Hugging Face's logo

ciferecavivon
/
so-vits-svc3.0_big

Audio-to-Audio
Transformers
Chinese
Japanese
English
Inference Endpoints
Model card Files Community
ciferecavivon commited on
Commit
b838720
•
1 Parent(s): 5a8196d

Upload 2 files

Browse files
Files changed (2) hide show
  1. 128_G_200000.pth +3 -0
  2. config_128.json +164 -0
128_G_200000.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c90631de5b1931836779c39eb3c868386563e1d6cbf6676a865f3de7371ae4bc
3
+ size 699702108
config_128.json ADDED
@@ -0,0 +1,164 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "train": {
3
+ "log_interval": 100,
4
+ "eval_interval": 2500,
5
+ "seed": 2044,
6
+ "epochs": 1500,
7
+ "learning_rate": 0.0001,
8
+ "betas": [
9
+ 0.8,
10
+ 0.99
11
+ ],
12
+ "eps": 1e-09,
13
+ "batch_size": 12,
14
+ "fp16_run": false,
15
+ "lr_decay": 0.999875,
16
+ "segment_size": 17920,
17
+ "init_lr_ratio": 1,
18
+ "warmup_epochs": 0,
19
+ "c_mel": 45,
20
+ "c_kl": 1.0,
21
+ "use_sr": true,
22
+ "max_speclen": 384,
23
+ "port": "8001"
24
+ },
25
+ "data": {
26
+ "training_files": "filelists/train.txt",
27
+ "validation_files": "filelists/val.txt",
28
+ "max_wav_value": 32768.0,
29
+ "sampling_rate": 32000,
30
+ "filter_length": 1280,
31
+ "hop_length": 320,
32
+ "win_length": 1280,
33
+ "n_mel_channels": 80,
34
+ "mel_fmin": 0.0,
35
+ "mel_fmax": null
36
+ },
37
+ "model": {
38
+ "inter_channels": 192,
39
+ "hidden_channels": 192,
40
+ "filter_channels": 768,
41
+ "n_heads": 2,
42
+ "n_layers": 6,
43
+ "kernel_size": 3,
44
+ "p_dropout": 0.1,
45
+ "resblock": "1",
46
+ "resblock_kernel_sizes": [
47
+ 3,
48
+ 7,
49
+ 11
50
+ ],
51
+ "resblock_dilation_sizes": [
52
+ [
53
+ 1,
54
+ 3,
55
+ 5
56
+ ],
57
+ [
58
+ 1,
59
+ 3,
60
+ 5
61
+ ],
62
+ [
63
+ 1,
64
+ 3,
65
+ 5
66
+ ]
67
+ ],
68
+ "upsample_rates": [
69
+ 10,
70
+ 8,
71
+ 2,
72
+ 2
73
+ ],
74
+ "upsample_initial_channel": 512,
75
+ "upsample_kernel_sizes": [
76
+ 16,
77
+ 16,
78
+ 4,
79
+ 4
80
+ ],
81
+ "n_layers_q": 3,
82
+ "use_spectral_norm": false,
83
+ "gin_channels": 256,
84
+ "ssl_dim": 256,
85
+ "n_speakers": 128
86
+ },
87
+ "spk": {
88
+ "0":0,
89
+ "1":1,
90
+ "2":2,
91
+ "3":3,
92
+ "4":4,
93
+ "5":5,
94
+ "6":6,
95
+ "7":7,
96
+ "8":8,
97
+ "9":9,
98
+ "10":10,
99
+ "11":11,
100
+ "12":12,
101
+ "13":13,
102
+ "14":14,
103
+ "15":15,
104
+ "16":16,
105
+ "17":17,
106
+ "18":18,
107
+ "19":19,
108
+ "20":20,
109
+ "21":21,
110
+ "22":22,
111
+ "23":23,
112
+ "24":24,
113
+ "25":25,
114
+ "26":26,
115
+ "27":27,
116
+ "28":28,
117
+ "29":29,
118
+ "30":30,
119
+ "31":31,
120
+ "32":32,
121
+ "33":33,
122
+ "34":34,
123
+ "35":35,
124
+ "36":36,
125
+ "37":37,
126
+ "38":38,
127
+ "39":39,
128
+ "40":40,
129
+ "41":41,
130
+ "42":42,
131
+ "43":43,
132
+ "44":44,
133
+ "45":45,
134
+ "46":46,
135
+ "47":47,
136
+ "48":48,
137
+ "49":49,
138
+ "50":50,
139
+ "51":51,
140
+ "52":52,
141
+ "53":53,
142
+ "54":54,
143
+ "55":55,
144
+ "56":56,
145
+ "57":57,
146
+ "58":58,
147
+ "59":59,
148
+ "60":60,
149
+ "61":61,
150
+ "62":62,
151
+ "63":63,
152
+ "64":64,
153
+ "65":65,
154
+ "66":66,
155
+ "67":67,
156
+ "68":68,
157
+ "69":69,
158
+ "70":70,
159
+ "71":71,
160
+ "72":72,
161
+ "73":73,
162
+ "74":74
163
+ }
164
+ }