Upload folder using huggingface_hub
Browse files
audio_vae/config.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "AutoencoderKLLTX2Audio",
|
| 3 |
+
"_diffusers_version": "0.37.0.dev0",
|
| 4 |
+
"attn_resolutions": null,
|
| 5 |
+
"base_channels": 128,
|
| 6 |
+
"causality_axis": "height",
|
| 7 |
+
"ch_mult": [
|
| 8 |
+
1,
|
| 9 |
+
2,
|
| 10 |
+
4
|
| 11 |
+
],
|
| 12 |
+
"double_z": true,
|
| 13 |
+
"dropout": 0.0,
|
| 14 |
+
"in_channels": 2,
|
| 15 |
+
"is_causal": true,
|
| 16 |
+
"latent_channels": 8,
|
| 17 |
+
"mel_bins": 64,
|
| 18 |
+
"mel_hop_length": 160,
|
| 19 |
+
"mid_block_add_attention": false,
|
| 20 |
+
"norm_type": "pixel",
|
| 21 |
+
"num_res_blocks": 2,
|
| 22 |
+
"output_channels": 2,
|
| 23 |
+
"resolution": 256,
|
| 24 |
+
"sample_rate": 16000
|
| 25 |
+
}
|
audio_vae/diffusion_pytorch_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b36ce4066065ce0aa5ff4d7cf96a3e3bc0859c6fefcf864663e3fe686c5c181c
|
| 3 |
+
size 106507972
|