Hugging Face's logo

IAHispano
/
Applio

Audio-to-Audio
ONNX
AI
RVC
VITS
VC
Voice Conversion
Voice2Voice
Model card Files Community
5
blaise-tk commited on
Commit
ca22a14
•
1 Parent(s): afb5d76

Upload 8 files

Browse files
Files changed (8) hide show
  1. Resources/embedders/chinese_hubert_base/chinese_hubert_base.bin +3 -0
  2. Resources/embedders/chinese_hubert_base/chinese_hubert_base_config.json +71 -0
  3. Resources/embedders/contentvec/contentvec.bin +3 -0
  4. Resources/embedders/contentvec/contentvec_config.json +71 -0
  5. Resources/embedders/japanese_hubert_base/japanese_hubert_base.bin +3 -0
  6. Resources/embedders/japanese_hubert_base/japanese_hubert_base_config.json +71 -0
  7. Resources/embedders/korean_hubert_base/korean_hubert_base.bin +3 -0
  8. Resources/embedders/korean_hubert_base/korean_hubert_base_config.json +78 -0
Resources/embedders/chinese_hubert_base/chinese_hubert_base.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2fefccd26c2794a583b80f6f7210c721873cb7ebae2c1cde3baf9b27855e24d8
3
+ size 377552987
Resources/embedders/chinese_hubert_base/chinese_hubert_base_config.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.1,
3
+ "apply_spec_augment": true,
4
+ "architectures": [
5
+ "HubertModel"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "bos_token_id": 1,
9
+ "classifier_proj_size": 256,
10
+ "conv_bias": false,
11
+ "conv_dim": [
12
+ 512,
13
+ 512,
14
+ 512,
15
+ 512,
16
+ 512,
17
+ 512,
18
+ 512
19
+ ],
20
+ "conv_kernel": [
21
+ 10,
22
+ 3,
23
+ 3,
24
+ 3,
25
+ 3,
26
+ 2,
27
+ 2
28
+ ],
29
+ "conv_stride": [
30
+ 5,
31
+ 2,
32
+ 2,
33
+ 2,
34
+ 2,
35
+ 2,
36
+ 2
37
+ ],
38
+ "ctc_loss_reduction": "sum",
39
+ "ctc_zero_infinity": false,
40
+ "do_stable_layer_norm": false,
41
+ "eos_token_id": 2,
42
+ "feat_extract_activation": "gelu",
43
+ "feat_extract_norm": "group",
44
+ "feat_proj_dropout": 0.0,
45
+ "feat_proj_layer_norm": true,
46
+ "final_dropout": 0.1,
47
+ "hidden_act": "gelu",
48
+ "hidden_dropout": 0.1,
49
+ "hidden_size": 768,
50
+ "initializer_range": 0.02,
51
+ "intermediate_size": 3072,
52
+ "layer_norm_eps": 1e-05,
53
+ "layerdrop": 0.1,
54
+ "mask_feature_length": 10,
55
+ "mask_feature_min_masks": 0,
56
+ "mask_feature_prob": 0.0,
57
+ "mask_time_length": 10,
58
+ "mask_time_min_masks": 2,
59
+ "mask_time_prob": 0.05,
60
+ "model_type": "hubert",
61
+ "num_attention_heads": 12,
62
+ "num_conv_pos_embedding_groups": 16,
63
+ "num_conv_pos_embeddings": 128,
64
+ "num_feat_extract_layers": 7,
65
+ "num_hidden_layers": 12,
66
+ "pad_token_id": 0,
67
+ "torch_dtype": "float32",
68
+ "transformers_version": "4.20.0.dev0",
69
+ "use_weighted_layer_sum": false,
70
+ "vocab_size": 32
71
+ }
Resources/embedders/contentvec/contentvec.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8dd400e054ddf4e6be75dab5a2549db748cc99e756a097c496c099f65a4854e
