npy", "labels": "/m/07qjznl", "caption": "A clock ticking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YlrKGCtSsAkA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YlrKGCtSsAkA.npy", "labels": "/m/09ct_", "caption": "A toy helicopter flying as wind blows into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part7/Y5iTRKJqUIw8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y5iTRKJqUIw8.npy", "labels": "/m/07qjznl,/m/09x0r", "caption": "Bells ringing followed by a steam engine whistling blowing as a crowd of people talk in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YsTMKled6Q1M.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YsTMKled6Q1M.npy", "labels": "/m/015p6,/m/0h0rv,/t/dd00129", "caption": "Whistling with pigeons cooing, wings flapping, and birds chirping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part7/Y5OM3tJh51pE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y5OM3tJh51pE.npy", "labels": "/m/02qldy,/m/02zsn,/m/09x0r", "caption": "A lady speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part19/YMj_BO-iK1G4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YMj_BO-iK1G4.npy", "labels": "/m/0llzx", "caption": "A sewing machine operating followed by metal clacking and gears cranking then scissors snipping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YcFoXRmGgIME.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YcFoXRmGgIME.npy", "labels": "/m/01g50p,/m/0284vy3,/m/04zmvq,/m/06d_3,/m/07jdr,/m/07yv9", "caption": "A loud metallic whine punctuated by a train horn" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YSCow4mpBsGY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YSCow4mpBsGY.npy", "labels": "/m/01d3sd", "caption": "Woosh of air and loud snoring" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YtdpiXW68adA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YtdpiXW68adA.npy", "labels": "/m/0463cq4,/m/09x0r", "caption": "A female voice crying followed by a person speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/Ykx6Rj4MDIAw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ykx6Rj4MDIAw.npy", "labels": "/m/07rjwbb", "caption": "A cuckoo clock cooing followed by a steam engine running on railroad tracks as steam hisses and a railroad crossing signal bell rings in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/YgkWd1HugK2w.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YgkWd1HugK2w.npy", "labels": "/m/015p6,/m/0h0rv,/t/dd00129", "caption": "Pigeons coo and flap their wings" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YAUJPx81qKtY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YAUJPx81qKtY.npy", "labels": "/m/01h3n,/m/03vt0,/m/0h2mp", "caption": "Insects buzzing as a man talks and birds chirp in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/YzBXoaQ1GVlc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YzBXoaQ1GVlc.npy", "labels": "/m/09x0r,/m/0ytgt,/t/dd00013,/t/dd00126", "caption": "Children speak in the distance and a woman speaks nearby with some rustling and banging" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/Yii3Geza3hAU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yii3Geza3hAU.npy", "labels": "/m/0llzx", "caption": "A man yells in the background, and a sewing machine sews garments" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3rna9zo5ZOs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3rna9zo5ZOs.npy", "labels": "/m/02qldy,/m/05zppz,/m/09x0r", "caption": "A man is speaking along with noise from a cheering crowd" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YtwFypUcdgRc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YtwFypUcdgRc.npy", "labels": "/m/01bjv,/m/07yv9,/m/09x0r", "caption": "A man shouting then laughing as wind blows heavily into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/YfYTZVxQ8LJk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YfYTZVxQ8LJk.npy", "labels": "/m/09x0r,/m/0ytgt,/t/dd00125", "caption": "A woman talking before and after a young girl gasping then talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part24/YVQnmlf2OsUg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YVQnmlf2OsUg.npy", "labels": "/m/09ct_", "caption": "A high pitched engine running consistently with intermittent scraping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YROootH-mtEI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YROootH-mtEI.npy", "labels": "/m/0j6m2", "caption": "Water flows loudly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9BukzlPNqC8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9BukzlPNqC8.npy", "labels": "/m/01d380,/m/09x0r", "caption": "'A power tool vibrating with men speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YHdPSebdDxe4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YHdPSebdDxe4.npy", "labels": "/m/03q5_w", "caption": "A beep is followed by retching and muffled speech" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4UPOUGVMlEs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4UPOUGVMlEs.npy", "labels": "/t/dd00018", "caption": "Dogs growling as a pig snorts while grass rustles and someone is heavily breathing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y6dLkgq9EKPE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y6dLkgq9EKPE.npy", "labels": "/m/01bjv,/m/07yv9,/m/09x0r", "caption": "An adult male is speaking and a bus hisses" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/YdmUOSyPXkUw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YdmUOSyPXkUw.npy", "labels": "/m/06wzb,/m/07rjwbb", "caption": "Steam hissing. With light mechanical sounds" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/Yk1QxQ4jJaEQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yk1QxQ4jJaEQ.npy", "labels": "/m/07r04,/m/07yv9,/m/09x0r,/t/dd00129", "caption": "Motor sounds with male speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part9/Y8Zo30kV5aiI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y8Zo30kV5aiI.npy", "labels": "/m/012n7d,/m/03j1ly,/m/03kmc9", "caption": "Vehicles driving by as emergency sirens sound" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part0/Y-Sz4z0QwEuM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y-Sz4z0QwEuM.npy", "labels": "/m/03q5_w", "caption": "A long, loud burp" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y4CAMv5nlr-0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4CAMv5nlr-0.npy", "labels": "/m/02qldy,/m/05zppz,/m/09x0r", "caption": "A man speaking forcefully" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y6ZwYgzcN6Is.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y6ZwYgzcN6Is.npy", "labels": "/m/09x0r,/m/0j6m2,/t/dd00129", "caption": "A woman yelling and laughing as ocean waves crash and a group of people shout while wind blows into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YIhvXtS9-IxM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YIhvXtS9-IxM.npy", "labels": "/m/07yv9,/m/09ct_", "caption": "An idle helicopter engine running" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y1wW0YJQ-Xa0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1wW0YJQ-Xa0.npy", "labels": "/m/07qlf79,/m/09x0r", "caption": "A cough, then spray paint bottle shaking and spraying while a muffle of people talking in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/YdYvL6uEMl6E.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YdYvL6uEMl6E.npy", "labels": "/m/019jd,/m/02rlv9,/m/034srq,/m/03m9d0z,/m/05kq4,/t/dd00092", "caption": "An engine running and wind blowing hard" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/Yi1u_2eZYYlE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yi1u_2eZYYlE.npy", "labels": "/m/07pb8fc,/m/07r04,/m/07yv9", "caption": "An engine running very briefly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part4/Y2a6GNu6uCDE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y2a6GNu6uCDE.npy", "labels": "/m/02qldy,/m/02zsn,/m/09x0r", "caption": "A woman speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/YwrQDkX0NbTA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YwrQDkX0NbTA.npy", "labels": "/m/019jd,/m/02rlv9,/m/07yv9", "caption": "A motorboat driving by while water splashes" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YFXdoNvmrYxo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YFXdoNvmrYxo.npy", "labels": "/m/03vt0,/m/09x0r,/t/dd00129", "caption": "A young girl speaking followed by a man speaking then a young boy speaking as birds chirp in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YL8dA-2Lu2hY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YL8dA-2Lu2hY.npy", "labels": "/m/01w250", "caption": "High pitched, rhythmic whistling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y1ed87LLY97k.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1ed87LLY97k.npy", "labels": "/m/07rjwbb", "caption": "Constant faint humming and a few light knocks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/YinQOrxc_oZo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YinQOrxc_oZo.npy", "labels": "/t/dd00018", "caption": "Oinking followed by screams" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part19/YMOxddxW5PXs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YMOxddxW5PXs.npy", "labels": "/m/09x0r,/m/0dxrf", "caption": "A man is speaking as food is frying" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9hxFqltp3xw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9hxFqltp3xw.npy", "labels": "/m/07qlf79,/m/09x0r", "caption": "A woman speaks with some clicks and then hissing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YJhGp7HmRQxg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YJhGp7HmRQxg.npy", "labels": "/m/03k3r,/m/07q5rw0,/m/09x0r,/m/0jbk", "caption": "A metal clack followed by a horse neighing as birds chirp and gusts of wind blow in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YIKnx3hJv1bs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YIKnx3hJv1bs.npy", "labels": "/m/07qlf79", "caption": "Something spraying from a hose, followed by the buzz of a machine." }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YUCy1BEx8jBE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YUCy1BEx8jBE.npy", "labels": "/m/0j6m2", "caption": "A man talks while water burbles" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YEQVWhHmT_cE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YEQVWhHmT_cE.npy", "labels": "/m/02qldy,/m/05zppz,/m/09x0r", "caption": "A crowd of people applauding followed by clothes rustling as a man is talking followed by glass shattering and a crowd of people laughing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part0/Y-NrFeH-kBSM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y-NrFeH-kBSM.npy", "labels": "/m/032s66", "caption": "A gun cocking followed by a gunshot and a man talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YNmmbNqmsPaY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YNmmbNqmsPaY.npy", "labels": "/m/07pb8fc,/m/07yv9,/m/0k4j", "caption": "Humming and rattling of an idling engine with some bells ringing in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3VHpLxtd498.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3VHpLxtd498.npy", "labels": "/m/015p6,/m/09x0r,/m/0h0rv", "caption": "Pigeons are cooing along with a machine rumbling noise and a man speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YnmLMLgWPmFM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YnmLMLgWPmFM.npy", "labels": "/m/09x0r,/m/0j6m2", "caption": "A motorboat engine running as water splashes and a man shouts in the background followed by birds chirping in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YL_CNz9Vrtkw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YL_CNz9Vrtkw.npy", "labels": "/m/028ght,/m/09x0r", "caption": "A man talking followed by a crowd of people cheering and applauding" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YlHh0SwUhP8U.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YlHh0SwUhP8U.npy", "labels": "/m/09ddx", "caption": "Metal clicking before a gunshot firing followed by a person sighing and metal clanking while wood clacks proceeded by another gunshot firing as ducks quack in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9z2OwpftxUE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9z2OwpftxUE.npy", "labels": "/m/0ngt1", "caption": "Continuous thunder" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YSNy_axSCoyw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YSNy_axSCoyw.npy", "labels": "/m/07qjznl", "caption": "A clock ticking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part0/Y-CcGuq0yoKo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y-CcGuq0yoKo.npy", "labels": "/m/02qldy,/m/02zsn,/m/09x0r", "caption": "A female speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y1IoHRTUp86c.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1IoHRTUp86c.npy", "labels": "/m/07yv9,/m/0k5j,/t/dd00129", "caption": "A woman talking over an intercom as an aircraft engine runs then accelerates" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YXWw7ZM1c_QA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YXWw7ZM1c_QA.npy", "labels": "/m/07qjznl,/m/09x0r", "caption": "Wood sanding followed by a woman talking as a clock ticks proceeded by a cuckoo clock alarm cooing and bell ringing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YZ0IrCa4MvOA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YZ0IrCa4MvOA.npy", "labels": "/m/0130jx,/m/02jz0l,/m/07pqc89,/m/0838f", "caption": "Water trickling rapidly and draining" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YWLzzpzOKtnY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YWLzzpzOKtnY.npy", "labels": "/m/01h3n,/m/09x0r", "caption": "Male speaking and an insect buzzing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/Yhrv6fwnmBkY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yhrv6fwnmBkY.npy", "labels": "/m/068hy,/m/07rc7d9,/m/09b5t,/m/09x0r,/m/0bt9lr,/m/0jbk,/t/dd00136", "caption": "A rooster cackles and a dog yelps and whimpers followed by a man laughing and then speaking then the dog barks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YLs2vrr9TamU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YLs2vrr9TamU.npy", "labels": "/m/083vt", "caption": "Heavy machinery operating followed by wood crunching and cracking as wind blows into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YEQVWhHmT_cE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YEQVWhHmT_cE.npy", "labels": "/m/02qldy,/m/05zppz,/m/09x0r", "caption": "Fabric shuffling followed by a man talking then a series of glass shattering and a crowd of people laughing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/Yq4YFJA5pFXc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yq4YFJA5pFXc.npy", "labels": "/m/09ct_,/t/dd00129", "caption": "Wind blowing into a microphone followed by plastic clacking then an electric toy motor starting up" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y6i5eQOpFk_U.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y6i5eQOpFk_U.npy", "labels": "/m/0130jx,/m/02jz0l,/m/0838f", "caption": "Water flowing from a faucet with some light bangs and a man speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YL2dyilgQ8iM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YL2dyilgQ8iM.npy", "labels": "/m/09t49,/t/dd00092", "caption": "Wind blows followed by rustling and scraping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YtB8TiiXwKmA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YtB8TiiXwKmA.npy", "labels": "/m/01d380,/m/07k1x,/m/0_ksk", "caption": "Vibrations and humming from a power tool starting and stopping several times" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y54eRRbCtPn8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y54eRRbCtPn8.npy", "labels": "/m/02qldy,/m/02zsn,/m/09x0r", "caption": "A woman is speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y22L_3pBa1AI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y22L_3pBa1AI.npy", "labels": "/m/07yv9,/m/0k4j,/t/dd00134", "caption": "Humming and vibrations of a vehicle speeding past and into the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/YA61Mry8zBwE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YA61Mry8zBwE.npy", "labels": "/m/07rv9rh,/m/09x0r,/m/0jbk", "caption": "A man speaking over an intercom followed by a crowd of people talking then applauding" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9XqkKuTqEOM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9XqkKuTqEOM.npy", "labels": "/m/02dgv", "caption": "Wood brushing followed by a door creaking then wood clanking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part1/Y0_K6OKtoBBU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y0_K6OKtoBBU.npy", "labels": "/m/01yrx,/m/068hy,/m/07qrkrw,/m/0jbk", "caption": "Silence followed by white noise and meowing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/Yo7-X8DAToGc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yo7-X8DAToGc.npy", "labels": "/m/012f08,/m/07yv9,/m/0ltv,/t/dd00134", "caption": "A vehicle accelerating and driving by" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/Yr2KhpX_QgXA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yr2KhpX_QgXA.npy", "labels": "/m/02mk9,/m/02x984l,/m/09x0r", "caption": "A man speaks with some distant humming and vibrating getting louder" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y4CAMv5nlr-0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4CAMv5nlr-0.npy", "labels": "/m/02qldy,/m/05zppz,/m/09x0r", "caption": "A man speaks as he gives a speech and then the crowd cheers" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3Sml1wHcuxo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3Sml1wHcuxo.npy", "labels": "/m/01g50p,/m/0284vy3,/m/06d_3,/m/07jdr,/m/07rwm0c", "caption": "A train running on a railroad track as steam hisses and a train horn blows several times along with a railroad crossing signal ringing in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part38/YvEWmHtiznF8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YvEWmHtiznF8.npy", "labels": "/m/012f08,/m/01bjv,/m/07yv9,/m/09x0r", "caption": "A man is talking while a bus is idling in the background." }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y1FNJbN-eHY4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1FNJbN-eHY4.npy", "labels": "/m/03q5_w,/m/09x0r", "caption": "Burping and girls laughing with many voices in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YlVr-PxhZo8s.