Upload 2 files
Browse files
sound_tokenizer/config.json
ADDED
|
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model_type": "autoencoder_v2",
|
| 3 |
+
"sampling_rate": 48000,
|
| 4 |
+
"stereo": true,
|
| 5 |
+
"use_wav_as_input": true,
|
| 6 |
+
"normalize_volume": true,
|
| 7 |
+
"hop_size": 1920,
|
| 8 |
+
"input_channels": 1,
|
| 9 |
+
"enc_type": "spec_convnext",
|
| 10 |
+
"enc_dim": 192,
|
| 11 |
+
"enc_intermediate_dim": 768,
|
| 12 |
+
"enc_num_layers": 12,
|
| 13 |
+
"enc_num_blocks": 2,
|
| 14 |
+
"enc_n_fft": 64,
|
| 15 |
+
"enc_hop_length": 16,
|
| 16 |
+
"enc_latent_dim": 128,
|
| 17 |
+
"enc_c_mults": [
|
| 18 |
+
1,
|
| 19 |
+
2,
|
| 20 |
+
4
|
| 21 |
+
],
|
| 22 |
+
"enc_strides": [
|
| 23 |
+
4,
|
| 24 |
+
5,
|
| 25 |
+
6
|
| 26 |
+
],
|
| 27 |
+
"enc_identity_init": false,
|
| 28 |
+
"enc_use_snake": true,
|
| 29 |
+
"dec_type": "oobleck",
|
| 30 |
+
"dec_dim": 320,
|
| 31 |
+
"dec_c_mults": [
|
| 32 |
+
1,
|
| 33 |
+
2,
|
| 34 |
+
4,
|
| 35 |
+
8,
|
| 36 |
+
16
|
| 37 |
+
],
|
| 38 |
+
"dec_strides": [
|
| 39 |
+
2,
|
| 40 |
+
4,
|
| 41 |
+
5,
|
| 42 |
+
6,
|
| 43 |
+
8
|
| 44 |
+
],
|
| 45 |
+
"dec_use_snake": true,
|
| 46 |
+
"dec_final_tanh": false,
|
| 47 |
+
"dec_out_channels": 2,
|
| 48 |
+
"dec_anti_aliasing": false,
|
| 49 |
+
"dec_use_nearest_upsample": false,
|
| 50 |
+
"dec_use_tanh_at_final": false,
|
| 51 |
+
"bottleneck_type": "vae",
|
| 52 |
+
"bottleneck": {
|
| 53 |
+
"type": "vae"
|
| 54 |
+
},
|
| 55 |
+
"activation": "snakebeta",
|
| 56 |
+
"snake_logscale": true,
|
| 57 |
+
"anti_aliasing": false,
|
| 58 |
+
"use_cuda_kernel": false,
|
| 59 |
+
"causal": false,
|
| 60 |
+
"padding_mode": "zeros",
|
| 61 |
+
"vocoder_input_dim": 64,
|
| 62 |
+
"latent_mean": null,
|
| 63 |
+
"latent_std": null
|
| 64 |
+
}
|
sound_tokenizer/diffusion_pytorch_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a4b6da5975bf89f6853fe589ad4752d281ac79fbdfad52ea90537fa080b4b9c2
|
| 3 |
+
size 1985176840
|