3
+ size 378342945
Resources/embedders/contentvec/contentvec_config.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.1,
3
+ "apply_spec_augment": true,
4
+ "architectures": [
5
+ "HubertModelWithFinalProj"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "bos_token_id": 1,
9
+ "classifier_proj_size": 256,
10
+ "conv_bias": false,
11
+ "conv_dim": [
12
+ 512,
13
+ 512,
14
+ 512,
15
+ 512,
16
+ 512,
17
+ 512,
18
+ 512
19
+ ],
20
+ "conv_kernel": [
21
+ 10,
22
+ 3,
23
+ 3,
24
+ 3,
25
+ 3,
26
+ 2,
27
+ 2
28
+ ],
29
+ "conv_stride": [
30
+ 5,
31
+ 2,
32
+ 2,
33
+ 2,
34
+ 2,
35
+ 2,
36
+ 2
37
+ ],
38
+ "ctc_loss_reduction": "sum",
39
+ "ctc_zero_infinity": false,
40
+ "do_stable_layer_norm": false,
41
+ "eos_token_id": 2,
42
+ "feat_extract_activation": "gelu",
43
+ "feat_extract_norm": "group",
44
+ "feat_proj_dropout": 0.0,
45
+ "feat_proj_layer_norm": true,
46
+ "final_dropout": 0.1,
47
+ "hidden_act": "gelu",
48
+ "hidden_dropout": 0.1,
49
+ "hidden_size": 768,
50
+ "initializer_range": 0.02,
51
+ "intermediate_size": 3072,
52
+ "layer_norm_eps": 1e-05,
53
+ "layerdrop": 0.1,
54
+ "mask_feature_length": 10,
55
+ "mask_feature_min_masks": 0,
56
+ "mask_feature_prob": 0.0,
57
+ "mask_time_length": 10,
58
+ "mask_time_min_masks": 2,
59
+ "mask_time_prob": 0.05,
60
+ "model_type": "hubert",
61
+ "num_attention_heads": 12,
62
+ "num_conv_pos_embedding_groups": 16,
63
+ "num_conv_pos_embeddings": 128,
64
+ "num_feat_extract_layers": 7,
65
+ "num_hidden_layers": 12,
66
+ "pad_token_id": 0,
67
+ "torch_dtype": "float32",
68
+ "transformers_version": "4.27.3",
69
+ "use_weighted_layer_sum": false,
70
+ "vocab_size": 32
71
+ }
Resources/embedders/japanese_hubert_base/japanese_hubert_base.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c023ccb71e4c2b5a324c94fc5ebe12403d3081c5f370df229892419996fd113
3
+ size 377554841
Resources/embedders/japanese_hubert_base/japanese_hubert_base_config.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.1,
3
+ "apply_spec_augment": true,
4
+ "architectures": [
5
+ "HubertModel"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "bos_token_id": 1,
9
+ "classifier_proj_size": 256,
10
+ "conv_bias": false,
11
+ "conv_dim": [
12
+ 512,
13
+ 512,
14
+ 512,
15
+ 512,
16
+ 512,
17
+ 512,
18
+ 512
19
+ ],
20
+ "conv_kernel": [
21
+ 10,
22
+ 3,
23
+ 3,
24
+ 3,
25
+ 3,
26
+ 2,
27
+ 2
28
+ ],
29
+ "conv_stride": [
30
+ 5,
31
+ 2,
32
+ 2,
33
+ 2,
34
+ 2,
35
+ 2,
36
+ 2
37
+ ],
38
+ "ctc_loss_reduction": "sum",
39
+ "ctc_zero_infinity": false,
40
+ "do_stable_layer_norm": false,
41
+ "eos_token_id": 2,
42
+ "feat_extract_activation": "gelu",
43
+ "feat_extract_norm": "group",
44
+ "feat_proj_dropout": 0.0,
45
+ "feat_proj_layer_norm": true,
46
+ "final_dropout": 0.1,
47
+ "hidden_act": "gelu",
48
