Hugging Face's logo

zwa73
/
SoulTide-AudioData-Model

Japanese
Model card Files
xet
Community
zwa73 commited on
Commit
7a795f0
·
1 Parent(s): 3ad8586

20230202

Browse files
Files changed (7) hide show
  1. VITS/20230202-40speaker/best/D_128000.pth +3 -0
  2. VITS/20230202-40speaker/best/G_128000.pth +3 -0
  3. VITS/20230202-40speaker/best/config.json +104 -0
  4. VITS/20230202-40speaker/config.json +104 -0
  5. VITS/20230202-40speaker/pruned/P_G_128000.pth +3 -0
  6. VITS/20230202-40speaker/pruned/config.json +104 -0
  7. VITS/20230202-40speaker/train.log +0 -0
VITS/20230202-40speaker/best/D_128000.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8957392ed2cc932a89d2309892af3f9b2bd837c18d7b9163b9059398a3c8df8
3
+ size 561099143
VITS/20230202-40speaker/best/G_128000.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d380f3db75649fb4d60efbd8b80532d22653c75e2fb0cb0cfa252a2ca890f73b
3
+ size 476905883
VITS/20230202-40speaker/best/config.json ADDED
@@ -0,0 +1,104 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "train": {
3
+ "log_interval": 1600,
4
+ "eval_interval": 1600,
5
+ "seed": 1234,
6
+ "epochs": 2000,
7
+ "learning_rate": 2e-4,
8
+ "betas": [0.8, 0.99],
9
+ "eps": 1e-9,
10
+ "batch_size": 16,
11
+ "fp16_run": true,
12
+ "lr_decay": 0.999875,
13
+ "segment_size": 8192,
14
+ "init_lr_ratio": 1,
15
+ "warmup_epochs": 0,
16
+ "c_mel": 45,
17
+ "c_kl": 1.0
18
+ },
19
+ "data": {
20
+ "training_files":"filelists/train_filelist.txt.cleaned",
21
+ "validation_files":"filelists/val_filelist.txt.cleaned",
22
+ "text_cleaners":["japanese_cleaners"],
23
+ "max_wav_value": 32768.0,
24
+ "sampling_rate": 22050,
25
+ "filter_length": 1024,
26
+ "hop_length": 256,
27
+ "win_length": 1024,
28
+ "n_mel_channels": 80,
29
+ "mel_fmin": 0.0,
30
+ "mel_fmax": null,
31
+ "add_blank": true,
32
+ "n_speakers": 40,
33
+ "cleaned_text": true
34
+ },
35
+ "model": {
36
+ "inter_channels": 192,
37
+ "hidden_channels": 192,
38
+ "filter_channels": 768,
39
+ "n_heads": 2,
40
+ "n_layers": 6,
41
+ "kernel_size": 3,
42
+ "p_dropout": 0.1,
43
+ "resblock": "1",
44
+ "resblock_kernel_sizes": [3,7,11],
45
+ "resblock_dilation_sizes": [[1,3,5], [1,3,5], [1,3,5]],
46
+ "upsample_rates": [8,8,2,2],
47
+ "upsample_initial_channel": 512,
48
+ "upsample_kernel_sizes": [16,16,4,4],
49
+ "n_layers_q": 3,
50
+ "use_spectral_norm": false,
51
+ "gin_channels": 256
52
+ },
53
+ "speakers": [
54
+ "Akaset","Alisa","AmaneInori","Andrea","Asuna","Aurora",
55
+ "Benten","Colcher","Dreizehn","Ennis","EtsukazuMiko",
56
+ "Freesia","Gawana","HagakureRuri","HazukiYuki","Ithil",
57
+ "Juewa","Lavira","Lilyiro","Minerdwen","Mist",
58
+ "NankungLin","Netsuki","NetsukiFox","NicoletteLamel","QuLing",
59
+ "SakuyaMako","Satya","Silenus","TsukinoMiyo","Virgina","AkasetNS",
60