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YlVr-PxhZo8s.npy", "labels": "/m/07pb8fc,/m/07yv9,/t/dd00126", "caption": "Hissing and vibrating from an idling engine" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part24/YUhCzD6EBJBU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YUhCzD6EBJBU.npy", "labels": "/m/01d380,/m/07k1x,/m/0_ksk", "caption": "A power drill operating with a man speaking and a click" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/YwVi5w_NU6CM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YwVi5w_NU6CM.npy", "labels": "/m/012f08,/m/012ndj,/m/03j1ly,/m/03kmc9,/m/07r04,/m/07yv9", "caption": "Humming of an engine with a ringing siren" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YSZ6CcXINiiE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YSZ6CcXINiiE.npy", "labels": "/m/014zdl,/m/07qsvvw,/m/09x0r", "caption": "A man briefly talks followed by a loud burst then laughter" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4pv3w--cRrA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4pv3w--cRrA.npy", "labels": "/m/09t49", "caption": "A machine makes a constant rumbling noise" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YbygBWUkpaC8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YbygBWUkpaC8.npy", "labels": "/m/020bb7,/m/07pggtn,/m/09x0r,/m/0jbk,/t/dd00129", "caption": "A man speaking followed by a bird chirping close by" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/YiOCpICiu4LA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YiOCpICiu4LA.npy", "labels": "/m/01h3n,/m/03l9g,/m/03vt0,/m/0h2mp", "caption": "A man speaks with chirping birds and faint buzzing of insects" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y7MLERaOgK_Y.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y7MLERaOgK_Y.npy", "labels": "/m/0llzx", "caption": "A small girl sings with vibrations of a sewing machine which stops" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YRk-ujWKzPuc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YRk-ujWKzPuc.npy", "labels": "/m/06mb1,/t/dd00038", "caption": "Continuous and steady rainfall" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/YxQDq3A4Zfbo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YxQDq3A4Zfbo.npy", "labels": "/m/019jd,/m/034srq,/m/03m9d0z,/m/05kq4,/m/0hsrw,/t/dd00092", "caption": "Water splashing and wind blowing over a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y1slvoNgzBLE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1slvoNgzBLE.npy", "labels": "/m/01g50p,/m/06d_3,/m/07jdr,/m/07yv9,/m/0912c9", "caption": "A high tone signal followed by train moving down tracks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YAf4a-9rcnP0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YAf4a-9rcnP0.npy", "labels": "/m/07qsvvw", "caption": "Bursting and popping noises like gunfire" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YAagLJkfrFMk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YAagLJkfrFMk.npy", "labels": "/m/01jt3m", "caption": "A toilet flushing followed by a person breathing then metal clacking and a toilet flushing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YC5kmOK_l4jc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YC5kmOK_l4jc.npy", "labels": "/m/09x0r,/m/0ytgt,/t/dd00001", "caption": "A young girl talking as a baby is laughing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part9/Y8DQfjqPCTI8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y8DQfjqPCTI8.npy", "labels": "/m/01h3n,/m/03vt0,/m/0h2mp", "caption": "Bees are buzzing while birds chirp and two adult males are having a conversation" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/YgQMTOKsCIyk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YgQMTOKsCIyk.npy", "labels": "/m/015p6,/m/07qwf61,/m/09ddx,/m/09x0r", "caption": "Ducks quacking followed by male speech" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/YpaetCbEqp2w.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YpaetCbEqp2w.npy", "labels": "/m/0463cq4", "caption": "A child crying followed by a person blowing their nose during a series of computer mouse clicks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YE6FH_xp3I54.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YE6FH_xp3I54.npy", "labels": "/m/07pggtn,/m/09x0r,/m/0jbk,/t/dd00129", "caption": "A man speaking as birds chirp in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part4/Y30D1tqNFHMc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y30D1tqNFHMc.npy", "labels": "/m/01jwx6,/m/0chx_", "caption": "A loud engine roars followed by four loud beeps." }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part24/YVOXl8iR-HnI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YVOXl8iR-HnI.npy", "labels": "/m/014yck,/m/07yv9,/m/09x0r,/m/0cmf2,/m/0k5j", "caption": "A jet engine hums first distant then louder as it passes by" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part0/Y-BUWGM7qeUM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y-BUWGM7qeUM.npy", "labels": "/m/06mb1", "caption": "Rain falling and wind blowing hard with rustling leaves" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y1ed87LLY97k.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1ed87LLY97k.npy", "labels": "/m/07rjwbb", "caption": "Thumping on a wooden surface before and after plastic clanking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/Yr2djvq1vc68.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yr2djvq1vc68.npy", "labels": "/m/0130jx,/m/02jz0l,/m/0838f", "caption": "Water running out of a faucet, some hitting a sink bottom, and some water filling a cup" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YL8dA-2Lu2hY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YL8dA-2Lu2hY.npy", "labels": "/m/01w250", "caption": "Someone is whistling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YB3O476LeuXY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YB3O476LeuXY.npy", "labels": "/m/07pb8fc,/t/dd00130", "caption": "An engine running" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3n05BjV7r7M.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3n05BjV7r7M.npy", "labels": "/m/02dgv,/m/02y_763", "caption": "Rattling and banging with faint humming" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YYH4qi8Ul6v0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YYH4qi8Ul6v0.npy", "labels": "/m/09x0r,/t/dd00002", "caption": "Baby crying then man speaking and humming" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YcFoXRmGgIME.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YcFoXRmGgIME.npy", "labels": "/m/01g50p,/m/0284vy3,/m/04zmvq,/m/06d_3,/m/07jdr,/m/07yv9", "caption": "A train travels on the railroad and sounds the train horn" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YbA5zPFSFZAA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YbA5zPFSFZAA.npy", "labels": "/m/07rqsjt", "caption": "Digital beeping with static electric scratching" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/Yt4prXmPwthg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yt4prXmPwthg.npy", "labels": "/m/09x0r,/m/0llzx", "caption": "A sewing machine is in use, and a woman talks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YYEYeQ0lIkBQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YYEYeQ0lIkBQ.npy", "labels": "/m/015p6,/m/09ddx,/m/09x0r", "caption": "Ducks quack as people communicate" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y473wBEwC35M.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y473wBEwC35M.npy", "labels": "/m/02qldy,/m/05zppz,/m/09x0r", "caption": "A car honks in the background while a man speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YSQHYl2Kp5ww.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YSQHYl2Kp5ww.npy", "labels": "/m/07ptfmf,/m/0dxrf", "caption": "Instrumental music playing followed by two men speaking as food and oil sizzle and metal clanking against a pot" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YFA11v4SmdBc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YFA11v4SmdBc.npy", "labels": "/m/01w250,/m/09x0r", "caption": "A man speaking followed by a series of whistling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YXQxIXaX_7M0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YXQxIXaX_7M0.npy", "labels": "/m/09t49,/m/09x0r", "caption": "A large volume of water is rushing fast, splashing and roaring, and an adult male shout in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part4/Y2bq2lc3DLwM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y2bq2lc3DLwM.npy", "labels": "/m/07yv9,/m/09x0r,/m/0k4j,/t/dd00134", "caption": "As an adult male speaks, a mid-size motor vehicle engine runs, accelerates and approaches" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/Yh5_1pnkl_SY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yh5_1pnkl_SY.npy", "labels": "/m/02jz0l,/m/0838f", "caption": "Water pouring into a glass container as a man faintly speaks in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/Yhmd6pa2e_rs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yhmd6pa2e_rs.npy", "labels": "/m/01bjv,/m/07yv9,/m/09x0r", "caption": "A bus is driving, and people are speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YAf4a-9rcnP0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YAf4a-9rcnP0.npy", "labels": "/m/07qsvvw", "caption": "Firecrackers exploding followed by footsteps squeaking and shuffling then compressed air spraying" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/YoNHCc_izsDE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YoNHCc_izsDE.npy", "labels": "/m/01j3sz,/m/07rrlb6", "caption": "An infant and woman laughing as water splashes and birds chirp in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part7/Y5OM3tJh51pE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y5OM3tJh51pE.npy", "labels": "/m/02qldy,/m/02zsn,/m/09x0r", "caption": "A female speaking continuously" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part4/Y2ymiXjImwGs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y2ymiXjImwGs.npy", "labels": "/m/012ndj,/m/01bjv,/m/09x0r", "caption": "A siren with people talking faintly in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part27/Y_xylo5_IiaM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y_xylo5_IiaM.npy", "labels": "/m/09x0r,/m/0ytgt,/t/dd00125", "caption": "A young girl talking as a woman is talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YrE6BJ0Bo4w4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YrE6BJ0Bo4w4.npy", "labels": "/m/02jz0l,/m/09x0r,/t/dd00125", "caption": "Female speaking, water running, and then female speech" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4fz0-Kx2oNs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4fz0-Kx2oNs.npy", "labels": "/m/0dxrf", "caption": "Food frying in a pan" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y1QNLMF-Kl_s.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1QNLMF-Kl_s.npy", "labels": "/m/02qldy,/m/02zsn,/m/09x0r", "caption": "Female speaking continuously" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/Yz1ax0QPpd14.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yz1ax0QPpd14.npy", "labels": "/m/015p6,/m/09ddx", "caption": "A duck quacking as birds chirp and a pigeon cooing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part19/YNX0gR9Eebp0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YNX0gR9Eebp0.npy", "labels": "/m/03dnzn,/m/09x0r,/m/0ytgt", "caption": "Water is trickling and splashing into more water and thumping is occurring, a young child coos, and an adult female speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YD9tinq3RMpU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YD9tinq3RMpU.npy", "labels": "/m/019jd,/m/02rlv9,/m/07yv9,/m/09x0r", "caption": "Outdoor noise from a water vehicle as people are talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YniwgMbB6tpQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YniwgMbB6tpQ.npy", "labels": "/m/01d3sd", "caption": "Plastic clicking and tapping followed by a woman snoring" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y6aWnK1GyeJY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y6aWnK1GyeJY.npy", "labels": "/m/0463cq4,/m/09x0r", "caption": "A baby cries while electronic speech occurs in the background, an adult female speaks, a sneeze occurs, and an adult female speaks once more" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YCwxgQS3SXic.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YCwxgQS3SXic.npy", "labels": "/m/0llzx", "caption": "A sewing machine operating" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YXrJcmftCY04.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YXrJcmftCY04.npy", "labels": "/m/028ght", "caption": "A crowd of people shout and give applause" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/Yos_2U4xqTqw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yos_2U4xqTqw.npy", "labels": "/m/014zdl,/m/07qsvvw,/m/07s2xch", "caption": "Wind blowing followed by heavy footsteps on a solid surface then a man groaning proceeded by two explosions" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YmW1EpJYcy_E.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YmW1EpJYcy_E.npy", "labels": "/m/04_sv,/m/07yv9,/t/dd00128", "caption": "A motorbike revving and driving by as wind blows heavily into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YHg6HxylRGDo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YHg6HxylRGDo.npy", "labels": "/m/012n7d,/m/03j1ly,/m/03kmc9", "caption": "A two-tone emergency vehicle siren is blaring, and vehicular traffic is present in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y2ErfX6ZT5pM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y2ErfX6ZT5pM.npy", "labels": "/m/01jt3m", "caption": "Some humming followed by a toilet flushing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3XcIVh40pTI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3XcIVh40pTI.npy", "labels": "/m/01d3sd", "caption": "A sleeping person snores loudly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/YeYbFtxZmKL4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YeYbFtxZmKL4.npy", "labels": "/m/03k3r,/m/09x0r,/m/0jbk", "caption": "Clanking and rustling with people faintly speaking and horse clip-clopping in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/Yj1AiqT5oHZc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yj1AiqT5oHZc.npy", "labels": "/m/02fs_r,/m/09x0r,/t/dd00125", "caption": "A man talking followed by several electronic beeps" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/Ylq9RvAA4mqY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ylq9RvAA4mqY.npy", "labels": "/m/07ptfmf,/m/0dxrf", "caption": "Sizzling food with some scraping and rattling as a man speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YFc9pG54DDJM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YFc9pG54DDJM.npy", "labels": "/m/01jt3m,/m/0838f", "caption": "Water flowing down a flushed toilet" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y1_z6NcidGzM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1_z6NcidGzM.npy", "labels": "/m/07swgks,/m/09x0r,/m/0j6m2", "caption": "Water running with clanking and children murmuring in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/YonBZOH88OYs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YonBZOH88OYs.npy", "labels": "/m/07qlf79", "caption": "Air spraying several times as a machine motor hums in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3kBlVLkN0zo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3kBlVLkN0zo.npy", "labels": "/m/03fwl,/m/09x0r,/m/0ch8v,/m/0jbk", "caption": "A goat bleats and background voices" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YbhlhcGONisM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YbhlhcGONisM.npy", "labels": "/m/0316dw,/m/09x0r", "caption": "A man talking as fabric shuffles during a series of computer mouse clicks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YArHiac57pVk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YArHiac57pVk.npy", "labels": "/m/07qjznl,/m/09x0r", "caption": "A man is speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y2KR0C5ysO8o.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y2KR0C5ysO8o.npy", "labels": "/m/02mk9,/m/07pb8fc,/m/07q2z82,/m/07yv9,/m/09x0r,/t/dd00066", "caption": "A motor revs hard, a man speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/YxnVqvc7N7Po.