Upload 16 files
Browse files- zipvoice/fm_decoder.onnx +3 -0
- zipvoice/fm_decoder_int8.onnx +3 -0
- zipvoice/model.json +28 -0
- zipvoice/model.pt +3 -0
- zipvoice/model.safetensors +3 -0
- zipvoice/text_encoder.onnx +3 -0
- zipvoice/text_encoder_int8.onnx +3 -0
- zipvoice/tokens.txt +360 -0
- zipvoice_distill/fm_decoder.onnx +3 -0
- zipvoice_distill/fm_decoder_int8.onnx +3 -0
- zipvoice_distill/model.json +28 -0
- zipvoice_distill/model.pt +3 -0
- zipvoice_distill/model.safetensors +3 -0
- zipvoice_distill/text_encoder.onnx +3 -0
- zipvoice_distill/text_encoder_int8.onnx +3 -0
- zipvoice_distill/tokens.txt +360 -0
zipvoice/fm_decoder.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b50421792fd4b34f1df0a6deb3afd6f0eef339a65bd541402cb4c290e00d5fba
|
| 3 |
+
size 477298426
|
zipvoice/fm_decoder_int8.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bcc5074850198d9a77efa1fc2ffae138acaeb038f2ec4f16adc192fe6c2f82d8
|
| 3 |
+
size 124495491
|
zipvoice/model.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model" : {
|
| 3 |
+
"fm_decoder_downsampling_factor" : "1,2,4,2,1",
|
| 4 |
+
"fm_decoder_num_layers" : "2,2,4,4,4",
|
| 5 |
+
"fm_decoder_cnn_module_kernel" : "31,15,7,15,31",
|
| 6 |
+
"fm_decoder_feedforward_dim" : 1536,
|
| 7 |
+
"fm_decoder_num_heads" : 4,
|
| 8 |
+
"fm_decoder_dim" : 512,
|
| 9 |
+
"text_encoder_downsampling_factor" : "1",
|
| 10 |
+
"text_encoder_num_layers" : "4",
|
| 11 |
+
"text_encoder_feedforward_dim" : 512,
|
| 12 |
+
"text_encoder_cnn_module_kernel" : 9,
|
| 13 |
+
"text_encoder_num_heads" : 4,
|
| 14 |
+
"text_encoder_dim" : 192,
|
| 15 |
+
"query_head_dim" : 32,
|
| 16 |
+
"value_head_dim" : 12,
|
| 17 |
+
"pos_head_dim" : 4,
|
| 18 |
+
"pos_dim" : 48,
|
| 19 |
+
"time_embed_dim" : 192,
|
| 20 |
+
"text_embed_dim" : 192
|
| 21 |
+
},
|
| 22 |
+
"feature" : {
|
| 23 |
+
"sampling_rate": 24000,
|
| 24 |
+
"feat_dim": 100,
|
| 25 |
+
"n_fft" : 1024,
|
| 26 |
+
"hop_length" : 256
|
| 27 |
+
}
|
| 28 |
+
}
|
zipvoice/model.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:99e6cc91bd13ee6ccffc0aa7c8c3bd9941423de290d057f2424ab89d6c5352f4
|
| 3 |
+
size 491161451
|
zipvoice/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:172a20b18f41e3453ae5dc6551e9fef4924dc1ac30ecd50b763226c9538afdce
|
| 3 |
+
size 490777328
|
zipvoice/text_encoder.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dbc27921d2b6808e0b5626b98714a107d4b6049b5b6af9ed57163e5f14394426
|
| 3 |
+
size 17614052
|