+ "AuroraNS","SilenusNS","ColcherNS","None","None","None","None","Kokkoro"
61
+ ],
62
+ "symbols": [
63
+ "_",
64
+ ",",
65
+ ".",
66
+ "!",
67
+ "?",
68
+ "-",
69
+ "A",
70
+ "E",
71
+ "I",
72
+ "N",
73
+ "O",
74
+ "Q",
75
+ "U",
76
+ "a",
77
+ "b",
78
+ "d",
79
+ "e",
80
+ "f",
81
+ "g",
82
+ "h",
83
+ "i",
84
+ "j",
85
+ "k",
86
+ "m",
87
+ "n",
88
+ "o",
89
+ "p",
90
+ "r",
91
+ "s",
92
+ "t",
93
+ "u",
94
+ "v",
95
+ "w",
96
+ "y",
97
+ "z",
98
+ "\u0283",
99
+ "\u02a7",
100
+ "\u2193",
101
+ "\u2191",
102
+ " "
103
+ ]
104
+ }
VITS/20230202-40speaker/config.json ADDED
@@ -0,0 +1,104 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "train": {
3
+ "log_interval": 1600,
4
+ "eval_interval": 1600,
5
+ "seed": 1234,
6
+ "epochs": 2000,
7
+ "learning_rate": 2e-4,
8
+ "betas": [0.8, 0.99],
9
+ "eps": 1e-9,
10
+ "batch_size": 16,
11
+ "fp16_run": true,
12
+ "lr_decay": 0.999875,
13
+ "segment_size": 8192,
14
+ "init_lr_ratio": 1,
15
+ "warmup_epochs": 0,
16
+ "c_mel": 45,
17
+ "c_kl": 1.0
18
+ },
19
+ "data": {
20
+ "training_files":"filelists/train_filelist.txt.cleaned",
21
+ "validation_files":"filelists/val_filelist.txt.cleaned",
22
+ "text_cleaners":["japanese_cleaners"],
23
+ "max_wav_value": 32768.0,
24
+ "sampling_rate": 22050,
25
+ "filter_length": 1024,
26
+ "hop_length": 256,
27
+ "win_length": 1024,
28
+ "n_mel_channels": 80,
29
+ "mel_fmin": 0.0,
30
+ "mel_fmax": null,
31
+ "add_blank": true,
32
+ "n_speakers": 40,
33
+ "cleaned_text": true
34
+ },
35
+ "model": {
36
+ "inter_channels": 192,
37
+ "hidden_channels": 192,
38
+ "filter_channels": 768,
39
+ "n_heads": 2,
40
+ "n_layers": 6,
41
+ "kernel_size": 3,
42
+ "p_dropout": 0.1,
43
+ "resblock": "1",
44
+ "resblock_kernel_sizes": [3,7,11],
45
+ "resblock_dilation_sizes": [[1,3,5], [1,3,5], [1,3,5]],
46
+ "upsample_rates": [8,8,2,2],
47
+ "upsample_initial_channel": 512,
48
+ "upsample_kernel_sizes": [16,16,4,4],
49
+ "n_layers_q": 3,
50
+ "use_spectral_norm": false,
51
+ "gin_channels": 256
52
+ },
53
+ "speakers": [
54
+ "Akaset","Alisa","AmaneInori","Andrea","Asuna","Aurora",
55
+ "Benten","Colcher","Dreizehn","Ennis","EtsukazuMiko",
56
+ "Freesia","Gawana","HagakureRuri","HazukiYuki","Ithil",
57
+ "Juewa","Lavira","Lilyiro","Minerdwen","Mist",
58
+ "NankungLin","Netsuki","NetsukiFox","NicoletteLamel","QuLing",
59
+ "SakuyaMako","Satya","Silenus","TsukinoMiyo","Virgina","AkasetNS",
60
+ "AuroraNS","SilenusNS","ColcherNS","None","None","None","None","Kokkoro"
61
+ ],
62
+ "symbols": [
63
+ "_",
64
+ ",",
65
+ ".",
66
+ "!",
67
+ "?",
68
+ "-",
69
+ "A",
70
+ "E",
71
+ "I",
72
+ "N",
73
+ "O",
74
+ "Q",
75
+ "U",
76
+ "a",
77
+ "b",
78
+ "d",
79
+ "e",
80
+ "f",
81
+ "g",
82
+ "h",
83
+ "i",
84
+ "j",
85
+ "k",
86
+ "m",
87
+ "n",
88
+ "o",
89
+ "p",
90
+ "r",
91
+ "s",
92
+ "t",
93
+ "u",
94
+ "v",