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YxnVqvc7N7Po.npy", "labels": "/m/07cx4,/m/09x0r", "caption": "A woman and man speaking followed by a phone clicking then a phone call ring" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YW7OJevEgq7w.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YW7OJevEgq7w.npy", "labels": "/m/05tny_,/m/068hy,/m/07rc7d9,/m/0bt9lr,/m/0jbk", "caption": "Dog yapping and panting" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part24/YVMsbrcHPBfk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YVMsbrcHPBfk.npy", "labels": "/m/03fwl", "caption": "A goat bleating repeatedly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YNlKlRKz8OKI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YNlKlRKz8OKI.npy", "labels": "/m/015p6,/m/020bb7,/m/07pggtn", "caption": "A woman speaking with a chuckle followed by a bird chirping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YmlnUJH4BQnk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YmlnUJH4BQnk.npy", "labels": "/m/07pdjhy", "caption": "Female speech and rubbing simultaneously" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y1FNJbN-eHY4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1FNJbN-eHY4.npy", "labels": "/m/03q5_w,/m/09x0r", "caption": "A crowd murmuring with several belches followed by laughter" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9ZZHvwaH-CU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9ZZHvwaH-CU.npy", "labels": "/m/032s66", "caption": "Gunfire sounds with video game sounds" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part38/YvaujJ7msKfc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YvaujJ7msKfc.npy", "labels": "/m/012n7d,/m/03j1ly,/m/03kmc9", "caption": "City ambiance with light music playing and wind blowing on a microphone as police sirens sound in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/Yjs4dr5JusdM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yjs4dr5JusdM.npy", "labels": "/m/07cx4,/m/09x0r", "caption": "The voices of a man and a women talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YObWjGBJF_94.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YObWjGBJF_94.npy", "labels": "/m/02jz0l,/m/07ptzwd", "caption": "White noise while music is playing in the background followed by a series of plastic clicking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YE9zN3-C64KE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YE9zN3-C64KE.npy", "labels": "/m/09x0r,/t/dd00018", "caption": "A woman talking followed by a pig oinking then fabric rustling before camera muffling and footsteps walking on a hard surface" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y6eX6bJOFftA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y6eX6bJOFftA.npy", "labels": "/m/02rlv9,/m/07yv9,/m/09x0r", "caption": "A motorboat drives in the distance as people talk and rap music plays in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/Yf8WPf5F22xI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yf8WPf5F22xI.npy", "labels": "/m/01hsr_", "caption": "A rapid ticktock and then a man speaks and sneezes followed by another man hiccuping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part9/Y86dNVnTwH6U.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y86dNVnTwH6U.npy", "labels": "/m/09x0r,/m/0llzx", "caption": "Rustling and then a machine operating" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y11SEBDuoqSk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y11SEBDuoqSk.npy", "labels": "/m/07yv9,/m/0cmf2,/m/0k5j", "caption": "Humming of an engine with rapid gunshots" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YRfGapDlAYoQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YRfGapDlAYoQ.npy", "labels": "/m/01w250", "caption": "A person whistling as a crowd of people talk in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YB3O476LeuXY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YB3O476LeuXY.npy", "labels": "/m/07pb8fc,/t/dd00130", "caption": "A motorbike engine running idle" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/YfmEft49sPfE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YfmEft49sPfE.npy", "labels": "/m/05zppz,/m/09t49,/m/09x0r", "caption": "A man speaks with wind blowing and leaves rustling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YniwgMbB6tpQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YniwgMbB6tpQ.npy", "labels": "/m/01d3sd", "caption": "A person snoring" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YtJhVH3VIrnE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YtJhVH3VIrnE.npy", "labels": "/m/02dgv", "caption": "Wood cracking and loud cluttering" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YXJba7pTbpD0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YXJba7pTbpD0.npy", "labels": "/m/07qlf79", "caption": "Air spraying followed by fire igniting then loud audio static followed by pressurized air releasing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/YeXj9OAik5cc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YeXj9OAik5cc.npy", "labels": "/m/04_sv,/m/07yv9,/t/dd00128", "caption": "A motorbike engine running idle as wind blows into a microphone and birds chirp in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YHkbCUN4V3TU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YHkbCUN4V3TU.npy", "labels": "/m/09x0r,/m/0ytgt,/t/dd00125", "caption": "A child screaming and laughing as woman talks and giggles followed by thumping on a wooden surface" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YETb9EIQOMAA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YETb9EIQOMAA.npy", "labels": "/m/02qldy,/m/02zsn,/m/09x0r", "caption": "A woman speaking on a microphone as a crowd of people talk in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YatmDP_fmK_8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YatmDP_fmK_8.npy", "labels": "/m/014zdl,/m/07qsvvw", "caption": "Mechanical growling followed by an explosion" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YITlqMkR5alY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YITlqMkR5alY.npy", "labels": "/m/03fwl,/m/09x0r,/m/0ch8v,/m/0jbk", "caption": "A cat meowing followed by a person screaming as a man talks in the background and wind blows into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part38/YwAZrOPvul4Y.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YwAZrOPvul4Y.npy", "labels": "/m/09x0r,/t/dd00112", "caption": "Man speaking while there is crinkling sound" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YkHIe4CfaccQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YkHIe4CfaccQ.npy", "labels": "/m/03fwl,/m/068hy,/m/0ch8v,/m/0jbk", "caption": "Baby goat bleating with licking sounds" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/Yazh_-OkQ-uI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yazh_-OkQ-uI.npy", "labels": "/m/07bgp,/m/07q0h5t,/m/09x0r", "caption": "Animals are bleating and people are talking in the background, an adult female and an adult male speak, and an aircraft is present in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/YoN0IcZaHD_8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YoN0IcZaHD_8.npy", "labels": "/m/01d380,/m/07k1x,/m/083vt,/m/09x0r,/t/dd00125", "caption": "A man talking followed by a power tool drilling then footsteps shuffling proceeded by a man talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YB8rdur4aams.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YB8rdur4aams.npy", "labels": "/m/07yv9,/m/0912c9,/t/dd00128", "caption": "A vehicle horn honking as a motor engine gurgles and wind blows into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/Yktc_tJxw8sc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yktc_tJxw8sc.npy", "labels": "/m/0463cq4", "caption": "A person makes sobbing noises" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YJ0yeFeKvIt8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YJ0yeFeKvIt8.npy", "labels": "/m/09t49", "caption": "Gusts of wind blowing as leaves rustle and birds chirp in the distance while wind blows into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YI4HpYGMMsz4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YI4HpYGMMsz4.npy", "labels": "/m/083vt,/m/09x0r", "caption": "Man speaking giving directions followed by tapping on table" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9_YfTz8cnFY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9_YfTz8cnFY.npy", "labels": "/m/06hck5,/m/06wzb,/m/07rjwbb", "caption": "A steam engine horn whistles followed by steam hissing as a group of people talk in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YSmdj6JFB9MQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YSmdj6JFB9MQ.npy", "labels": "/m/01jt3m,/m/09x0r", "caption": "Music plays and an adult female speaks, a flush occurs and water splashes and gurgles, and a young female speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9z8XIRyUq9Q.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9z8XIRyUq9Q.npy", "labels": "/m/02qldy,/m/02zsn,/m/09x0r", "caption": "A woman speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YIKnx3hJv1bs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YIKnx3hJv1bs.npy", "labels": "/m/07qlf79", "caption": "Compressed air spraying followed by a power tool buzzing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/Yy_OyLW9lBXU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yy_OyLW9lBXU.npy", "labels": "/m/09x0r,/t/dd00002", "caption": "Babies crying as a woman is laughing and a man is talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YFf8bCCJfVX4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YFf8bCCJfVX4.npy", "labels": "/m/032s66", "caption": "Rapid and repeated gunfire and then male speech" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/YhqPBcvex1VU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YhqPBcvex1VU.npy", "labels": "/m/09x0r,/t/dd00002", "caption": "A person talking softly before an infant cries" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YXWw7ZM1c_QA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YXWw7ZM1c_QA.npy", "labels": "/m/07qjznl,/m/09x0r", "caption": "Rustling and distant sanding with nearby ticking and chiming from a coo clock" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part1/Y096oTVzc5Gs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y096oTVzc5Gs.npy", "labels": "/m/09x0r,/m/0bt9lr,/m/0jbk,/t/dd00136", "caption": "A woman talking as a dog growls followed by a fan blowing air" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part15/YGGgQR7aIofY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YGGgQR7aIofY.npy", "labels": "/m/012f08,/m/01bjv,/m/07yv9", "caption": "A vehicle horn honking followed by a bus driving in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YKvrcRMfFzOE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YKvrcRMfFzOE.npy", "labels": "/m/07yv9,/m/09ct_,/m/0k5j", "caption": "A helicopter flying as wind blows heavily into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YQvATUKXYFBs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YQvATUKXYFBs.npy", "labels": "/m/01g50p,/m/0284vy3,/m/06d_3,/m/07jdr,/m/07rwm0c", "caption": "A train running on railroad tracks while a train horn blows as railroad warning signals ring" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y0qbHT34qTZE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y0qbHT34qTZE.npy", "labels": "/m/032s66,/m/06q74,/m/09x0r", "caption": "Loud gunshots and explosions with men speaking, water splashing, wind blowing, and thunder roaring" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YTQr9v-PQOc4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YTQr9v-PQOc4.npy", "labels": "/m/01hsr_", "caption": "Humming noise then sneezing and coughing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/Yr2djvq1vc68.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yr2djvq1vc68.npy", "labels": "/m/0130jx,/m/02jz0l,/m/0838f", "caption": "A faucet pouring water as a plastic container fills with liquid and scrubbing against a plastic surface while water trickles" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/Yq3SEOW2m4WY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yq3SEOW2m4WY.npy", "labels": "/m/01g50p,/m/0284vy3,/m/06d_3,/m/07jdr,/m/07rwm0c", "caption": "Distant humming gets louder as a train passes after honking a horn" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YljrL7Cb-jr8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YljrL7Cb-jr8.npy", "labels": "/m/07qlf79", "caption": "Water is spraying out of machines onto surfaces while the machines are running" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y6i5eQOpFk_U.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y6i5eQOpFk_U.npy", "labels": "/m/0130jx,/m/02jz0l,/m/0838f", "caption": "A man speaking as water runs from the faucet" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y13CBvjHZhOA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y13CBvjHZhOA.npy", "labels": "/m/012f08,/m/07yv9,/m/0k4j,/t/dd00134", "caption": "A motor vehicle engine is running while race cars are passing by" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/YwSHzVxdMiTo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YwSHzVxdMiTo.npy", "labels": "/m/09x0r,/t/dd00018", "caption": "A pig squeals and men speak" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YK2kIOBeCfuo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YK2kIOBeCfuo.npy", "labels": "/m/028ght,/m/09x0r", "caption": "A crowd of people laughing and cheering as a man speaks on a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/Ygbi6MxPf3hA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ygbi6MxPf3hA.npy", "labels": "/m/034srq,/m/03m9d0z,/m/05kq4,/t/dd00092", "caption": "Gusts of wind blowing followed by harp music then more wind blowing and birds chirping in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/YhGWarNR6xmg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YhGWarNR6xmg.npy", "labels": "/m/06wzb,/m/07rjwbb", "caption": "Continuous hissing at varying levels" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YcFHFVGOtp6g.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YcFHFVGOtp6g.npy", "labels": "/m/09ld4,/m/09x0r", "caption": "Buzzing continues getting louder than softer as people talk" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YTWOgvDaDqlU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YTWOgvDaDqlU.npy", "labels": "/m/083vt", "caption": "High pitched metal whirring is followed by a large motor operating and low-pitched whirring and grinding of wood" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YXWw7ZM1c_QA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YXWw7ZM1c_QA.npy", "labels": "/m/07qjznl,/m/09x0r", "caption": "Sounds of a mechanical clock" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part0/Y-mb4Fw4Z0xg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y-mb4Fw4Z0xg.npy", "labels": "/m/012f08,/m/07yv9,/m/09x0r,/m/0k4j,/t/dd00134", "caption": "Humming of an engine with wind blowing and people speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YJhGp7HmRQxg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YJhGp7HmRQxg.npy", "labels": "/m/03k3r,/m/07q5rw0,/m/09x0r,/m/0jbk", "caption": "Humming of engines followed by the neigh of a horse and birds chirping in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/YyVjivgsU2aA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YyVjivgsU2aA.npy", "labels": "/m/012f08,/m/07rknqz,/m/07yv9,/m/09x0r,/m/0h9mv,/m/0k4j,/m/0ltv", "caption": "Humming and accelerating of a car engine with squealing tires and people speaking faintly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9b6RqajfAmw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9b6RqajfAmw.npy", "labels": "/m/015p6,/m/0h0rv,/t/dd00129", "caption": "Pigeons cooing and flapping their wings" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/Ynq0BF9zGkzg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ynq0BF9zGkzg.npy", "labels": "/m/09x0r,/t/dd00018", "caption": "A person screaming followed glass crashing then two men communicating with each other as seagulls squawk in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part9/Y8nUqSYC66mI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y8nUqSYC66mI.npy", "labels": "/m/0j6m2", "caption": "Applause together with speech and hollering with running water in our he background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YYH4qi8Ul6v0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YYH4qi8Ul6v0.npy", "labels": "/m/09x0r,/t/dd00002", "caption": "A man talking as an infant is crying followed by a man humming" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part19/YMPLZUg89y5U.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YMPLZUg89y5U.npy", "labels": "/m/07r04,/m/07yv9,/m/09x0r", "caption": "A large truck engine running idle as a man is talking while wind blows heavily into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/Yjid4t-FzUn0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yjid4t-FzUn0.npy", "labels": "/m/03fwl,/m/07s04w4,/m/09x0r", "caption": "A person speaks and a goat bleats" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/YztSjcZNUY7A.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YztSjcZNUY7A.npy", "labels": "/m/09x0r,/t/dd00002", "caption": "A baby crying followed by the voice of a woman" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9z8XIRyUq9Q.