zipvoice/text_encoder_int8.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b6addc04ce3d3f896554ecb4a60d111af18dfc9114ea848cb665bcd5b8b03357
|
| 3 |
+
size 5542574
|
zipvoice/tokens.txt
ADDED
|
@@ -0,0 +1,360 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
_ 0
|
| 2 |
+
^ 1
|
| 3 |
+
$ 2
|
| 4 |
+
3
|
| 5 |
+
! 4
|
| 6 |
+
' 5
|
| 7 |
+
( 6
|
| 8 |
+
) 7
|
| 9 |
+
, 8
|
| 10 |
+
- 9
|
| 11 |
+
. 10
|
| 12 |
+
: 11
|
| 13 |
+
; 12
|
| 14 |
+
? 13
|
| 15 |
+
a 14
|
| 16 |
+
b 15
|
| 17 |
+
c 16
|
| 18 |
+
d 17
|
| 19 |
+
e 18
|
| 20 |
+
f 19
|
| 21 |
+
h 20
|
| 22 |
+
i 21
|
| 23 |
+
j 22
|
| 24 |
+
k 23
|
| 25 |
+
l 24
|
| 26 |
+
m 25
|
| 27 |
+
n 26
|
| 28 |
+
o 27
|
| 29 |
+
p 28
|
| 30 |
+
q 29
|
| 31 |
+
r 30
|
| 32 |
+
s 31
|
| 33 |
+
t 32
|
| 34 |
+
u 33
|
| 35 |
+
v 34
|
| 36 |
+
w 35
|
| 37 |
+
x 36
|
| 38 |
+
y 37
|
| 39 |
+
z 38
|
| 40 |
+
æ 39
|
| 41 |
+
ç 40
|
| 42 |
+
ð 41
|
| 43 |
+
ø 42
|
| 44 |
+
ħ 43
|
| 45 |
+
ŋ 44
|
| 46 |
+
œ 45
|
| 47 |
+
ǀ 46
|
| 48 |
+
ǁ 47
|
| 49 |
+
ǂ 48
|
| 50 |
+
ǃ 49
|
| 51 |
+
ɐ 50
|
| 52 |
+
ɑ 51
|
| 53 |
+
ɒ 52
|
| 54 |
+
ɓ 53
|
| 55 |
+
ɔ 54
|
| 56 |
+
ɕ 55
|
| 57 |
+
ɖ 56
|
| 58 |
+
ɗ 57
|
| 59 |
+
ɘ 58
|
| 60 |
+
ə 59
|
| 61 |
+
ɚ 60
|
| 62 |
+
ɛ 61
|
| 63 |
+
ɜ 62
|
| 64 |
+
ɞ 63
|
| 65 |
+
ɟ 64
|
| 66 |
+
ɠ 65
|
| 67 |
+
ɡ 66
|
| 68 |
+
ɢ 67
|
| 69 |
+
ɣ 68
|
| 70 |
+
ɤ 69
|
| 71 |
+
ɥ 70
|
| 72 |
+
ɦ 71
|
| 73 |
+
ɧ 72
|
| 74 |
+
ɨ 73
|
| 75 |
+
ɪ 74
|
| 76 |
+
ɫ 75
|
| 77 |
+
ɬ 76
|
| 78 |
+
ɭ 77
|
| 79 |
+
ɮ 78
|
| 80 |
+
ɯ 79
|
| 81 |
+
ɰ 80
|
| 82 |
+
ɱ 81
|
| 83 |
+
ɲ 82
|
| 84 |
+
ɳ 83
|
| 85 |
+
ɴ 84
|
| 86 |
+
ɵ 85
|
| 87 |
+
ɶ 86
|
| 88 |
+
ɸ 87
|
| 89 |
+
ɹ 88
|
| 90 |
+
ɺ 89
|
| 91 |
+
ɻ 90
|
| 92 |
+
ɽ 91
|
| 93 |
+
ɾ 92
|
| 94 |
+
ʀ 93
|
| 95 |
+
ʁ 94
|
| 96 |
+
ʂ 95
|
| 97 |
+
ʃ 96
|
| 98 |
+
ʄ 97
|
| 99 |
+
ʈ 98
|
| 100 |
+
ʉ 99
|
| 101 |
+
ʊ 100
|
| 102 |
+
ʋ 101
|
| 103 |
+
ʌ 102
|
| 104 |
+
ʍ 103
|
| 105 |
+
ʎ 104
|
| 106 |
+
ʏ 105
|
| 107 |
+
ʐ 106
|
| 108 |
+
ʑ 107
|
| 109 |
+
ʒ 108
|
| 110 |
+
ʔ 109
|
| 111 |
+
ʕ 110
|
| 112 |
+
ʘ 111
|
| 113 |
+
ʙ 112
|
| 114 |
+
ʛ 113
|
| 115 |
+
ʜ 114
|
| 116 |
+
ʝ 115
|
| 117 |
+
ʟ 116
|
| 118 |
+
ʡ 117
|
| 119 |
+
ʢ 118
|
| 120 |
+
ʲ 119
|
| 121 |
+
ˈ 120
|
| 122 |
+
ˌ 121
|
| 123 |
+
ː 122
|
| 124 |
+
ˑ 123
|
| 125 |
+
˞ 124
|
| 126 |
+
β 125
|
| 127 |
+
θ 126
|
| 128 |
+
χ 127
|
| 129 |
+
ᵻ 128
|
| 130 |
+
ⱱ 129
|
| 131 |
+
0 130
|
| 132 |
+
1 131
|
| 133 |
+
2 132
|
| 134 |
+
3 133
|
| 135 |
+
4 134
|
| 136 |
+
5 135
|
| 137 |
+
6 136
|
| 138 |
+
7 137
|
| 139 |
+
8 138
|
| 140 |
+
9 139
|
| 141 |
