Upload model
Browse files- config.json +3 -4
- model.safetensors +2 -2
config.json
CHANGED
|
@@ -1,8 +1,7 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "./tmp/vits_finetuned_angry",
|
| 3 |
"activation_dropout": 0.1,
|
| 4 |
"architectures": [
|
| 5 |
-
"
|
| 6 |
],
|
| 7 |
"attention_dropout": 0.1,
|
| 8 |
"depth_separable_channels": 2,
|
|
@@ -52,7 +51,7 @@
|
|
| 52 |
"noise_scale_duration": 0.8,
|
| 53 |
"num_attention_heads": 2,
|
| 54 |
"num_hidden_layers": 6,
|
| 55 |
-
"num_speakers":
|
| 56 |
"posterior_encoder_num_wavenet_layers": 16,
|
| 57 |
"prior_encoder_num_flows": 4,
|
| 58 |
"prior_encoder_num_wavenet_layers": 4,
|
|
@@ -80,7 +79,7 @@
|
|
| 80 |
],
|
| 81 |
"sampling_rate": 16000,
|
| 82 |
"segment_size": 8192,
|
| 83 |
-
"speaker_embedding_size":
|
| 84 |
"speaking_rate": 1.0,
|
| 85 |
"spectrogram_bins": 513,
|
| 86 |
"torch_dtype": "float32",
|
|
|
|
| 1 |
{
|
|
|
|
| 2 |
"activation_dropout": 0.1,
|
| 3 |
"architectures": [
|
| 4 |
+
"VitsModelForPreTraining"
|
| 5 |
],
|
| 6 |
"attention_dropout": 0.1,
|
| 7 |
"depth_separable_channels": 2,
|
|
|
|
| 51 |
"noise_scale_duration": 0.8,
|
| 52 |
"num_attention_heads": 2,
|
| 53 |
"num_hidden_layers": 6,
|
| 54 |
+
"num_speakers": 1,
|
| 55 |
"posterior_encoder_num_wavenet_layers": 16,
|
| 56 |
"prior_encoder_num_flows": 4,
|
| 57 |
"prior_encoder_num_wavenet_layers": 4,
|
|
|
|
| 79 |
],
|
| 80 |
"sampling_rate": 16000,
|
| 81 |
"segment_size": 8192,
|
| 82 |
+
"speaker_embedding_size": 0,
|
| 83 |
"speaking_rate": 1.0,
|
| 84 |
"spectrogram_bins": 513,
|
| 85 |
"torch_dtype": "float32",
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:288ebc5b047526f9a93b7bbdf32fbaa5cf73cbebdca9d16c1181580c3f273de7
|
| 3 |
+
size 332164552
|