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9z8XIRyUq9Q.npy", "labels": "/m/02qldy,/m/02zsn,/m/09x0r", "caption": "Older woman speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y14izd_i3ryE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y14izd_i3ryE.npy", "labels": "/m/07rv9rh,/m/09x0r,/m/0jbk", "caption": "Wind rushes by, a motorcycle sounds, a man speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part27/Y_z-bidQYVao.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y_z-bidQYVao.npy", "labels": "/m/07qjznl,/m/09x0r", "caption": "Wooing with some humming" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/Ye6jSpvTvfJ0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ye6jSpvTvfJ0.npy", "labels": "/m/06mb1,/m/0cj0r", "caption": "It is raining with strong wind sounds" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part9/Y8DQfjqPCTI8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y8DQfjqPCTI8.npy", "labels": "/m/01h3n,/m/03vt0,/m/0h2mp", "caption": "Men speaking with insects buzzing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part15/YFlk-X0gwjF4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YFlk-X0gwjF4.npy", "labels": "/m/020bb7,/m/09x0r,/t/dd00129", "caption": "Birds chirp in the distance and a man speaks, and walks through the grass" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y40cuHrYfaqA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y40cuHrYfaqA.npy", "labels": "/m/068hy,/m/07rc7d9,/m/09x0r,/m/0bt9lr,/m/0jbk,/t/dd00136", "caption": "Dogs are barking and growling, and an adult male speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part19/YMtK8L8gXRrI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YMtK8L8gXRrI.npy", "labels": "/m/01jt3m", "caption": "Footsteps shuffling followed by a cat meowing then a toilet flushing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YsbW7XwwUtSU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YsbW7XwwUtSU.npy", "labels": "/m/07qjznl,/m/07qjznt", "caption": "A clock chimes and ticktocks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/YxnVqvc7N7Po.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YxnVqvc7N7Po.npy", "labels": "/m/07cx4,/m/09x0r", "caption": "An adult female speaks through a phone, an adult male speaks, the adult female speaks again, the adult male speaks, the adult female speaks once more, a click occurs, and then a phone rings" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YJHhEjsAkZoc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YJHhEjsAkZoc.npy", "labels": "/m/01g50p,/m/0284vy3,/m/06d_3,/m/07jdr,/m/07rwm0c", "caption": "A train honks for a long time as it drives by" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YEp72tyiL3as.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YEp72tyiL3as.npy", "labels": "/m/0ngt1", "caption": "Thunder pounds as rain downpours and then fades away" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YlfO471Rn61k.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YlfO471Rn61k.npy", "labels": "/m/06wzb,/m/07rjwbb", "caption": "Steam hisses while machinery runs" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/YfsBR7e_X_0Y.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YfsBR7e_X_0Y.npy", "labels": "/m/09x0r,/m/0ytgt,/t/dd00125", "caption": "A young kid speaking with a series of slapping on a hard surface as a baby is yelling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y7D7xgd4WJ50.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y7D7xgd4WJ50.npy", "labels": "/m/0395lw", "caption": "A bell ringing repeatedly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YR91bUbtKrRs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YR91bUbtKrRs.npy", "labels": "/m/09x0r,/t/dd00002", "caption": "A woman and a boy speaking in a foreign language then a baby cries and the boy laughs." }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y1j5NMuq1X30.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1j5NMuq1X30.npy", "labels": "/m/07qlf79", "caption": "A motor engine humming as liquid sprays and music plays in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part24/YVkbp8VmL3pM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YVkbp8VmL3pM.npy", "labels": "/m/0463cq4", "caption": "An infant crying as cloth shuffles" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YbIV3bJZpkgA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YbIV3bJZpkgA.npy", "labels": "/m/07yv9,/m/09ct_", "caption": "A helicopter flying in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part24/YVkbp8VmL3pM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YVkbp8VmL3pM.npy", "labels": "/m/0463cq4", "caption": "An infant crying as fabric shuffles" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YEbpOXac13yo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YEbpOXac13yo.npy", "labels": "/m/01bjv,/m/07yv9,/m/09x0r", "caption": "A man talking followed by another man talking in the background as a vehicle drives and other vehicles pass by" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YqakN0JNbpcU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YqakN0JNbpcU.npy", "labels": "/m/01h3n,/m/03vt0,/m/09x0r", "caption": "A man talking followed by wind blowing into a microphone while insects buzz" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YBoe3MeEpn_c.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBoe3MeEpn_c.npy", "labels": "/m/04brg2,/m/09x0r,/t/dd00125", "caption": "A woman speaking click of moving dishes followed by spraying of a can" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/YeYbFtxZmKL4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YeYbFtxZmKL4.npy", "labels": "/m/03k3r,/m/09x0r,/m/0jbk", "caption": "Plastic clanking as a horse trots and a woman talks in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YYEYeQ0lIkBQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YYEYeQ0lIkBQ.npy", "labels": "/m/015p6,/m/09ddx,/m/09x0r", "caption": "A man shouting and hollering as ducks quack and chirp while wind blows into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/YpuZL08fzpXk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YpuZL08fzpXk.npy", "labels": "/m/032s66,/m/04zjc", "caption": "A speech and gunfire followed by a gun being loaded" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/Yi1u_2eZYYlE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yi1u_2eZYYlE.npy", "labels": "/m/07pb8fc,/m/07r04,/m/07yv9", "caption": "A engine running briefly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/YeYbFtxZmKL4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YeYbFtxZmKL4.npy", "labels": "/m/03k3r,/m/09x0r,/m/0jbk", "caption": "An animal is moving with clip-clop noise with speech in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YFeHndzYAUkg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YFeHndzYAUkg.npy", "labels": "/m/01d380,/m/07k1x,/m/0_ksk", "caption": "Power tool motor whining and drilling ending in a squeal" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part27/Y_z-bidQYVao.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y_z-bidQYVao.npy", "labels": "/m/07qjznl,/m/09x0r", "caption": "A man vocalizing a high-pitch sound and then speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YETb9EIQOMAA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YETb9EIQOMAA.npy", "labels": "/m/02qldy,/m/02zsn,/m/09x0r", "caption": "A woman is speaking with low speech from a crowd" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4Ujigme2IxY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4Ujigme2IxY.npy", "labels": "/m/01jwx6", "caption": "An engine running and screeching with rustling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YU3CAjsm1sec.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YU3CAjsm1sec.npy", "labels": "/m/01yrx,/m/068hy,/m/07qrkrw,/m/0jbk", "caption": "Cats meowing loudly and then a male voice" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YEvZ3jOMYWxk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YEvZ3jOMYWxk.npy", "labels": "/m/02qldy,/m/02zsn,/m/09x0r", "caption": "A woman delivering a speech" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YD96OO7nYYsg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YD96OO7nYYsg.npy", "labels": "/m/07q2z82,/m/07yv9,/m/0k4j", "caption": "A muffled vehicle engine accelerating then revving as vehicles pass by" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YAMQei29haCw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YAMQei29haCw.npy", "labels": "/m/01d380", "caption": "Buzzing and humming of a motor with a man speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YAI1OweEW8C0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YAI1OweEW8C0.npy", "labels": "/m/06mb1,/m/07r10fb,/m/0jb2l,/m/0ngt1", "caption": "Rain lightly falling while water trickles and splashes followed by wind blowing into a microphone then thunder roaring in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YEY4p0_NJVQs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YEY4p0_NJVQs.npy", "labels": "/m/02qldy,/m/02zsn,/m/09x0r", "caption": "A woman speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YKJKHDKKW3XU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YKJKHDKKW3XU.npy", "labels": "/m/07swgks", "caption": "A liquid gurgles as it drains" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y14ekd4nkpwc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y14ekd4nkpwc.npy", "labels": "/t/dd00002", "caption": "An infant makes babbling noise followed by crying" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YP12nvSpKXcs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YP12nvSpKXcs.npy", "labels": "/m/01h3n,/m/03vt0,/m/0h2mp", "caption": "Insects buzz nearby with distant birds chirping followed by rustling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YZTYAQBnU4GM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YZTYAQBnU4GM.npy", "labels": "/m/015p6,/m/068hy,/m/07pggtn", "caption": "Several small birds chirping with faint rustling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y7XXSOzDQ2z0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y7XXSOzDQ2z0.npy", "labels": "/m/07yv9,/m/0h9mv,/m/0k4j,/m/0ltv", "caption": "An engine throttles and clanks and then suddenly accelerates off into the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YC_ga5m6nOhI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YC_ga5m6nOhI.npy", "labels": "/m/06hck5,/m/06wzb,/m/07rjwbb", "caption": "A train passes with a honking horn and rustling tracks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YYQSuFyFm3Lc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YYQSuFyFm3Lc.npy", "labels": "/m/01g50p,/m/0284vy3,/m/06d_3,/m/07jdr", "caption": "A train running on a railroad track followed by a vehicle door closing and a man talking while a train horn is blowing and railroad crossing signals are ringing in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YZTYAQBnU4GM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YZTYAQBnU4GM.npy", "labels": "/m/015p6,/m/068hy,/m/07pggtn", "caption": "Birds chirping as well as some clanking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YBLMWD6fxhpo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBLMWD6fxhpo.npy", "labels": "/t/dd00018", "caption": "A walking in the grass and a pig oink sound" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part4/Y2RjqBRzmxaM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y2RjqBRzmxaM.npy", "labels": "/m/06mb1,/m/07r10fb,/t/dd00038", "caption": "Females voice narrating a scene as music is playing and rain drops are falling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YD9GHUPGWsV0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YD9GHUPGWsV0.npy", "labels": "/m/07bgp,/m/07q0h5t,/m/09x0r", "caption": "Sheep bleat and a woman speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part1/Y-nQHwrRLfc0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y-nQHwrRLfc0.npy", "labels": "/m/02mk9,/m/07pb8fc,/t/dd00066", "caption": "A mid-size motor is idling, vibrating and humming" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y1PvMtRIlZNI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1PvMtRIlZNI.npy", "labels": "/m/07swgks", "caption": "Water splashes and gurgles" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4SZ7JXDCNps.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4SZ7JXDCNps.npy", "labels": "/m/07yv9,/m/0k4j,/m/0ltv", "caption": "Plastic rattling as a vehicle engine accelerates" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YAbplcXwXnvE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YAbplcXwXnvE.npy", "labels": "/m/09x0r,/t/dd00112", "caption": "A young girl speaks with some crinkling plastic" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YmaVYiednkSg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YmaVYiednkSg.npy", "labels": "/m/07qlf79,/m/09x0r", "caption": "A man speaking followed by air spraying while vibration rumbling grows louder" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part0/Y-JP1GqPEKtw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y-JP1GqPEKtw.npy", "labels": "/m/07k1x,/m/083vt,/m/09x0r", "caption": "A man talking while a saw is running" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/YdZDgJzGtLLU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YdZDgJzGtLLU.npy", "labels": "/m/07pqc89", "caption": "Water flows and splashes" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YSoO1HhaEc9Q.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YSoO1HhaEc9Q.npy", "labels": "/m/09x0r,/t/dd00018", "caption": "Humming and vibrating with a man speaking and small oinks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YtmLAXm1WlnE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YtmLAXm1WlnE.npy", "labels": "/m/01h3n,/m/03vt0,/m/0h2mp", "caption": "A woman speaks with nearby insects buzzing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part15/YFi4-IqJo2xQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YFi4-IqJo2xQ.npy", "labels": "/m/02mk9,/m/07rqsjt,/m/07yv9,/m/0k4j", "caption": "An engine hums and rattles as it accelerates" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3xDZ-kdGE3o.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3xDZ-kdGE3o.npy", "labels": "/m/01jt3m,/m/0838f", "caption": "Metal rattling followed by a door slamming shut then plastic clacking proceeded by a toilet flushing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3qrVku794u0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3qrVku794u0.npy", "labels": "/m/02fs_r,/m/09x0r,/m/0fx9l", "caption": "Male speech and then a child speaks with repeated taps and a beep" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YL6rnV0oNIII.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YL6rnV0oNIII.npy", "labels": "/m/07qjznl", "caption": "A beep and clicking noise repeat." }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YqakN0JNbpcU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YqakN0JNbpcU.npy", "labels": "/m/01h3n,/m/03vt0,/m/09x0r", "caption": "A man talking followed by footsteps walking on dirt as a swarm of insects buzz and birds chirp in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YWU3qB7gf6ao.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YWU3qB7gf6ao.npy", "labels": "/m/02fs_r", "caption": "A shrill beep followed by four clicks while low voices converse in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YXf5LjaE_JQ0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YXf5LjaE_JQ0.npy", "labels": "/m/07qlf79,/m/09x0r", "caption": "A man talking as plastic rattles while a truck engine runs idle and vehicles drive by in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YBrPFQDr99Gg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBrPFQDr99Gg.npy", "labels": "/m/02qldy,/m/05zppz,/m/09x0r", "caption": "A crowd applauds and whistles, then an adult male speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y7bO0AJI-ihs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y7bO0AJI-ihs.npy", "labels": "/m/03k3r,/m/07rv9rh,/m/0jbk", "caption": "A couple of horses are slowly walking in unison" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YLP_DzNUkAKY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YLP_DzNUkAKY.npy", "labels": "/m/06wzb,/m/07rjwbb", "caption": "People speaking faintly with some humming and a hydraulic hiss" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YawxrHOpt-sE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YawxrHOpt-sE.npy", "labels": "/m/03fwl,/m/09x0r,/m/0ch8v,/m/0jbk", "caption": "A goat screams as people communicate" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y1_z6NcidGzM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1_z6NcidGzM.npy", "labels": "/m/07swgks,/m/09x0r,/m/0j6m2", "caption": "Water splashes with people speaking in the distance and a faint whistle" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YAizmnCDlXos.