shichaog commited on
Commit
86c5869
·
verified ·
1 Parent(s): 8cf7295

Add models files

Browse files
Files changed (7) hide show
  1. .gitattributes +2 -0
  2. D.pth +3 -0
  3. DUR.pth +3 -0
  4. G.pth +3 -0
  5. G_no_ref.wav +3 -0
  6. G_ref.wav +3 -0
  7. config.json +197 -0
.gitattributes CHANGED
@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ G_no_ref.wav filter=lfs diff=lfs merge=lfs -text
37
+ G_ref.wav filter=lfs diff=lfs merge=lfs -text
D.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0092162ad9bb486043d1b013d678fb2bc453195ca4297bf115eb02f1c49e1688
3
+ size 561099897
DUR.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba3c11cb3702e7169dda283c89251a2a9ba7c152050fcef11c6f9c7fb6610ab6
3
+ size 6892258
G.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ead3451402598acc245b78e252761cc475386fcfa2a2cf7bdf00860bc84dd925
3
+ size 623964174
G_no_ref.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7f98eede380f592781571e9296333f5e8d58293789182d06ed899fcbbd8fa70
3
+ size 429728
G_ref.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2e8cf65f5e383d35f19abac9e39d7ac98678edd37571b6f5e05284ffbb1413f
3
+ size 411296
config.json ADDED
@@ -0,0 +1,197 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "train": {
3
+ "attr_dropout_prob": 0.3,
4
+ "clone_dropout_prob": 0.3,
5
+ "log_interval": 200,
6
+ "eval_interval": 1000,
7
+ "seed": 52,
8
+ "epochs": 10000,
9
+ "learning_rate": 2e-05,
10
+ "betas": [
11
+ 0.8,
12
+ 0.99
13
+ ],
14
+ "eps": 1e-09,
15
+ "batch_size": 6,
16
+ "fp16_run": false,
17
+ "lr_decay": 0.999875,
18
+ "segment_size": 16384,
19
+ "init_lr_ratio": 1,
20
+ "warmup_epochs": 0,
21
+ "c_mel": 45,
22
+ "c_kl": 1.0,
23
+ "grad_clip_thresh": 1.0,
24
+ "skip_optimizer": true
25
+ },
26
+ "data": {
27
+ "training_files": "path/to/your/train.list",
28
+ "validation_files": "path/to/your/val.list",
29
+ "max_wav_value": 32768.0,
30
+ "sampling_rate": 44100,
31
+ "filter_length": 2048,
32
+ "hop_length": 512,
33
+ "win_length": 2048,
34
+ "n_mel_channels": 128,
35
+ "mel_fmin": 0.0,
36
+ "mel_fmax": null,
37
+ "add_blank": true,
38
+ "cleaned_text": true
39
+ },
40
+ "model": {
41
+ "gender_embed_dim": 16,
42
+ "pitch_embed_dim": 16,
43
+ "use_spk_conditioned_encoder": true,
44
+ "use_noise_scaled_mas": true,
45
+ "use_mel_posterior_encoder": false,
46
+ "use_duration_discriminator": true,
47
+ "inter_channels": 192,
48
+ "hidden_channels": 192,
49
+ "filter_channels": 768,
50
+ "n_heads": 2,
51
+ "n_layers": 6,
52
+ "n_layers_trans_flow": 3,
53
+ "kernel_size": 3,
54
+ "p_dropout": 0.1,
55
+ "resblock": "1",
56
+ "resblock_kernel_sizes": [
57
+ 3,
58
+ 7,
59
+ 11
60
+ ],
61
+ "resblock_dilation_sizes": [
62
+ [
63
+ 1,
64
+ 3,
65
+ 5
66
+ ],
67
+ [
68
+ 1,
69
+ 3,
70
+ 5
71
+ ],
72
+ [
73
+ 1,
74
+ 3,
75
+ 5
76
+ ]
77
+ ],
78
+ "upsample_rates": [
79
+ 8,
80
+ 8,
81
+ 2,
82
+ 2,
83
+ 2
84
+ ],
85
+ "upsample_initial_channel": 512,
86
+ "upsample_kernel_sizes": [
87
+ 16,
88
+ 16,
89
+ 8,
90
+ 2,
91
+ 2
92
+ ],
93
+ "n_layers_q": 3,
94
+ "use_spectral_norm": false,
95
+ "gin_channels": 256
96
+ },
97
+ "num_languages": 3,
98
+ "num_tones": 10,
99
+ "symbols": [
100
+ "_",
101
+ "AA",
102
+ "E",
103
+ "EE",
104
+ "En",
105
+ "OO",
106
+ "V",
107
+ "a",
108
+ "aa",
109
+ "ae",
110
+ "ah",
111
+ "ai",
112
+ "an",
113
+ "ang",
114
+ "ao",
115
+ "aw",
116
+ "ay",
117
+ "b",
118
+ "c",
119
+ "ch",
120
+ "d",
121
+ "dh",
122
+ "e",
123
+ "eh",
124
+ "ei",
125
+ "en",
126
+ "eng",
127
+ "er",
128
+ "ey",
129
+ "f",
130
+ "g",
131
+ "h",
132
+ "hh",
133
+ "i",
134
+ "i0",
135
+ "ia",
136
+ "ian",
137
+ "iang",
138
+ "iao",
139
+ "ie",
140
+ "ih",
141
+ "in",
142
+ "ing",
143
+ "iong",
144
+ "ir",
145
+ "iu",
146
+ "iy",
147
+ "j",
148
+ "jh",
149
+ "k",
150
+ "l",
151
+ "m",
152
+ "n",
153
+ "ng",
154
+ "o",
155
+ "ong",
156
+ "ou",
157
+ "ow",
158
+ "oy",
159
+ "p",
160
+ "q",
161
+ "r",
162
+ "s",
163
+ "sh",
164
+ "t",
165
+ "th",
166
+ "u",
167
+ "ua",
168
+ "uai",
169
+ "uan",
170
+ "uang",
171
+ "uh",
172
+ "ui",
173
+ "un",
174
+ "uo",
175
+ "uw",
176
+ "v",
177
+ "van",
178
+ "ve",
179
+ "vn",
180
+ "w",
181
+ "x",
182
+ "y",
183
+ "z",
184
+ "zh",
185
+ "!",
186
+ "?",
187
+ "…",
188
+ ",",
189
+ ".",
190
+ "'",
191
+ "-",
192
+ "¿",
193
+ "¡",
194
+ "SP",
195
+ "UNK"
196
+ ]
197
+ }