Text-to-Audio
Transformers
English
Inference Endpoints
declare-lab-sutd commited on
Commit
bf778ea
1 Parent(s): 3afa7d5

First TANGO Version

Browse files
main_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"text_encoder_name": "google/flan-t5-large", "scheduler_name": "stabilityai/stable-diffusion-2-1", "unet_model_name": null, "unet_model_config_path": "configs/diffusion_model_config.json", "snr_gamma": 5.0}
pytorch_model_main.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a79eba873b614adf5a25daa9a958e254bc520100f4ccd44babda5fbb4cc565db
3
+ size 4829066707
pytorch_model_stft.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8674a4cc9755fafa48350bfa3412cf9b9a0d357d18289dbfd86f0fb34e1ca4db
3
+ size 8537803
pytorch_model_vae.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d49e1881f38bd4f4fcaaf1c56686c02fb15f75e80dec5f773ae235b2cf1b61b
3
+ size 442713669
stft_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"filter_length": 1024, "hop_length": 160, "win_length": 1024, "n_mel_channels": 64, "sampling_rate": 16000, "mel_fmin": 0, "mel_fmax": 8000}
vae_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"image_key": "fbank", "subband": 1, "embed_dim": 8, "time_shuffle": 1, "ddconfig": {"double_z": true, "z_channels": 8, "resolution": 256, "downsample_time": false, "in_channels": 1, "out_ch": 1, "ch": 128, "ch_mult": [1, 2, 4], "num_res_blocks": 2, "attn_resolutions": [], "dropout": 0.0}, "scale_factor": 0.9227914214134216}