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YAizmnCDlXos.npy", "labels": "/m/07qjznl,/m/07qjznt", "caption": "A high pitched bell ringing continuously" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/Ygf6H_MWCqjw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ygf6H_MWCqjw.npy", "labels": "/m/015p6,/m/09ddx", "caption": "A duck quacking followed by plastic camera muffling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YajheseWZmmU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YajheseWZmmU.npy", "labels": "/m/01yrx,/m/07qrkrw,/m/0jbk", "caption": "A cat meowing as a person is kissing aloud followed by a man giggling during light audio static" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YHxZADVzNIqs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YHxZADVzNIqs.npy", "labels": "/m/015p6,/m/020bb7,/m/07pggtn", "caption": "Water trickles as birds chirp then drums begin to play" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3Sml1wHcuxo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3Sml1wHcuxo.npy", "labels": "/m/01g50p,/m/0284vy3,/m/06d_3,/m/07jdr,/m/07rwm0c", "caption": "A train horn blowing as a train runs on railroad tracks while a train signal beeps in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/Yhrv6fwnmBkY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yhrv6fwnmBkY.npy", "labels": "/m/068hy,/m/07rc7d9,/m/09b5t,/m/09x0r,/m/0bt9lr,/m/0jbk,/t/dd00136", "caption": "A dog whimpers then a male voice laughs and talks as the dog starts to bark shortly after" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YZ3wDry8nnJs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YZ3wDry8nnJs.npy", "labels": "/m/09x0r,/m/0ytgt,/t/dd00125", "caption": "Splashing water followed by a girl speaking then scraping and spitting" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y59VP93Tzjmg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y59VP93Tzjmg.npy", "labels": "/m/01g50p,/m/0284vy3,/m/06d_3,/m/07jdr", "caption": "A train horn blows several times with leaves rustling in the wind" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YkLYCjD6vWI4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YkLYCjD6vWI4.npy", "labels": "/m/06wzb,/m/07rjwbb", "caption": "A steam engine hissing while puffing steam as wind blows into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/Yg6CY7qvu81k.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yg6CY7qvu81k.npy", "labels": "/m/07p9k1k", "caption": "Music plays followed by a man speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part1/Y0a9wVat2PWk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y0a9wVat2PWk.npy", "labels": "/m/0284vy3,/m/07jdr,/m/07yv9", "caption": "Train horn sounds as it moves along tracks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4fz0-Kx2oNs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4fz0-Kx2oNs.npy", "labels": "/m/0dxrf", "caption": "Loud, continuous sizzling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4ftDFi4684Y.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4ftDFi4684Y.npy", "labels": "/m/07qjznl", "caption": "Rhythmic tick took" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y1FNJbN-eHY4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1FNJbN-eHY4.npy", "labels": "/m/03q5_w,/m/09x0r", "caption": "A crowd of people talking followed by two girls belching with a group of girls laughing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part7/Y5rh5-MCjqq8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y5rh5-MCjqq8.npy", "labels": "/m/01d3sd", "caption": "Snoring and heavy breathing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YsVYTOURVsQ0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YsVYTOURVsQ0.npy", "labels": "/m/07pqc89,/m/09x0r", "caption": "A man talking as water streams in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YObWjGBJF_94.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YObWjGBJF_94.npy", "labels": "/m/02jz0l,/m/07ptzwd", "caption": "A machine is in use and making whoosh and vibrating sounds" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/Yjs4dr5JusdM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yjs4dr5JusdM.npy", "labels": "/m/07cx4,/m/09x0r", "caption": "A woman and a man speaking through a telephone speaker" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YEUZaxaWqhwg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YEUZaxaWqhwg.npy", "labels": "/m/07yv9,/m/0cmf2,/m/0k5j", "caption": "Airplane moving down a runway with muddled speech in background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/Yne2DpKCIr4Y.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yne2DpKCIr4Y.npy", "labels": "/m/034srq,/m/03m9d0z,/m/05kq4,/t/dd00092", "caption": "Wind blows and waves crash with distant humming" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YIvg_q4t-3w0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YIvg_q4t-3w0.npy", "labels": "/m/02dgv,/m/09x0r", "caption": "Female speech followed by a thumping noise" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YawxrHOpt-sE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YawxrHOpt-sE.npy", "labels": "/m/03fwl,/m/09x0r,/m/0ch8v,/m/0jbk", "caption": "A goat yelling as a crowd of people talk and vehicles drive by in the background followed by people laughing and someone clicking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YLP_DzNUkAKY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YLP_DzNUkAKY.npy", "labels": "/m/06wzb,/m/07rjwbb", "caption": "A muffled steam engine running as a crowd of people talk followed by muffled steam hissing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part38/Yv7BaYF0kagM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yv7BaYF0kagM.npy", "labels": "/m/07yv9,/m/0k5j,/t/dd00129", "caption": "Airplane engine idles continuously" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YsTMKled6Q1M.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YsTMKled6Q1M.npy", "labels": "/m/015p6,/m/0h0rv,/t/dd00129", "caption": "A person whistling followed by pigeons cooing and bird wings flapping as birds chirp in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YBvw2gv1fcZw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBvw2gv1fcZw.npy", "labels": "/m/03q5_w,/m/09x0r", "caption": "Girl speaks then a loud burp followed by girls laughing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9z8XIRyUq9Q.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9z8XIRyUq9Q.npy", "labels": "/m/02qldy,/m/02zsn,/m/09x0r", "caption": "Woman speaking with a southern drawl" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part19/YMTaLknnq4wc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YMTaLknnq4wc.npy", "labels": "/m/01w250", "caption": "Whistling occurs, followed by an adult female singing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4lv9aLXtud0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4lv9aLXtud0.npy", "labels": "/m/03q5_w,/m/09x0r,/t/dd00125", "caption": "A man yelling before and after a person belching" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YlYhwCRX2wNc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YlYhwCRX2wNc.npy", "labels": "/m/04brg2,/m/09x0r", "caption": "A woman speaks with dishes clanging and water running in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part15/YH7rd9bZtbgc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YH7rd9bZtbgc.npy", "labels": "/m/0395lw", "caption": "A bell sounds its horn" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/Yy3-M1sonh3M.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yy3-M1sonh3M.npy", "labels": "/m/01jt3m", "caption": "Slight rustling and thumping occur, followed by a flush of water with splashing and gurgling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/YjOYvIISk--4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YjOYvIISk--4.npy", "labels": "/m/0130jx,/m/02jz0l,/m/0838f", "caption": "A man is speaking as tap water runs" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YAMQei29haCw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YAMQei29haCw.npy", "labels": "/m/01d380", "caption": "A drill running and a man vocalizing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YEY4p0_NJVQs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YEY4p0_NJVQs.npy", "labels": "/m/02qldy,/m/02zsn,/m/09x0r", "caption": "A woman speaking on a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/Yg6CY7qvu81k.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yg6CY7qvu81k.npy", "labels": "/m/07p9k1k", "caption": "Music and a male speech" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/Ya_Rjlu50TfA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ya_Rjlu50TfA.npy", "labels": "/m/01d3sd,/m/07q0yl5,/m/09x0r", "caption": "A person snoring repetitively" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YFKaJsvcyHTk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YFKaJsvcyHTk.npy", "labels": "/t/dd00002", "caption": "A baby crying loudly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YK_Vre_-4KqU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YK_Vre_-4KqU.npy", "labels": "/m/07yv9,/m/0k5j,/t/dd00129", "caption": "An airplane engine revving then running" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9dLLsZVRSZI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9dLLsZVRSZI.npy", "labels": "/m/07r04,/m/07yv9,/t/dd00129", "caption": "Humming and rustling from a large engine followed by two honks of a horn" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y0yETgW44MZU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y0yETgW44MZU.npy", "labels": "/m/01g50p,/m/0284vy3,/m/04zmvq,/m/06d_3,/m/07jdr,/m/07yv9,/t/dd00129", "caption": "A honking horn from an oncoming train" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/Yoklu5ZJD_2U.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yoklu5ZJD_2U.npy", "labels": "/m/015p6,/m/068hy,/m/07pggtn", "caption": "Birds chirping repeatedly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/Yjj2RyNDj7no.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yjj2RyNDj7no.npy", "labels": "/m/01h3n,/m/03vt0,/m/0h2mp", "caption": "Insects are buzzing, and birds are chirping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3ejndVEAcmQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3ejndVEAcmQ.npy", "labels": "/m/01yrx,/m/068hy,/m/07qrkrw,/m/07r81j2,/m/0jbk", "caption": "Cats meows and hisses and some thuds" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YnaPgJvWTIY4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YnaPgJvWTIY4.npy", "labels": "/m/04_sv,/m/07yv9,/t/dd00066,/t/dd00128", "caption": "A motorcycle engine idles and then shifts gears" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part0/Y-aYumc8KoXg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y-aYumc8KoXg.npy", "labels": "/m/07yv9,/m/0912c9,/m/0k4j", "caption": "A distant horn ring as a vehicle approaches" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part4/Y2sZhC_mKeic.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y2sZhC_mKeic.npy", "labels": "/m/01yrx,/m/068hy,/m/07qrkrw", "caption": "A cat meows as he enters the room and something is dropped with a big thump" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YBOB65Nd0pXo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBOB65Nd0pXo.npy", "labels": "/m/02l6bg,/m/07yv9,/m/09ct_", "caption": "A helicopter engine running idle as wind blows heavily into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YbA5zPFSFZAA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YbA5zPFSFZAA.npy", "labels": "/m/07rqsjt", "caption": "Digital static and beeps" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YOt0bN_hz2ec.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YOt0bN_hz2ec.npy", "labels": "/m/0195fx,/m/01g50p,/m/0284vy3,/m/06d_3,/m/07jdr,/m/07rwm0c", "caption": "A train horn blowing followed by a train running on railroad tracks passes by" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/Yjid4t-FzUn0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yjid4t-FzUn0.npy", "labels": "/m/03fwl,/m/07s04w4,/m/09x0r", "caption": "A man is talking and snickering followed by a goat bleating" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YkLYCjD6vWI4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YkLYCjD6vWI4.npy", "labels": "/m/06wzb,/m/07rjwbb", "caption": "A loud hissing and chugging growing louder" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y7XUt6sQS7nM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y7XUt6sQS7nM.npy", "labels": "/m/07bgp,/m/07q0h5t,/m/09x0r", "caption": "Several animals are bleating and the wind is blowing, while a group of people talk in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/YoN0IcZaHD_8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YoN0IcZaHD_8.npy", "labels": "/m/01d380,/m/07k1x,/m/083vt,/m/09x0r,/t/dd00125", "caption": "A man talking followed by a power tool drilling then footsteps shuffling and a man speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/Ydkiwn2FdDVw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ydkiwn2FdDVw.npy", "labels": "/m/09ddx,/m/09x0r", "caption": "A female voice and a duck quacking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9hxFqltp3xw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9hxFqltp3xw.npy", "labels": "/m/07qlf79,/m/09x0r", "caption": "A woman vocally demonstrating something, followed by spraying" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y1IoHRTUp86c.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1IoHRTUp86c.npy", "labels": "/m/07yv9,/m/0k5j,/t/dd00129", "caption": "A woman speaks briefly over a radio with an aircraft engine running" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YCvNAwby6Xos.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YCvNAwby6Xos.npy", "labels": "/m/09x0r,/m/0llzx,/t/dd00125", "caption": "A man talking as a sewing machine rapidly operates and hums" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YPWjEfOkb6ro.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YPWjEfOkb6ro.npy", "labels": "/m/07swgks,/m/09x0r", "caption": "Water trickling and dripping as a crowd of people talk in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/YdP5DbAzTl5M.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YdP5DbAzTl5M.npy", "labels": "/m/019jd,/m/02rlv9,/m/07yv9,/m/09x0r", "caption": "A motorboat engine running idle as wind blows into a microphone while a man talks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YcK2kSVR1d2o.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YcK2kSVR1d2o.npy", "labels": "/m/07qsvvw,/m/0g6b5", "caption": "Clicking and rustling followed by explosions and several pops" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YJC2ZrXzCX4Y.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YJC2ZrXzCX4Y.npy", "labels": "/m/01d3sd,/m/09x0r", "caption": "A group of children talking in the background followed by a woman then a man talking as a person is snoring" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YPuLuZ_TXv-0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YPuLuZ_TXv-0.npy", "labels": "/m/0316dw,/m/0c2wf", "caption": "Typing on a typewriter" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4_Cak7gvly4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4_Cak7gvly4.npy", "labels": "/m/07rqsjt", "caption": "A series of whooshes as music plays and a crowd of people talk in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YWOywdRmySs0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YWOywdRmySs0.npy", "labels": "/m/09x0r,/t/dd00112", "caption": "A man speaks with some light crinkling of plastic" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YYflmW68gL4E.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YYflmW68gL4E.npy", "labels": "/m/03q5_w,/m/09x0r", "caption": "A woman laughs and talks after burping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part19/YNX0gR9Eebp0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YNX0gR9Eebp0.npy", "labels": "/m/03dnzn,/m/09x0r,/m/0ytgt", "caption": "Water splashing items floating in the water something doping in to the water women voice" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YbygBWUkpaC8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YbygBWUkpaC8.npy", "labels": "/m/020bb7,/m/07pggtn,/m/09x0r,/m/0jbk,/t/dd00129", "caption": "A man talking as another man speaks in the background followed by birds chirping and leaves rustling while wind blows into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YlgwpIImXCWA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YlgwpIImXCWA.npy", "labels": "/m/083vt,/m/09x0r,/t/dd00125", "caption": "A man talking followed by wood being sawed followed by paper shuffling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/Ygf6H_MWCqjw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ygf6H_MWCqjw.npy", "labels": "/m/015p6,/m/09ddx", "caption": "Ducks quack as a stream burbles and low speech in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YS_3aeOvniZc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YS_3aeOvniZc.npy", "labels": "/m/07yv9,/m/0k4j,/m/0ltv", "caption": "Car going fast with changing gear" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YtIM-H2rdq8U.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YtIM-H2rdq8U.npy", "labels": "/m/032s66", "caption": "Clicks followed by gunshots and breathing then some speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YnLtNjMimLE0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YnLtNjMimLE0.npy", "labels": "/m/07pqc89,/m/0838f", "caption": "Water trickling and lightly splashing followed by an animal hooting in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YLF6x7B0Ppvo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YLF6x7B0Ppvo.npy", "labels": "/m/07yv9,/m/0k4j,/m/0ltv", "caption": "A race car races, and the engine accelerates" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/YeJCaRgf1M20.