95
+ "w",
96
+ "y",
97
+ "z",
98
+ "\u0283",
99
+ "\u02a7",
100
+ "\u2193",
101
+ "\u2191",
102
+ " "
103
+ ]
104
+ }
VITS/20230202-40speaker/pruned/P_G_128000.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76c4c15bc021b4d72c3620cc13e5634744e45ebdc7cc2804f7c2487e7580a450
3
+ size 158917793
VITS/20230202-40speaker/pruned/config.json ADDED
@@ -0,0 +1,104 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "train": {
3
+ "log_interval": 1600,
4
+ "eval_interval": 1600,
5
+ "seed": 1234,
6
+ "epochs": 2000,
7
+ "learning_rate": 2e-4,
8
+ "betas": [0.8, 0.99],
9
+ "eps": 1e-9,
10
+ "batch_size": 16,
11
+ "fp16_run": true,
12
+ "lr_decay": 0.999875,
13
+ "segment_size": 8192,
14
+ "init_lr_ratio": 1,
15
+ "warmup_epochs": 0,
16
+ "c_mel": 45,
17
+ "c_kl": 1.0
18
+ },
19
+ "data": {
20
+ "training_files":"filelists/train_filelist.txt.cleaned",
21
+ "validation_files":"filelists/val_filelist.txt.cleaned",
22
+ "text_cleaners":["japanese_cleaners"],
23
+ "max_wav_value": 32768.0,
24
+ "sampling_rate": 22050,
25
+ "filter_length": 1024,
26
+ "hop_length": 256,
27
+ "win_length": 1024,
28
+ "n_mel_channels": 80,
29
+ "mel_fmin": 0.0,
30
+ "mel_fmax": null,
31
+ "add_blank": true,
32
+ "n_speakers": 40,
33
+ "cleaned_text": true
34
+ },
35
+ "model": {
36
+ "inter_channels": 192,
37
+ "hidden_channels": 192,
38
+ "filter_channels": 768,
39
+ "n_heads": 2,
40
+ "n_layers": 6,
41
+ "kernel_size": 3,
42
+ "p_dropout": 0.1,
43
+ "resblock": "1",
44
+ "resblock_kernel_sizes": [3,7,11],
45
+ "resblock_dilation_sizes": [[1,3,5], [1,3,5], [1,3,5]],
46
+ "upsample_rates": [8,8,2,2],
47
+ "upsample_initial_channel": 512,
48
+ "upsample_kernel_sizes": [16,16,4,4],
49
+ "n_layers_q": 3,
50
+ "use_spectral_norm": false,
51
+ "gin_channels": 256
52
+ },
53
+ "speakers": [
54
+ "Akaset","Alisa","AmaneInori","Andrea","Asuna","Aurora",
55
+ "Benten","Colcher","Dreizehn","Ennis","EtsukazuMiko",
56
+ "Freesia","Gawana","HagakureRuri","HazukiYuki","Ithil",
57
+ "Juewa","Lavira","Lilyiro","Minerdwen","Mist",
58
+ "NankungLin","Netsuki","NetsukiFox","NicoletteLamel","QuLing",
59
+ "SakuyaMako","Satya","Silenus","TsukinoMiyo","Virgina","AkasetNS",
60
+ "AuroraNS","SilenusNS","ColcherNS","None","None","None","None","Kokkoro"
61
+ ],
62
+ "symbols": [
63
+ "_",
64
+ ",",
65
+ ".",
66
+ "!",
67
+ "?",
68
+ "-",
69
+ "A",
70
+ "E",
71
+ "I",
72
+ "N",
73
+ "O",
74
+ "Q",
75
+ "U",
76
+ "a",
77
+ "b",
78
+ "d",
79
+ "e",
80
+ "f",
81
+ "g",
82
+ "h",
83
+ "i",
84
+ "j",
85
+ "k",
86
+ "m",
87
+ "n",
88
+ "o",
89
+ "p",
90
+ "r",
91
+ "s",
92
+ "t",
93
+ "u",
94
+ "v",
95
+ "w",
96
+ "y",
97
+ "z",
98
+ "\u0283",
99
+ "\u02a7",
100
+ "\u2193",
101
+ "\u2191",
102
+ " "
103
+ ]
104
+ }
VITS/20230202-40speaker/train.log ADDED
The diff for this file is too large to render. See raw diff