+ "hidden_dropout": 0.1,
49
+ "hidden_size": 768,
50
+ "initializer_range": 0.02,
51
+ "intermediate_size": 3072,
52
+ "layer_norm_eps": 1e-05,
53
+ "layerdrop": 0.1,
54
+ "mask_feature_length": 10,
55
+ "mask_feature_min_masks": 0,
56
+ "mask_feature_prob": 0.0,
57
+ "mask_time_length": 10,
58
+ "mask_time_min_masks": 2,
59
+ "mask_time_prob": 0.05,
60
+ "model_type": "hubert",
61
+ "num_attention_heads": 12,
62
+ "num_conv_pos_embedding_groups": 16,
63
+ "num_conv_pos_embeddings": 128,
64
+ "num_feat_extract_layers": 7,
65
+ "num_hidden_layers": 12,
66
+ "pad_token_id": 0,
67
+ "torch_dtype": "float32",
68
+ "transformers_version": "4.28.1",
69
+ "use_weighted_layer_sum": false,
70
+ "vocab_size": 32
71
+ }
Resources/embedders/korean_hubert_base/korean_hubert_base.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:931f6232879f8eadf7dbd9e00e1fa4cac61ad269af89d509b2ed75009b1a02c5
3
+ size 377554841
Resources/embedders/korean_hubert_base/korean_hubert_base_config.json ADDED
@@ -0,0 +1,78 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.1,
3
+ "apply_spec_augment": true,
4
+ "architectures": [
5
+ "HubertModel"
6
+ ],
7
+ "auto_map": {
8
+ "FlaxAutoModel": "modeling_flax_hubert.FlaxHubertModel"
9
+ },
10
+ "attention_dropout": 0.1,
11
+ "bos_token_id": 1,
12
+ "conv_bias": false,
13
+ "conv_dim": [
14
+ 512,
15
+ 512,
16
+ 512,
17
+ 512,
18
+ 512,
19
+ 512,
20
+ 512
21
+ ],
22
+ "conv_kernel": [
23
+ 10,
24
+ 3,
25
+ 3,
26
+ 3,
27
+ 3,
28
+ 2,
29
+ 2
30
+ ],
31
+ "conv_stride": [
32
+ 5,
33
+ 2,
34
+ 2,
35
+ 2,
36
+ 2,
37
+ 2,
38
+ 2
39
+ ],
40
+ "ctc_loss_reduction": "sum",
41
+ "ctc_zero_infinity": false,
42
+ "do_stable_layer_norm": false,
43
+ "eos_token_id": 2,
44
+ "feat_extract_activation": "gelu",
45
+ "feat_extract_dropout": 0.0,
46
+ "feat_extract_norm": "group",
47
+ "feat_proj_dropout": 0.1,
48
+ "feat_proj_layer_norm": true,
49
+ "final_dropout": 0.1,
50
+ "final_proj_size": 256,
51
+ "gradient_checkpointing": false,
52
+ "hidden_act": "gelu",
53
+ "hidden_dropout": 0.1,
54
+ "hidden_dropout_prob": 0.1,
55
+ "hidden_size": 768,
56
+ "initializer_range": 0.02,
57
+ "intermediate_size": 3072,
58
+ "layer_norm_eps": 1e-05,
59
+ "layerdrop": 0.1,
60
+ "mask_feature_length": 10,
61
+ "mask_feature_min_masks": 0,
62
+ "mask_feature_prob": 0.0,
63
+ "mask_time_length": 10,
64
+ "mask_time_min_masks": 2,
65
+ "mask_time_prob": 0.05,
66
+ "model_type": "hubert",
67
+ "num_attention_heads": 12,
68
+ "num_conv_pos_embedding_groups": 16,
69
+ "num_conv_pos_embeddings": 128,
70
+ "num_feat_extract_layers": 7,
71
+ "num_hidden_layers": 12,
72
+ "pad_token_id": 0,
73
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
74
+ "torch_dtype": "float32",
75
+ "transformers_version": "4.30.0.dev0",
76
+ "use_weighted_layer_sum": false,
77
+ "vocab_size": 32
78
+ }