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YeJCaRgf1M20.npy", "labels": "/m/07qjznl", "caption": "A bell ringing followed by a camera muffling then plastic scrapping on a wooden surface proceeded by a clock ticking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/Yc0IggDOisOo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yc0IggDOisOo.npy", "labels": "/m/0395lw,/m/09x0r", "caption": "Bells ringing with voices in background and wind blowing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YYqYCDis3EUA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YYqYCDis3EUA.npy", "labels": "/m/01h3n,/m/03vt0,/m/0h2mp", "caption": "A swarm of insects buzzing as birds chirp in the background while wind blows into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YCBwXKOpJY_o.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YCBwXKOpJY_o.npy", "labels": "/m/01h8n0,/m/02zsn,/m/09x0r,/m/0ytgt", "caption": "A woman talking followed by a kid talking while birds chirp in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part4/Y2bq2lc3DLwM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y2bq2lc3DLwM.npy", "labels": "/m/07yv9,/m/09x0r,/m/0k4j,/t/dd00134", "caption": "A man is speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y7RMpCCkQks0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y7RMpCCkQks0.npy", "labels": "/m/07rjwbb", "caption": "Repeated ripping occurs, then sharp tapping in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part0/Y-Sz4z0QwEuM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y-Sz4z0QwEuM.npy", "labels": "/m/03q5_w", "caption": "Burping, belching" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YFJkvAMLmejY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YFJkvAMLmejY.npy", "labels": "/m/0912c9,/m/09x0r,/t/dd00125", "caption": "A young man and a girl talking followed by a horn honking then a group of people laughing and a person clapping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/Yi6MQCm58zlY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yi6MQCm58zlY.npy", "labels": "/m/020bb7,/m/068hy,/m/0jbk", "caption": "Screeching and male speech" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part9/Y8BPTQO_cx7E.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y8BPTQO_cx7E.npy", "labels": "/m/028ght", "caption": "A man is speaking followed by applause" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YENTi8Sn4vdM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YENTi8Sn4vdM.npy", "labels": "/m/0j6m2", "caption": "A child and a women speaking with water running in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YF-47fRplQEc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YF-47fRplQEc.npy", "labels": "/m/07bgp,/m/07q0h5t,/m/09x0r", "caption": "Goats bleat followed by female speech and a younger female speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YtjCNwdOUiGc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YtjCNwdOUiGc.npy", "labels": "/m/07qv_d5,/m/07yv9,/m/0912c9", "caption": "A bus engine running followed by a vehicle horn honking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4sb9jN0SgTM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4sb9jN0SgTM.npy", "labels": "/m/02mk9,/m/07pb8fc,/m/07q2z82,/m/07yv9,/m/09x0r,/m/0k4j,/t/dd00066", "caption": "An engine revving and then male speech" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YbIV3bJZpkgA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YbIV3bJZpkgA.npy", "labels": "/m/07yv9,/m/09ct_", "caption": "A helicopter flying in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YNeWW30WZjPc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YNeWW30WZjPc.npy", "labels": "/m/01z5f,/m/05tny_,/m/068hy,/m/07rc7d9,/m/0bt9lr,/m/0jbk,/t/dd00125", "caption": "A dog growling and barking repeatedly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/YeqcdsdLz954.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YeqcdsdLz954.npy", "labels": "/m/014zdl,/m/07qsvvw", "caption": "An explosion sounds with bursting noises" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part4/Y2a6GNu6uCDE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y2a6GNu6uCDE.npy", "labels": "/m/02qldy,/m/02zsn,/m/09x0r", "caption": "A woman talking in an auditorium" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part9/Y8DLcBdC5UrE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y8DLcBdC5UrE.npy", "labels": "/m/07swgks", "caption": "White noise followed by a loud clanging then birds chirping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YRrmBGjJqlEo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YRrmBGjJqlEo.npy", "labels": "/m/0316dw", "caption": "Typing on a computer keyboard followed by a computer mouse clicking as a man sniffles before talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4SZ7JXDCNps.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4SZ7JXDCNps.npy", "labels": "/m/07yv9,/m/0k4j,/m/0ltv", "caption": "A vehicle engine accelerating and plastic rattling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/YhpDltmawxIM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YhpDltmawxIM.npy", "labels": "/m/0130jx,/m/02jz0l,/m/0838f", "caption": "Water trickling onto a metal surface and filling a container" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y1a2XWJ8NA_Q.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1a2XWJ8NA_Q.npy", "labels": "/m/019jd,/m/02rlv9,/m/07yv9,/m/09x0r", "caption": "An engine running and wind blowing with people talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4KObP7cREWw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4KObP7cREWw.npy", "labels": "/m/02mk9,/m/07yv9,/m/0k4j", "caption": "An engine revving" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YkHIe4CfaccQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YkHIe4CfaccQ.npy", "labels": "/m/03fwl,/m/068hy,/m/0ch8v,/m/0jbk", "caption": "A goat bleating" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y1Og2TJ3bXW0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1Og2TJ3bXW0.npy", "labels": "/m/07yv9,/m/0cmf2,/m/0k5j,/t/dd00128", "caption": "An aircraft engine running then slowing down with a plastic clank in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YROootH-mtEI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YROootH-mtEI.npy", "labels": "/m/0j6m2", "caption": "Water flowing down a river" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YC9NC7wJ7C3w.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YC9NC7wJ7C3w.npy", "labels": "/m/02qldy,/m/02zsn,/m/09x0r", "caption": "A female speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YXZTt1xdK8uQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YXZTt1xdK8uQ.npy", "labels": "/m/07swgks", "caption": "An engine running and water splashing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YS0SQyFXbqF8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YS0SQyFXbqF8.npy", "labels": "/m/09ld4", "caption": "An animal gurgling followed by a bell clinking as a kid yells and a man laughs then speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YQoEal_hKz4Q.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YQoEal_hKz4Q.npy", "labels": "/m/032s66,/m/04zjc", "caption": "Several rapid bursts of gunshots in the distance followed by nearby gunshots and a man speaking over a radio" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YHZ9O6sc7cLA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YHZ9O6sc7cLA.npy", "labels": "/m/05tny_,/m/07rc7d9,/m/0bt9lr", "caption": "A woman is speaking followed by a dog growling and barking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part7/Y5ORpSk5CIWc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y5ORpSk5CIWc.npy", "labels": "/m/09ct_", "caption": "A small motor is running and fades, and vibration is present" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part7/Y5OM3tJh51pE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y5OM3tJh51pE.npy", "labels": "/m/02qldy,/m/02zsn,/m/09x0r", "caption": "A woman giving a speech" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y6i5eQOpFk_U.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y6i5eQOpFk_U.npy", "labels": "/m/0130jx,/m/02jz0l,/m/0838f", "caption": "Faucet water flowing as plastic clanks and a man speaks followed by another plastic clank and a kid laughing in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9PN4gyxpH2M.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9PN4gyxpH2M.npy", "labels": "/m/09x0r,/t/dd00112", "caption": "An adult male and an adult female speak, while rustling and metal scissors cutting paper occurs" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YmJ6ZO3xEcgw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YmJ6ZO3xEcgw.npy", "labels": "/m/01hsr_", "caption": "A woman sneezing repeatedly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YAR8-MVl_Mf8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YAR8-MVl_Mf8.npy", "labels": "/m/02dgv,/m/07rjzl8,/m/09x0r", "caption": "A man yells, slams a door and then speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YAFgGoY8Ihhg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YAFgGoY8Ihhg.npy", "labels": "/m/03j1ly,/m/03kmc9,/m/04qvtq", "caption": "An emergency siren going off as wind blows heavily into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/Yc3nlaAkv9bA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yc3nlaAkv9bA.npy", "labels": "/m/03fwl,/m/068hy,/m/09x0r,/m/0ch8v,/m/0jbk", "caption": "A man talking softly followed by a goat baaing and a cow mooing in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YAbplcXwXnvE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YAbplcXwXnvE.npy", "labels": "/m/09x0r,/t/dd00112", "caption": "A young woman talking as plastic crinkles and crumples" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part9/Y8DLcBdC5UrE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y8DLcBdC5UrE.npy", "labels": "/m/07swgks", "caption": "Whirring followed by a sudden object clanking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YrtgVoZCcBw8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YrtgVoZCcBw8.npy", "labels": "/m/03fwl,/m/09x0r,/m/0jbk", "caption": "Wind noise and farm animal noises followed by a goat screaming" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/Yo7jW6Suyfbs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yo7jW6Suyfbs.npy", "labels": "/m/012f08,/m/07yv9,/m/0k4j,/m/0ltv", "caption": "Race cars are auto racing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y40cuHrYfaqA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y40cuHrYfaqA.npy", "labels": "/m/068hy,/m/07rc7d9,/m/09x0r,/m/0bt9lr,/m/0jbk,/t/dd00136", "caption": "Two dogs barking and growling followed by a man talking in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/Yne2DpKCIr4Y.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yne2DpKCIr4Y.npy", "labels": "/m/034srq,/m/03m9d0z,/m/05kq4,/t/dd00092", "caption": "Waves are crashing as the wind blows heavily" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YQ0anPAIkfBE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YQ0anPAIkfBE.npy", "labels": "/m/0463cq4,/m/09x0r,/t/dd00002,/t/dd00125", "caption": "A woman talking as an infant is crying followed by a woman laughing while a man talks through a television speaker" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part24/YVjSEIRnLAh8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YVjSEIRnLAh8.npy", "labels": "/m/09x0r,/m/0dxrf", "caption": "A woman speaks with food sizzling in a pan with some chopping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part7/Y6Nvu6EcpdE8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y6Nvu6EcpdE8.npy", "labels": "/m/07pb8fc,/m/07yv9,/m/09x0r,/t/dd00130", "caption": "A man is talking then an engine turns on" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part9/Y8F-ndyrEWJ8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y8F-ndyrEWJ8.npy", "labels": "/m/012n7d,/m/03j1ly,/m/03kmc9", "caption": "Sirens and speeding cars along with police chatter" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part1/Y0Dt-pH0pW-Y.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y0Dt-pH0pW-Y.npy", "labels": "/m/04_sv,/m/07yv9,/m/09x0r", "caption": "A motorcycle driving then accelerating as a man talks over an intercom followed by another man cheering" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YLBe33dw9ezg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YLBe33dw9ezg.npy", "labels": "/m/09ct_,/m/09x0r", "caption": "High frequency humming" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YTaQKhIRwii4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YTaQKhIRwii4.npy", "labels": "/m/028ght", "caption": "A quick repeat of applause followed by continued applause" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part0/Y-Sz4z0QwEuM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y-Sz4z0QwEuM.npy", "labels": "/m/03q5_w", "caption": "A person burps loudly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/Yy1a8PntuXYw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yy1a8PntuXYw.npy", "labels": "/m/01jt3m", "caption": "Mechanical humming followed by a click and a toilet flushing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YQTSKjweEWew.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YQTSKjweEWew.npy", "labels": "/m/03m9d0z,/m/09x0r,/t/dd00129", "caption": "Wind and rain sounds, then a man begins to talk" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part1/Y0AsXkZkqelg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y0AsXkZkqelg.npy", "labels": "/m/028ght", "caption": "Large engine running with loud exhaust" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y1nUOGZgSzZo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1nUOGZgSzZo.npy", "labels": "/m/07swgks,/m/09x0r,/m/0j6m2", "caption": "Plastic thumping as a man laughs followed by a kid speaking in the distance as water splashes and wind blows into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YXIooZl1QdM4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YXIooZl1QdM4.npy", "labels": "/m/03q5_w", "caption": "Several loud burps" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YB8rdur4aams.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YB8rdur4aams.npy", "labels": "/m/07yv9,/m/0912c9,/t/dd00128", "caption": "Rattling of an engine with wind blowing and a horn honking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part9/Y7upINC4seBw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y7upINC4seBw.npy", "labels": "/m/019jd,/m/02rlv9,/m/07yv9,/m/09x0r", "caption": "A man speaking as an idle motorboat engine runs and water trickles while wind blows into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YsTMKled6Q1M.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YsTMKled6Q1M.npy", "labels": "/m/015p6,/m/0h0rv,/t/dd00129", "caption": "Whistling with flapping wings and cooing pigeons with other birds chirping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YR4fXcbWFhJg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YR4fXcbWFhJg.npy", "labels": "/m/03k3r,/m/09x0r,/m/0ch8v,/m/0jbk,/t/dd00129", "caption": "A man speaking with wind noise and a woman speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YZ7yDwpdGelM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YZ7yDwpdGelM.npy", "labels": "/m/07pqc89,/m/09x0r", "caption": "Puncturing sound, followed by water trickling and a man speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YWU3qB7gf6ao.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YWU3qB7gf6ao.npy", "labels": "/m/02fs_r", "caption": "Digital beeping and clicks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9BGLAUSF0sk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9BGLAUSF0sk.npy", "labels": "/m/01jwx6,/m/0chx_", "caption": "Machinery running" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YljrL7Cb-jr8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YljrL7Cb-jr8.npy", "labels": "/m/07qlf79", "caption": "A power sprayer sprays surfaces" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/Yfx4r_KuW6No.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yfx4r_KuW6No.npy", "labels": "/m/09x0r,/m/0ytgt,/t/dd00126", "caption": "A young boy crying as a woman is talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YOFVzrakJhbw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YOFVzrakJhbw.npy", "labels": "/m/068hy,/m/07bgp,/m/07q0h5t,/m/0jbk", "caption": "The wind is blowing, and an adult male laughs and animals bleat" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part15/YGuizRlAQ8qQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YGuizRlAQ8qQ.npy", "labels": "/m/01d380", "caption": "A power tool drilling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YRdC8cviN6Bs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YRdC8cviN6Bs.npy", "labels": "/m/06mb1,/t/dd00038", "caption": "Light rainfall together with rustling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YArHiac57pVk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YArHiac57pVk.npy", "labels": "/m/07qjznl,/m/09x0r", "caption": "Men are communicating followed by a ticktock noise" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YOt0bN_hz2ec.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YOt0bN_hz2ec.npy", "labels": "/m/0195fx,/m/01g50p,/m/0284vy3,/m/06d_3,/m/07jdr,/m/07rwm0c", "caption": "Train horn blows followed by clickety-clack of rails" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/YyhDw7PZje3g.