Hugging Face's logo

pandases
/
GPT-SoVITS-fork

Text-to-Speech
PyTorch
hubert
Model card Files Community
wa007 commited on
Commit
b6b5ecb
•
1 Parent(s): 3cb774d

init

Browse files
Files changed (15) hide show
  1. README.md +5 -3
  2. chinese-hubert-base/config.json +72 -0
  3. chinese-hubert-base/preprocessor_config.json +9 -0
  4. chinese-roberta-wwm-ext-large/config.json +34 -0
  5. chinese-roberta-wwm-ext-large/pytorch_model.bin +3 -0
  6. chinese-roberta-wwm-ext-large/tokenizer.json +0 -0
  7. config.json +72 -0
  8. gsv-v2final-pretrained/s1bert25hz-5kh-longer-epoch=12-step=369668.ckpt +3 -0
  9. gsv-v2final-pretrained/s2D2333k.pth +3 -0
  10. gsv-v2final-pretrained/s2G2333k.pth +3 -0
  11. preprocessor_config.json +9 -0
  12. pytorch_model.bin +3 -0
  13. s1bert25hz-2kh-longer-epoch=68e-step=50232.ckpt +3 -0
  14. s2D488k.pth +3 -0
  15. s2G488k.pth +3 -0
README.md CHANGED
@@ -1,3 +1,5 @@
1
- ---
2
- license: mit
3
- ---
 
 
 
