First model version

.gitattributes

@@ -25,3 +25,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zstandard filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text

classifier.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a50d9024ff58d317031c9787d4c6c614d454a87a8ef32f9d36338cd3ff57adbc
+size 762555

embedding_model.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab750d5c06d713477045fa798fab5d33e959dbc0dfe4de510a9a47844c79a19a
+size 84474355

hyperparams.yaml

@@ -0,0 +1,57 @@
+pretrained_path: TalTechNLP/voxlingua107-epaca-tdnn-ce
+
+
+# Feature parameters
+n_mels: 60
+left_frames: 0
+right_frames: 0
+deltas: false
+
+# Number of speakers
+out_n_neurons: 107
+
+# Functions
+compute_features: !new:speechbrain.lobes.features.Fbank
+  n_mels: 60
+  left_frames: 0
+  right_frames: 0
+  deltas: false
+
+embedding_model: !new:speechbrain.lobes.models.ECAPA_TDNN.ECAPA_TDNN
+  input_size: 60
+  channels: [1024, 1024, 1024, 1024, 3072]
+  kernel_sizes: [5, 3, 3, 3, 1]
+  dilations: [1, 2, 3, 4, 1]
+  attention_channels: 128
+  lin_neurons: 256
+
+
+classifier: !new:speechbrain.lobes.models.Xvector.Classifier
+  input_shape: [null, null, 256]
+  activation: !name:torch.nn.LeakyReLU
+  lin_blocks: 1
+  lin_neurons: 512
+  out_neurons: !ref <out_n_neurons>
+
+
+mean_var_norm: !new:speechbrain.processing.features.InputNormalization
+  norm_type: sentence
+  std_norm: false
+
+modules:
+    compute_features: !ref <compute_features>
+    mean_var_norm: !ref <mean_var_norm>
+    embedding_model: !ref <embedding_model>
+    classifier: !ref <classifier>
+
+label_encoder: !new:speechbrain.dataio.encoder.CategoricalEncoder
+
+pretrainer: !new:speechbrain.utils.parameter_transfer.Pretrainer
+    loadables:
+        embedding_model: !ref <embedding_model>
+        classifier: !ref <classifier>
+        label_encoder: !ref <label_encoder>
+    paths:
+        embedding_model: !ref <pretrained_path>/embedding_model.ckpt
+        classifier: !ref <pretrained_path>/classifier.ckpt
+        label_encoder: !ref <pretrained_path>/label_encoder.txt

label_encoder.txt

@@ -0,0 +1,109 @@
+'ab' => 0
+'af' => 1
+'am' => 2
+'ar' => 3
+'as' => 4
+'az' => 5
+'ba' => 6
+'be' => 7
+'bg' => 8
+'bn' => 9
+'bo' => 10
+'br' => 11
+'bs' => 12
+'ca' => 13
+'ceb' => 14
+'cs' => 15
+'cy' => 16
+'da' => 17
+'de' => 18
+'el' => 19
+'en' => 20
+'eo' => 21
+'es' => 22
+'et' => 23
+'eu' => 24
+'fa' => 25
+'fi' => 26
+'fo' => 27
+'fr' => 28
+'gl' => 29
+'gn' => 30
+'gu' => 31
+'gv' => 32
+'ha' => 33
+'haw' => 34
+'hi' => 35
+'hr' => 36
+'ht' => 37
+'hu' => 38
+'hy' => 39
+'ia' => 40
+'id' => 41
+'is' => 42
+'it' => 43
+'iw' => 44
+'ja' => 45
+'jw' => 46
+'ka' => 47
+'kk' => 48
+'km' => 49
+'kn' => 50
+'ko' => 51
+'la' => 52
+'lb' => 53
+'ln' => 54
+'lo' => 55
+'lt' => 56
+'lv' => 57
+'mg' => 58
+'mi' => 59
+'mk' => 60
+'ml' => 61
+'mn' => 62
+'mr' => 63
+'ms' => 64
+'mt' => 65
+'my' => 66
+'ne' => 67
+'nl' => 68
+'nn' => 69
+'no' => 70
+'oc' => 71
+'pa' => 72
+'pl' => 73
+'ps' => 74
+'pt' => 75
+'ro' => 76
+'ru' => 77
+'sa' => 78
+'sco' => 79
+'sd' => 80
+'si' => 81
+'sk' => 82
+'sl' => 83
+'sn' => 84
+'so' => 85
+'sq' => 86
+'sr' => 87
+'su' => 88
+'sv' => 89
+'sw' => 90
+'ta' => 91
+'te' => 92
+'tg' => 93
+'th' => 94
+'tk' => 95
+'tl' => 96
+'tr' => 97
+'tt' => 98
+'uk' => 99
+'ur' => 100
+'uz' => 101
+'vi' => 102
+'war' => 103
+'yi' => 104
+'yo' => 105
+'zh' => 106
+================
+'starting_index' => 0

normalizer.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c369e01dfa2e0d84c6b116f33c7b94f1fe28c061642086538e93cde3d97c26ef
+size 1063