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YyhDw7PZje3g.npy", "labels": "/m/01h3n,/m/09x0r,/t/dd00129", "caption": "Man speaks while insects buzz" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YWOywdRmySs0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YWOywdRmySs0.npy", "labels": "/m/09x0r,/t/dd00112", "caption": "A man talking followed by paper and plastic crinkling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YalaxBd_EEUc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YalaxBd_EEUc.npy", "labels": "/m/03q5_w,/m/09x0r", "caption": "A man speaks followed by burping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YBL8ksJ0sTXk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBL8ksJ0sTXk.npy", "labels": "/m/01jwx6,/m/07pb8fc,/m/07yv9,/m/09x0r,/m/0k4j", "caption": "Ticking and humming from an idling engine followed by a man speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YKnsKf9KoNds.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YKnsKf9KoNds.npy", "labels": "/m/07cx4,/m/09x0r", "caption": "Male speech with another male speaking on the phone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y7JWHbs3gu1w.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y7JWHbs3gu1w.npy", "labels": "/m/01g50p,/m/0284vy3,/m/06d_3,/m/07jdr,/m/07rwm0c", "caption": "A train running and the horn honking and bells chiming" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YtfOIhQpYYe8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YtfOIhQpYYe8.npy", "labels": "/m/09ct_,/m/09x0r,/t/dd00129", "caption": "A helicopter is flying above while a man is talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YBGEMgl1xjac.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBGEMgl1xjac.npy", "labels": "/m/03vt0,/m/06hps,/m/09xqv", "caption": "Insects chirping and clicking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YIFRmbxWK8u0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YIFRmbxWK8u0.npy", "labels": "/m/07qjznl", "caption": "Mechanical click clacking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/YxnVqvc7N7Po.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YxnVqvc7N7Po.npy", "labels": "/m/07cx4,/m/09x0r", "caption": "Man and woman talking on phone clicking and tone when hanging up" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/YpWQeV08kYR0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YpWQeV08kYR0.npy", "labels": "/m/012n7d,/m/03j1ly,/m/03kmc9,/m/07yv9,/t/dd00128", "caption": "Emergency vehicle siren loudly then fading into the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part18/YLP_DzNUkAKY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YLP_DzNUkAKY.npy", "labels": "/m/06wzb,/m/07rjwbb", "caption": "Indiscriminate speech and then hissing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9_YfTz8cnFY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9_YfTz8cnFY.npy", "labels": "/m/06hck5,/m/06wzb,/m/07rjwbb", "caption": "A train emits the steam whistle sound with a hissing noise" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YIPfaRF76gVU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YIPfaRF76gVU.npy", "labels": "/m/012ndj,/m/03j1ly,/m/07r04,/m/07yv9,/m/09x0r", "caption": "A siren is wailing and an engine is running followed by a male voice." }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y1N_DtRpdAp8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1N_DtRpdAp8.npy", "labels": "/m/01jwx6", "caption": "An engine idling followed by the engine revving" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y7WkB6pflr6o.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y7WkB6pflr6o.npy", "labels": "/m/02qldy,/m/02zsn,/m/09x0r", "caption": "A woman speaks continuously" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YR4fXcbWFhJg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YR4fXcbWFhJg.npy", "labels": "/m/03k3r,/m/09x0r,/m/0ch8v,/m/0jbk,/t/dd00129", "caption": "Distant clip clops of horses with a man speaking and a woman screaming" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YBzHTqyX69pI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBzHTqyX69pI.npy", "labels": "/m/07pdjhy,/m/083vt", "caption": "Rubbing against wood with birds cooing and woman speaking briefly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YB-gTt3_rceQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YB-gTt3_rceQ.npy", "labels": "/m/09x0r,/m/0ytgt,/t/dd00125", "caption": "A kid talking followed by a group of people talking then a man speaking proceeded by a young girl talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y1WTSW96XP6E.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1WTSW96XP6E.npy", "labels": "/m/04_sv,/m/07yv9,/m/09x0r", "caption": "A man talking followed by a metal clack then a motorcycle engine starting up" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3hzy-FL24no.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3hzy-FL24no.npy", "labels": "/m/0j6m2", "caption": "A steady stream of water flowing as a small motor hum followed by plastic clicking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YrBUCIK8JRLg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YrBUCIK8JRLg.npy", "labels": "/m/034srq,/m/03m9d0z,/m/05kq4,/t/dd00092", "caption": "Waves breaking and some wind" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YFeHndzYAUkg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YFeHndzYAUkg.npy", "labels": "/m/01d380,/m/07k1x,/m/0_ksk", "caption": "A power tool drilling as rock music plays" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YDAN1t9ukkg0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YDAN1t9ukkg0.npy", "labels": "/m/01m2v,/m/0316dw", "caption": "Typing on a keyboard" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/Yorgwzt45ojE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yorgwzt45ojE.npy", "labels": "/m/015p6,/m/09x0r,/m/0h0rv,/t/dd00126", "caption": "A man talking as pigeons coo and bird wings flap" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y54eRRbCtPn8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y54eRRbCtPn8.npy", "labels": "/m/02qldy,/m/02zsn,/m/09x0r", "caption": "A woman speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YPYP-r0nvbFk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YPYP-r0nvbFk.npy", "labels": "/m/07bgp,/m/07q0h5t,/m/09x0r", "caption": "A man talking a sheep speaks while birds chirp in the background and wind blows into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/YdYvL6uEMl6E.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YdYvL6uEMl6E.npy", "labels": "/m/019jd,/m/02rlv9,/m/034srq,/m/03m9d0z,/m/05kq4,/t/dd00092", "caption": "An aircraft motor is operating with rhythmic whirring, then wind roars" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YtIM-H2rdq8U.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YtIM-H2rdq8U.npy", "labels": "/m/032s66", "caption": "A distorted gasping followed by footsteps walking on a hard surface and people grunting while a beating sounds in the background as a series of gunshots fire" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YrvtA7c1I4xo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YrvtA7c1I4xo.npy", "labels": "/m/07rqsjt", "caption": "Whooshing and humming with a man speaking and distant squeaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/YinSvboaSRwA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YinSvboaSRwA.npy", "labels": "/m/07k1x,/m/083vt,/m/09x0r", "caption": "A man speaking while power tools are whirring and running in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YTWOgvDaDqlU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YTWOgvDaDqlU.npy", "labels": "/m/083vt", "caption": "Wood being sawed by a machine followed by a heavy machine motor running while sawing wood" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part22/YSQHYl2Kp5ww.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YSQHYl2Kp5ww.npy", "labels": "/m/07ptfmf,/m/0dxrf", "caption": "Music then sizzle of frying food while male speaks" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part38/YuJzAf4PaExI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YuJzAf4PaExI.npy", "labels": "/m/07yv9,/m/09x0r,/m/0k5j", "caption": "Humming of an engine with some rustling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3wrdPAeqjVI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3wrdPAeqjVI.npy", "labels": "/m/083vt,/m/09x0r", "caption": "A man speaks with some high pitched ringing and some rustling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/Yir1XTdyt4IY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yir1XTdyt4IY.npy", "labels": "/m/014zdl,/m/07qsvvw,/m/09x0r", "caption": "An explosion followed by a man shouting." }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/YyRoKi7rhSRo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YyRoKi7rhSRo.npy", "labels": "/m/01jt3m,/m/0838f", "caption": "A bird tweets far away and someone flushes the toilet" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part27/Y_iUX8CibElk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y_iUX8CibElk.npy", "labels": "/m/0ngt1", "caption": "Rain falling outside" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y1PvMtRIlZNI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1PvMtRIlZNI.npy", "labels": "/m/07swgks", "caption": "Water gurgling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3RultJjvTWI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3RultJjvTWI.npy", "labels": "/m/019jd,/m/034srq,/m/03m9d0z,/t/dd00092", "caption": "People are talking and water is splashing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part27/Y_GI7meqlYZk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y_GI7meqlYZk.npy", "labels": "/m/01yrx,/m/068hy,/m/07qrkrw,/m/09x0r,/m/0jbk", "caption": "A cat is meowing, and a child is speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part7/Y63KW_EQ72yU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y63KW_EQ72yU.npy", "labels": "/m/014zdl,/m/07qsvvw", "caption": "Very loud explosions with pops and bursts of more explosions" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y0fMXnvD38zI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y0fMXnvD38zI.npy", "labels": "/m/019jd,/m/034srq,/m/03m9d0z,/m/05kq4,/t/dd00092", "caption": "Ocean waves crashing and water splashing as gusts of wind blow and seagulls squawking in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/Ypgq2KPX5_SA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ypgq2KPX5_SA.npy", "labels": "/t/dd00112", "caption": "Paper is crinkling and crumpling, and thumping occurs" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/YwNiYSYJXssA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YwNiYSYJXssA.npy", "labels": "/m/03k3r,/m/09x0r,/m/0jbk", "caption": "A young girl talking as a crowd of people talk then gasp" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3ghVB-KaU_E.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3ghVB-KaU_E.npy", "labels": "/m/07rjwbb", "caption": "Cloth scrapping then cloth shuffling as a man talks while compressed air hisses in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/Yx5AH2gW_8S4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yx5AH2gW_8S4.npy", "labels": "/m/0h0rv,/m/0jbk,/t/dd00125", "caption": "A door creaking followed by metal tapping and a wooden clack as pigeons coo" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part13/YE3Q1jfTeuWs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YE3Q1jfTeuWs.npy", "labels": "/t/dd00002", "caption": "A baby cries quickly followed by heavy breathing and rattling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9ucb5HYO8ps.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9ucb5HYO8ps.npy", "labels": "/m/03q5_w,/m/09x0r", "caption": "An inhale then a burp with girls speaking and laughing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part27/Y_z6pymOet7g.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y_z6pymOet7g.npy", "labels": "/m/01jt3m,/m/09x0r", "caption": "A man talking followed by a toilet flushing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/Yoklu5ZJD_2U.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yoklu5ZJD_2U.npy", "labels": "/m/015p6,/m/068hy,/m/07pggtn", "caption": "A bird sings followed by drumming" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part9/Y7fmOlUlwoNg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y7fmOlUlwoNg.npy", "labels": "/m/09x0r,/m/0llzx,/t/dd00127", "caption": "Clicking and screeching metal with people speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YOMGHnJV0l2U.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YOMGHnJV0l2U.npy", "labels": "/m/02p01q,/m/07pdjhy,/m/083vt", "caption": "Metal scrapping on wood followed by wood sanding then more metal scrapping against wood" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part0/Y-FW109cbv0g.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y-FW109cbv0g.npy", "labels": "/m/01hsr_,/m/09x0r", "caption": "Muffled speech followed by laughter" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YBa92IrXFvJo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBa92IrXFvJo.npy", "labels": "/m/019jd,/m/02rlv9,/m/07yv9", "caption": "An idle motorboat engine running" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4UPOUGVMlEs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4UPOUGVMlEs.npy", "labels": "/t/dd00018", "caption": "A boar snorting as dogs growl and heavily breathe while footsteps shuffle on foliage and crickets chirp in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YCefFMA3klxk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YCefFMA3klxk.npy", "labels": "/m/012f08,/m/07r04,/m/07yv9,/m/0912c9", "caption": "Humming from a truck with a blowing horn" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/YgbtcDoh0q3c.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YgbtcDoh0q3c.npy", "labels": "/m/01j3sz,/m/07s04w4,/m/09x0r", "caption": "Rustling and scratching and then laughter" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YP12nvSpKXcs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YP12nvSpKXcs.npy", "labels": "/m/01h3n,/m/03vt0,/m/0h2mp", "caption": "Insects buzzing as a bird is chirping in the distance followed by camera muffling and a person talking then sniffling as footsteps move over foliage" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YYflmW68gL4E.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YYflmW68gL4E.npy", "labels": "/m/03q5_w,/m/09x0r", "caption": "Burping followed by girls laughing and speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YtwFypUcdgRc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YtwFypUcdgRc.npy", "labels": "/m/01bjv,/m/07yv9,/m/09x0r", "caption": "A loud wind sound as a man is speaking and laughing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part0/Y-EaZ7EJJUl0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y-EaZ7EJJUl0.npy", "labels": "/m/023pjk,/m/04brg2", "caption": "Cup being set down followed a man talking and mixing something in the cup" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YBQ-r9mEHssU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBQ-r9mEHssU.npy", "labels": "/m/03k3r,/m/07rv9rh,/m/09x0r,/m/0jbk", "caption": "Running through grass and leaves, metal clinking, then a woman laughs" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part10/Y9HVgYs8OOLc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y9HVgYs8OOLc.npy", "labels": "/m/015p6,/m/09x0r,/m/0h0rv,/t/dd00125", "caption": "A male voice speaks and a bird coos and flaps its wings" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y0ury8KHQdL4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y0ury8KHQdL4.npy", "labels": "/m/01m2v,/m/0316dw,/m/09x0r", "caption": "A man speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/YzoctgurhvHE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YzoctgurhvHE.npy", "labels": "/m/012f08,/m/02dgv,/m/04gxbd,/m/07yv9", "caption": "A plastic rattling followed by a plastic hatch opening followed by plastic clanking and a vehicle engine accelerating while a man is talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/YelztUCeNQvQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YelztUCeNQvQ.npy", "labels": "/m/0195fx,/m/01g50p,/m/0284vy3,/m/06d_3,/m/07jdr", "caption": "Subway horn blows followed by the sound traveling down the rails" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YU90e2P9jy30.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YU90e2P9jy30.npy", "labels": "/m/07pqc89,/m/09x0r", "caption": "Multiple basketballs bouncing on a hard surface and shoes squeaking as a man shouts in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YkXjzsroVTtw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YkXjzsroVTtw.npy", "labels": "/m/020bb7,/m/07pggtn,/m/09x0r", "caption": "A man is speaking as birds are tweeting" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y7P6lcyeDKNI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y7P6lcyeDKNI.npy", "labels": "/m/0199g,/m/04_sv,/m/07yv9,/m/09x0r", "caption": "Rustling with rattling followed by a man speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part32/YiOCpICiu4LA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YiOCpICiu4LA.npy", "labels": "/m/01h3n,/m/03l9g,/m/03vt0,/m/0h2mp", "caption": "Birds chirp and a great number of insects buzz, an adult male speaks, and then a sharp thump occurs" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/Yy-RSojxgkDo.