1
+ ---
2
+ license: mit
3
+ pipeline_tag: text-to-speech
4
+ ---
5
+ pretrained models used in https://github.com/RVC-Boss/GPT-SoVITS
chinese-hubert-base/config.json ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/data/docker/liujing04/gpt-vits/chinese-hubert-base",
3
+ "activation_dropout": 0.1,
4
+ "apply_spec_augment": true,
5
+ "architectures": [
6
+ "HubertModel"
7
+ ],
8
+ "attention_dropout": 0.1,
9
+ "bos_token_id": 1,
10
+ "classifier_proj_size": 256,
11
+ "conv_bias": false,
12
+ "conv_dim": [
13
+ 512,
14
+ 512,
15
+ 512,
16
+ 512,
17
+ 512,
18
+ 512,
19
+ 512
20
+ ],
21
+ "conv_kernel": [
22
+ 10,
23
+ 3,
24
+ 3,
25
+ 3,
26
+ 3,
27
+ 2,
28
+ 2
29
+ ],
30
+ "conv_stride": [
31
+ 5,
32
+ 2,
33
+ 2,
34
+ 2,
35
+ 2,
36
+ 2,
37
+ 2
38
+ ],
39
+ "ctc_loss_reduction": "sum",
40
+ "ctc_zero_infinity": false,
41
+ "do_stable_layer_norm": false,
42
+ "eos_token_id": 2,
43
+ "feat_extract_activation": "gelu",
44
+ "feat_extract_norm": "group",
45
+ "feat_proj_dropout": 0.0,
46
+ "feat_proj_layer_norm": true,
47
+ "final_dropout": 0.1,
48
+ "hidden_act": "gelu",
49
+ "hidden_dropout": 0.1,
50
+ "hidden_size": 768,
51
+ "initializer_range": 0.02,
52
+ "intermediate_size": 3072,
53
+ "layer_norm_eps": 1e-05,
54
+ "layerdrop": 0.1,
55
+ "mask_feature_length": 10,
56
+ "mask_feature_min_masks": 0,
57
+ "mask_feature_prob": 0.0,
58
+ "mask_time_length": 10,
59
+ "mask_time_min_masks": 2,
60
+ "mask_time_prob": 0.05,
61
+ "model_type": "hubert",
62
+ "num_attention_heads": 12,
63
+ "num_conv_pos_embedding_groups": 16,
64
+ "num_conv_pos_embeddings": 128,
65
+ "num_feat_extract_layers": 7,
66
+ "num_hidden_layers": 12,
67
+ "pad_token_id": 0,
68
+ "torch_dtype": "float16",
69
+ "transformers_version": "4.30.2",
70
+ "use_weighted_layer_sum": false,
71
+ "vocab_size": 32
72
+ }
chinese-hubert-base/preprocessor_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "feature_extractor_type": "Wav2Vec2FeatureExtractor",
4
+ "feature_size": 1,
5
+ "padding_side": "right",
6
+ "padding_value": 0,
7
+ "return_attention_mask": false,
8
+ "sampling_rate": 16000
9
+ }
chinese-roberta-wwm-ext-large/config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/data/docker/liujing04/bert-vits2/Bert-VITS2-master20231106/bert/chinese-roberta-wwm-ext-large",
3
+ "architectures": [
4
+ "BertForMaskedLM"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "directionality": "bidi",
10
+ "eos_token_id": 2,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 1024,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 4096,
16
+ "layer_norm_eps": 1e-12,
17
+ "max_position_embeddings": 512,
18
+ "model_type": "bert",
19
+ "num_attention_heads": 16,
20
+ "num_hidden_layers": 24,
21
+ "output_past": true,
22
+ "pad_token_id": 0,
23
+ "pooler_fc_size": 768,
24
+ "pooler_num_attention_heads": 12,
25
+ "pooler_num_fc_layers": 3,
26
+ "pooler_size_per_head": 128,
27
+ "pooler_type": "first_token_transform",
28
+ "position_embedding_type": "absolute",
29
+ "torch_dtype": "float16",
30
+ "transformers_version": "4.30.2",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 21128
34
+ }
chinese-roberta-wwm-ext-large/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e53a693acc59ace251d143d068096ae0d7b79e4b1b503fa84c9dcf576448c1d8
3
+ size 651225145
chinese-roberta-wwm-ext-large/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
config.json ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/data/docker/liujing04/gpt-vits/chinese-hubert-base",
3
+ "activation_dropout": 0.1,
4
+ "apply_spec_augment": true,
5
+ "architectures": [
6
+ "HubertModel"
7
+ ],
8
+ "attention_dropout": 0.1,
9
+ "bos_token_id": 1,
10
+ "classifier_proj_size": 256,
11
+ "conv_bias": false,
12
+ "conv_dim": [
13
+ 512,
14
+ 512,
15
+ 512,
16
+ 512,
17
+ 512,
18
+ 512,
19
+ 512
20
+ ],
21
+ "conv_kernel": [
22
+ 10,
23
+ 3,
24
+ 3,
25
+ 3,
26
+ 3,
27
+ 2,
28
+ 2
29
+ ],
30
+ "conv_stride": [
31
+ 5,
32
+ 2,
33
+ 2,
34
+ 2,
35
+ 2,
36
+ 2,
37
+ 2
38
+ ],
39
+ "ctc_loss_reduction": "sum",
40
+ "ctc_zero_infinity": false,
41
+ "do_stable_layer_norm": false,
42
+ "eos_token_id": 2,
43
+ "feat_extract_activation": "gelu",
44
+ "feat_extract_norm": "group",
45
+ "feat_proj_dropout": 0.0,
46
+ "feat_proj_layer_norm": true,
47
+ "final_dropout": 0.1,
48
+ "hidden_act": "gelu",
49
+ "hidden_dropout": 0.1,
50
+ "hidden_size": 768,
51
+ "initializer_range": 0.02,
52
+ "intermediate_size": 3072,
53
+ "layer_norm_eps": 1e-05,
54
+ "layerdrop": 0.1,
55
+ "mask_feature_length": 10,
56
+ "mask_feature_min_masks": 0,
57
+ "mask_feature_prob": 0.0,
58
+ "mask_time_length": 10,
59
+ "mask_time_min_masks": 2,
60
+ "mask_time_prob": 0.05,
61
+ "model_type": "hubert",
62
+ "num_attention_heads": 12,
63
+ "num_conv_pos_embedding_groups": 16,
64
+ "num_conv_pos_embeddings": 128,
65
+ "num_feat_extract_layers": 7,
66
+ "num_hidden_layers": 12,
67
+ "pad_token_id": 0,
68
+ "torch_dtype": "float16",
69
+ "transformers_version": "4.30.2",
70
+ "use_weighted_layer_sum": false,
71
+ "vocab_size": 32
72
+ }
gsv-v2final-pretrained/s1bert25hz-5kh-longer-epoch=12-step=369668.ckpt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:732f94e63b148066e24c7f9d2637f3374083e637635f07fbdb695dee20ddbe1f
3
+ size 155315150
gsv-v2final-pretrained/s2D2333k.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ae7fe8dd8c8f2e718de359e00edac88b0c71ab2fd10b07ad4cc45070eb8a836
3
+ size 93534164
gsv-v2final-pretrained/s2G2333k.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:924fdccaa3c574bf139c25c9759aa1ed3b3f99e19a7c529ee996c2bc17663695
3
+ size 106035259
preprocessor_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "feature_extractor_type": "Wav2Vec2FeatureExtractor",
4
+ "feature_size": 1,
5
+ "padding_side": "right",
6
+ "padding_value": 0,
7
+ "return_attention_mask": false,
8
+ "sampling_rate": 16000
9
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24164f129c66499d1346e2aa55f183250c223161ec2770c0da3d3b08cf432d3c
3
+ size 188811417
s1bert25hz-2kh-longer-epoch=68e-step=50232.ckpt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1c1e17e9c99547a89388f72048cd6e1b41b5a18b170e86a46dfde0324d63eb1
3
+ size 155093966
s2D488k.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc579c1db3c1e21b721001cf99d7a584214280df19b002e200b630a34fa06eb8
3
+ size 93533667
s2G488k.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:020a014e1e01e550e510f2f61fae5e5f5b6aab40f15c22f1f12f724df507e835
3
+ size 105973721