Hugging Face's logo

csukuangfj
/
vits-zh-hf-fanchen-wnj

ONNX
Model card Files Community
csukuangfj commited on
Commit
1e0eb37
β€’
1 Parent(s): a264494

update

Browse files
Files changed (5) hide show
  1. G_wnj_latest.json +144 -0
  2. lexicon.txt +0 -0
  3. rule.fst +0 -0
  4. tokens.txt +50 -0
  5. vits-zh-hf-fanchen-wnj.onnx +3 -0
G_wnj_latest.json ADDED
@@ -0,0 +1,144 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "train": {
3
+ "log_interval": 10,
4
+ "eval_interval": 100,
5
+ "seed": 1234,
6
+ "epochs": 200,
7
+ "learning_rate": 0.0002,
8
+ "betas": [
9
+ 0.8,
10
+ 0.99
11
+ ],
12
+ "eps": 1e-09,
13
+ "batch_size": 8,
14
+ "fp16_run": true,
15
+ "lr_decay": 0.999875,
16
+ "segment_size": 8192,
17
+ "init_lr_ratio": 1,
18
+ "warmup_epochs": 0,
19
+ "c_mel": 45,
20
+ "c_kl": 1.0
21
+ },
22
+ "data": {
23
+ "training_files": "final_annotation_train.txt",
24
+ "validation_files": "final_annotation_val.txt",
25
+ "text_cleaners": [
26
+ "chinese_cleaners"
27
+ ],
28
+ "max_wav_value": 32768.0,
29
+ "sampling_rate": 16000,
30
+ "filter_length": 1024,
31
+ "hop_length": 256,
32
+ "win_length": 1024,
33
+ "n_mel_channels": 80,
34
+ "mel_fmin": 0.0,
35
+ "mel_fmax": null,
36
+ "add_blank": true,
37
+ "n_speakers": 1,
38
+ "cleaned_text": true
39
+ },
40
+ "model": {
41
+ "inter_channels": 192,
42
+ "hidden_channels": 192,
43
+ "filter_channels": 768,
44
+ "n_heads": 2,
45
+ "n_layers": 6,
46
+ "kernel_size": 3,
47
+ "p_dropout": 0.1,
48
+ "resblock": "1",
49
+ "resblock_kernel_sizes": [
50
+ 3,
51
+ 7,
52
+ 11
53
+ ],
54
+ "resblock_dilation_sizes": [
55
+ [
56
+ 1,
57
+ 3,
58
+ 5
59
+ ],
60
+ [
61
+ 1,
62
+ 3,
63
+ 5
64
+ ],
65
+ [
66
+ 1,
67
+ 3,
68
+ 5
69
+ ]
70
+ ],
71
+ "upsample_rates": [
72
+ 8,
73
+ 8,
74
+ 2,
75
+ 2
76
+ ],
77
+ "upsample_initial_channel": 512,
78
+ "upsample_kernel_sizes": [
79
+ 16,
80
+ 16,
81
+ 4,
82
+ 4
83
+ ],
84
+ "n_layers_q": 3,
85
+ "use_spectral_norm": false,
86
+ "gin_channels": 256
87
+ },
88
+ "speakers": {
89
+ "wnj": 0
90
+ },
91
+ "symbols": [
92
+ "_",
93
+ "\uff0c",
94
+ "\u3002",
95
+ "\uff01",
96
+ "\uff1f",
97
+ "\u2014",
98
+ "\u2026",
99
+ "\u3105",
100
+ "\u3106",
101
+ "\u3107",
102
+ "\u3108",
103
+ "\u3109",
104
+ "\u310a",
105
+ "\u310b",
106
+ "\u310c",
107
+ "\u310d",
108
+ "\u310e",
109
+ "\u310f",
110
+ "\u3110",
111
+ "\u3111",
112
+ "\u3112",
113
+ "\u3113",
114
+ "\u3114",
115
+ "\u3115",
116
+ "\u3116",
117
+ "\u3117",
118
+ "\u3118",
119
+ "\u3119",
120
+ "\u311a",
121
+ "\u311b",
122
+ "\u311c",
123
+ "\u311d",
124
+ "\u311e",
125
+ "\u311f",
126
+ "\u3120",
127
+ "\u3121",
128
+ "\u3122",
129
+ "\u3123",
130
+ "\u3124",
131
+ "\u3125",
132
+ "\u3126",
133
+ "\u3127",
134
+ "\u3128",
135
+ "\u3129",
136
+ "\u02c9",
137
+ "\u02ca",
138
+ "\u02c7",
139
+ "\u02cb",
140
+ "\u02d9",
141
+ " "
142
+ ],
143
+ "model_dir": "save_models\\wnj"
144
+ }
lexicon.txt ADDED
The diff for this file is too large to render. See raw diff
 
rule.fst ADDED
tokens.txt ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ _ 0
2
+ ， 1
3
+ 。 2
4
+ ！ 3
5
+ ？ 4
6
+ β€” 5
7
+ … 6
8
+ γ„… 7
9
+ ㄆ 8
10
+ ㄇ 9
11
+ γ„ˆ 10
12
+ ㄉ 11
13
+ γ„Š 12
14
+ γ„‹ 13
15
+ γ„Œ 14
16
+ ㄍ 15
17
+ γ„Ž 16
18
+ ㄏ 17
19
+ ㄐ 18
20
+ γ„‘ 19
21
+ γ„’ 20
22
+ γ„“ 21
23
+ γ„” 22
24
+ γ„• 23
25
+ γ„– 24
26
+ γ„— 25
27
+ γ„˜ 26
28
+ γ„™ 27
29
+ γ„š 28
30
+ γ„› 29
31
+ γ„œ 30
32
+ ㄝ 31
33
+ γ„ž 32
34
+ γ„Ÿ 33
35
+ γ„  34
36
+ γ„‘ 35
37
+ γ„’ 36
38
+ γ„£ 37
39
+ γ„€ 38
40
+ γ„₯ 39
41
+ ㄦ 40
42
+ ㄧ 41
43
+ ㄨ 42
44
+ γ„© 43
45
+ Λ‰ 44
46
+ ˊ 45
47
+ Λ‡ 46
48
+ Λ‹ 47
49
+ Λ™ 48
50
+ 49
vits-zh-hf-fanchen-wnj.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2398163f5a4f4a171855a75490d659ad982d27939aec2e0a4764bc1dc5a226d
3
+ size 121076173