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yy-RSojxgkDo.npy", "labels": "/m/015p6,/m/068hy,/m/07pggtn", "caption": "Man speaking, then a bird chipping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YXPebkNzsnRI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YXPebkNzsnRI.npy", "labels": "/m/01w250,/m/09x0r", "caption": "A person whistling followed by a young girl laughing as a man talks in the background then another person whistling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/Yg5l3Bz6lWnc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yg5l3Bz6lWnc.npy", "labels": "/m/01h3n,/m/03vt0", "caption": "Insects buzz and distant birds chirp" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part15/YGGgQR7aIofY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YGGgQR7aIofY.npy", "labels": "/m/012f08,/m/01bjv,/m/07yv9", "caption": "Musical horns from an approaching vehicle with a humming engine" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part9/Y7upINC4seBw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y7upINC4seBw.npy", "labels": "/m/019jd,/m/02rlv9,/m/07yv9,/m/09x0r", "caption": "A male speaking while engine noise in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part5/Y3ue0gJM0THk.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y3ue0gJM0THk.npy", "labels": "/m/02l6bg,/m/02mk9,/m/07pb8fc,/m/07q2z82,/t/dd00066", "caption": "A motor is revving up" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part9/Y8IdCiapDYCU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y8IdCiapDYCU.npy", "labels": "/m/068hy,/m/07rc7d9,/m/0bt9lr,/m/0jbk", "caption": "People are laughing and a small dog yips" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/YpWQeV08kYR0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YpWQeV08kYR0.npy", "labels": "/m/012n7d,/m/03j1ly,/m/03kmc9,/m/07yv9,/t/dd00128", "caption": "Sirens ring as an emergency vehicle speeds past" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part15/YFlk-X0gwjF4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YFlk-X0gwjF4.npy", "labels": "/m/020bb7,/m/09x0r,/t/dd00129", "caption": "Birds are chirping, an adult male speaks in the background, and an adult male speaks in the foreground" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YsI7_ycEYzAY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YsI7_ycEYzAY.npy", "labels": "/m/07qjznl,/m/07qjznt", "caption": "A clock ticking followed by someone sniffling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part4/Y2UNuMbxz9ds.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y2UNuMbxz9ds.npy", "labels": "/m/012f08,/m/07yv9,/m/0k4j,/t/dd00134", "caption": "A vehicle engine revving up as whips smack fiberglass followed by a vehicle accelerating at a fast rate and tires skidding" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part24/YV4PLSw_WzVw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YV4PLSw_WzVw.npy", "labels": "/m/07r04,/m/07rknqz,/m/07yv9", "caption": "Tires squealing followed by an engine revving" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YlgwpIImXCWA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YlgwpIImXCWA.npy", "labels": "/m/083vt,/m/09x0r,/t/dd00125", "caption": "A man speaks during rhythmic cutting" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YZY4aGEniU_E.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YZY4aGEniU_E.npy", "labels": "/m/07p9k1k", "caption": "Food sizzles as a man speaks with music playing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part26/YYNDKuNINDOY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YYNDKuNINDOY.npy", "labels": "/m/012ndj,/m/03j1ly,/m/03kmc9", "caption": "A fire engine with a siren fading then another loud siren" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part0/Y-EaZ7EJJUl0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y-EaZ7EJJUl0.npy", "labels": "/m/023pjk,/m/04brg2", "caption": "Dishes clanking followed by metal clanking on glass several times as a man is talking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part15/YFhimNYClv40.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YFhimNYClv40.npy", "labels": "/m/012ndj,/m/03j1ly,/m/03kmc9", "caption": "A fire truck sounds the siren as it travels" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YAf4a-9rcnP0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YAf4a-9rcnP0.npy", "labels": "/m/07qsvvw", "caption": "Two popping explosions followed by footsteps running on concrete followed by compressed air spraying" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YlmPMhs-9IYE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YlmPMhs-9IYE.npy", "labels": "/m/07yv9,/m/09x0r,/m/0k4j,/m/0ltv", "caption": "Distant humming of engines with people speaking and whistling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y79XDcI6xZm0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y79XDcI6xZm0.npy", "labels": "/m/02qldy,/m/05zppz,/m/09x0r", "caption": "A man speaking on a microphone as a crowd of people chant and clap while wind blows into a microphone" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YJdFmMw0zyKA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YJdFmMw0zyKA.npy", "labels": "/m/01j3sz,/m/09x0r", "caption": "A child speaking followed by a seal howling followed by water splashing then two women laughing in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part9/Y7fmOlUlwoNg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y7fmOlUlwoNg.npy", "labels": "/m/09x0r,/m/0llzx,/t/dd00127", "caption": "A machine makes stitching sounds while people are talking in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y0rSETXszQM0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y0rSETXszQM0.npy", "labels": "/m/028v0c,/m/04_sv,/m/07yv9,/t/dd00128", "caption": "A motorcycle engine starts and then revs and accelerates" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part20/YOmmPaIAXN0s.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YOmmPaIAXN0s.npy", "labels": "/m/03k3r,/m/07rv9rh,/m/09x0r,/m/0jbk", "caption": "A man speaks with some light cracking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YkOYg4ZtKcAs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YkOYg4ZtKcAs.npy", "labels": "/m/01yrx,/m/068hy,/m/07qrkrw,/m/0jbk", "caption": "A cat purrs then meows" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part29/Ycr0GiZr0TNY.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Ycr0GiZr0TNY.npy", "labels": "/m/01j3sz,/t/dd00001", "caption": "A spray bottle hisses as two infants laugh" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part7/Y67BsqRkh-dU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y67BsqRkh-dU.npy", "labels": "/m/01jt3m,/m/0838f", "caption": "A toilet flushing as music is playing and a man is singing in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YEUZaxaWqhwg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YEUZaxaWqhwg.npy", "labels": "/m/07yv9,/m/0cmf2,/m/0k5j", "caption": "Wind blows and people speak with some rattling and hissing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YBZCEDkx37rI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBZCEDkx37rI.npy", "labels": "/m/02mk9,/m/07pb8fc,/t/dd00066,/t/dd00130", "caption": "A vehicle engine revving then running idle followed by cloth shuffling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YbJMMp6PLKqM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YbJMMp6PLKqM.npy", "labels": "/m/0463cq4,/m/09x0r,/m/0ytgt,/t/dd00125", "caption": "A baby cries and a young girl speaks briefly" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part39/YxbLW9Wt1Jsg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YxbLW9Wt1Jsg.npy", "labels": "/m/0llzx", "caption": "Machine motors operating followed by glass boinking and a series of metal clacking and shuffling" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YCMUuelJFJ7Q.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YCMUuelJFJ7Q.npy", "labels": "/m/07qjznl,/m/07qjznt", "caption": "Music plays with low ticktock sounds and a baby cries" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YC_ga5m6nOhI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YC_ga5m6nOhI.npy", "labels": "/m/06hck5,/m/06wzb,/m/07rjwbb", "caption": "A steam engine running on railroad tracks while a steam engine whistle blows several times" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part1/Y0G7rb74R-2A.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y0G7rb74R-2A.npy", "labels": "/m/02qldy,/m/05zppz,/m/09x0r", "caption": "An adult male is speaking and an audience is laughing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/Yh3UhoHIMfpw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yh3UhoHIMfpw.npy", "labels": "/m/02_41,/m/03m9d0z,/t/dd00092", "caption": "Wind blows with some nearby rustling and distant passing traffic" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/YzoxFl3pddMg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YzoxFl3pddMg.npy", "labels": "/m/09ld4", "caption": "A frog croaking as a woman talks through an intercom while water is splashing and wood clanks in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part36/YqeSl7YZAfs4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YqeSl7YZAfs4.npy", "labels": "/m/0130jx,/m/02jz0l,/m/0838f", "caption": "Faucet water pouring followed by a man talking as water gurgles down a drain" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part27/Y_AcJVyToQUQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y_AcJVyToQUQ.npy", "labels": "/m/01j3sz,/m/09x0r", "caption": "A baby laughs while a man and a woman speaks and laughs as well" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part21/YPRUfwpmYwJ8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YPRUfwpmYwJ8.npy", "labels": "/m/07qlf79,/m/09x0r", "caption": "Male speech and spraying" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part16/YHdPSebdDxe4.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YHdPSebdDxe4.npy", "labels": "/m/03q5_w", "caption": "A man is speaking followed by a beep and burping sound" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y7bO0AJI-ihs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y7bO0AJI-ihs.npy", "labels": "/m/03k3r,/m/07rv9rh,/m/0jbk", "caption": "Horse feet clopping and an engine running" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part9/Y8o-Y4QP8LWs.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y8o-Y4QP8LWs.npy", "labels": "/m/023pjk,/m/04brg2", "caption": "Pots and dishes clanking as a man talks followed by liquid pouring into a container" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YAMQei29haCw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YAMQei29haCw.npy", "labels": "/m/01d380", "caption": "A power tool drill running before turning off and on as a man is talking and wood is clanking and scrapping in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part31/YglAeihz0NAM.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YglAeihz0NAM.npy", "labels": "/m/09x0r,/m/0ytgt,/t/dd00129", "caption": "People talk in the background and the wind is blows gently, and two kids speak in the foreground" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part4/Y30D1tqNFHMc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y30D1tqNFHMc.npy", "labels": "/m/01jwx6,/m/0chx_", "caption": "An engine running and a beeping sound" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YsbW7XwwUtSU.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YsbW7XwwUtSU.npy", "labels": "/m/07qjznl,/m/07qjznt", "caption": "A ticktock noise from a bell" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part34/YmGa2JgAiKV8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YmGa2JgAiKV8.npy", "labels": "/m/07pqc89,/m/09x0r", "caption": "A young male speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part3/Y1e98HeU9Vrg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1e98HeU9Vrg.npy", "labels": "/m/034srq,/m/03m9d0z,/m/05kq4", "caption": "Close ocean waves" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YBMayJId0X1s.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBMayJId0X1s.npy", "labels": "/m/0463cq4,/m/09x0r", "caption": "A baby crying and a man speaking" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/Yyrxa6_P2I80.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Yyrxa6_P2I80.npy", "labels": "/m/015p6,/m/0h0rv,/t/dd00129", "caption": "Many small, enclosed birds chirping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YIsUG5SKWNZA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YIsUG5SKWNZA.npy", "labels": "/m/09x0r,/t/dd00002", "caption": "A woman whispers, then a baby cries in the distance. The woman called, and a man speaks." }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part19/YMvHpNzDpC6Q.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YMvHpNzDpC6Q.npy", "labels": "/m/012f08,/m/03q5_w,/m/07yv9,/m/09x0r,/m/0k4j", "caption": "A motor engine is working far away and some boys talks then suddenly a loud eructation followed by laughs" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part33/YkgjNIDmO8a8.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YkgjNIDmO8a8.npy", "labels": "/m/012ndj,/m/03j1ly,/m/03kmc9", "caption": "A ringing of a siren with passing traffic" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part6/Y4ftDFi4684Y.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y4ftDFi4684Y.npy", "labels": "/m/07qjznl", "caption": "Light rustling followed by faint ticks of a clock" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part0/Y-JP1GqPEKtw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y-JP1GqPEKtw.npy", "labels": "/m/07k1x,/m/083vt,/m/09x0r", "caption": "A man speaks while operating a power tool" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part11/YAJtNitYMa1I.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YAJtNitYMa1I.npy", "labels": "/m/07p9k1k,/m/0dxrf", "caption": "Food sizzling and oil popping" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y13CBvjHZhOA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y13CBvjHZhOA.npy", "labels": "/m/012f08,/m/07yv9,/m/0k4j,/t/dd00134", "caption": "Engine noise with other engines passing by" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part17/YKJhGuhNHToA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YKJhGuhNHToA.npy", "labels": "/m/083vt", "caption": "A few seconds of silence then a rasping sound against wood" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y6ukYSXzfEgQ.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y6ukYSXzfEgQ.npy", "labels": "/m/02jz0l,/m/0838f", "caption": "Pots bang then a faucet turns on and water flows" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part25/YXQxIXaX_7M0.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YXQxIXaX_7M0.npy", "labels": "/m/09t49,/m/09x0r", "caption": "Water flows and people speak in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part40/YzoxFl3pddMg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YzoxFl3pddMg.npy", "labels": "/m/09ld4", "caption": "A frog croaks with speech and thumping noises in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part2/Y1QNLMF-Kl_s.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y1QNLMF-Kl_s.npy", "labels": "/m/02qldy,/m/02zsn,/m/09x0r", "caption": "A woman delivering a speech" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part23/YT32kii824pA.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YT32kii824pA.npy", "labels": "/m/083vt", "caption": "A man talking as metal rattles then clanks followed by several metal objects falling over onto a hard surface" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part7/Y5t6tSW0yT40.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y5t6tSW0yT40.npy", "labels": "/m/07qlf79", "caption": "Short spraying that stops near the end" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part35/YoZaEHkfh5Eg.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YoZaEHkfh5Eg.npy", "labels": "/m/07yv9,/m/0912c9,/m/0k4j", "caption": "A series of electronic dings while a vehicle horn honks twice followed by a plastic click while a dog barks in the distance" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part8/Y7P6lcyeDKNI.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/Y7P6lcyeDKNI.npy", "labels": "/m/0199g,/m/04_sv,/m/07yv9,/m/09x0r", "caption": "A bicycle pedaling on dirt followed by a twig snapping then a man talking and laughing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part28/YalaxBd_EEUc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YalaxBd_EEUc.npy", "labels": "/m/03q5_w,/m/09x0r", "caption": "A man talking followed by a series of belches" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part37/YtNxfdAd14qE.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YtNxfdAd14qE.npy", "labels": "/m/07p9k1k", "caption": "A machine makes sizzling noise with a television playing in the background" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part12/YBvw2gv1fcZw.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YBvw2gv1fcZw.npy", "labels": "/m/03q5_w,/m/09x0r", "caption": "A plastic clack followed by young girl talking then another a young girl burping proceeded by both girls laughing" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part30/YfrOqlk0Wm5Y.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YfrOqlk0Wm5Y.npy", "labels": "/m/07pdjhy", "caption": "A man speaks with some clicks and then loud long scrapes" }, { "wav": "zip_audios/unbalanced_train_segments/unbalanced_train_segments_part14/YF-47fRplQEc.wav", "seg_label": "/mnt/fast/nobackup/scratch4weeks/hl01486/datasets/audiocaps_segment_labels/averaged/YF-47fRplQEc.npy", "labels": "/m/07bgp,/m/07q0h5t,/m/09x0r", "caption": "Wind blowing followed by a distant goat bleating and women speaking" } ] }