+
̧ 140
|
| 142 |
+
̃ 141
|
| 143 |
+
̪ 142
|
| 144 |
+
̯ 143
|
| 145 |
+
̩ 144
|
| 146 |
+
ʰ 145
|
| 147 |
+
ˤ 146
|
| 148 |
+
ε 147
|
| 149 |
+
↓ 148
|
| 150 |
+
# 149
|
| 151 |
+
" 150
|
| 152 |
+
↑ 151
|
| 153 |
+
̺ 152
|
| 154 |
+
̻ 153
|
| 155 |
+
g 154
|
| 156 |
+
ʦ 155
|
| 157 |
+
X 156
|
| 158 |
+
̝ 157
|
| 159 |
+
̊ 158
|
| 160 |
+
a1 159
|
| 161 |
+
a2 160
|
| 162 |
+
a3 161
|
| 163 |
+
a4 162
|
| 164 |
+
a5 163
|
| 165 |
+
ai1 164
|
| 166 |
+
ai2 165
|
| 167 |
+
ai3 166
|
| 168 |
+
ai4 167
|
| 169 |
+
ai5 168
|
| 170 |
+
an1 169
|
| 171 |
+
an2 170
|
| 172 |
+
an3 171
|
| 173 |
+
an4 172
|
| 174 |
+
an5 173
|
| 175 |
+
ang1 174
|
| 176 |
+
ang2 175
|
| 177 |
+
ang3 176
|
| 178 |
+
ang4 177
|
| 179 |
+
ang5 178
|
| 180 |
+
ao1 179
|
| 181 |
+
ao2 180
|
| 182 |
+
ao3 181
|
| 183 |
+
ao4 182
|
| 184 |
+
ao5 183
|
| 185 |
+
b0 184
|
| 186 |
+
c0 185
|
| 187 |
+
ch0 186
|
| 188 |
+
d0 187
|
| 189 |
+
e1 188
|
| 190 |
+
e2 189
|
| 191 |
+
e3 190
|
| 192 |
+
e4 191
|
| 193 |
+
e5 192
|
| 194 |
+
ei1 193
|
| 195 |
+
ei2 194
|
| 196 |
+
ei3 195
|
| 197 |
+
ei4 196
|
| 198 |
+
ei5 197
|
| 199 |
+
en1 198
|
| 200 |
+
en2 199
|
| 201 |
+
en3 200
|
| 202 |
+
en4 201
|
| 203 |
+
en5 202
|
| 204 |
+
eng1 203
|
| 205 |
+
eng2 204
|
| 206 |
+
eng3 205
|
| 207 |
+
eng4 206
|
| 208 |
+
eng5 207
|
| 209 |
+
er2 208
|
| 210 |
+
er3 209
|
| 211 |
+
er4 210
|
| 212 |
+
er5 211
|
| 213 |
+
f0 212
|
| 214 |
+
g0 213
|
| 215 |
+
g2 214
|
| 216 |
+
g3 215
|
| 217 |
+
g4 216
|
| 218 |
+
g5 217
|
| 219 |
+
h0 218
|
| 220 |
+
i1 219
|
| 221 |
+
i2 220
|
| 222 |
+
i3 221
|
| 223 |
+
i4 222
|
| 224 |
+
i5 223
|
| 225 |
+
ia1 224
|
| 226 |
+
ia2 225
|
| 227 |
+
ia3 226
|
| 228 |
+
ia4 227
|
| 229 |
+
ia5 228
|
| 230 |
+
ian1 229
|
| 231 |
+
ian2 230
|
| 232 |
+
ian3 231
|
| 233 |
+
ian4 232
|
| 234 |
+
ian5 233
|
| 235 |
+
iang1 234
|
| 236 |
+
iang2 235
|
| 237 |
+
iang3 236
|
| 238 |
+
iang4 237
|
| 239 |
+
iang5 238
|
| 240 |
+
iao1 239
|
| 241 |
+
iao2 240
|
| 242 |
+
iao3 241
|
| 243 |
+
iao4 242
|
| 244 |
+
iao5 243
|
| 245 |
+
ie1 244
|
| 246 |
+
ie2 245
|
| 247 |
+
ie3 246
|
| 248 |
+
ie4 247
|
| 249 |
+
ie5 248
|
| 250 |
+
in1 249
|
| 251 |
+
in2 250
|
| 252 |
+
in3 251
|
| 253 |
+
in4 252
|
| 254 |
+
in5 253
|
| 255 |
+
ing1 254
|
| 256 |
+
ing2 255
|
| 257 |
+
ing3 256
|
| 258 |
+
ing4 257
|
| 259 |
+
ing5 258
|
| 260 |
+
iong1 259
|
| 261 |
+
iong2 260
|
| 262 |
+
iong3 261
|
| 263 |
+
iong4 262
|
| 264 |
+
iu1 263
|
| 265 |
+
iu2 264
|
| 266 |
+
iu3 265
|
| 267 |
+
iu4 266
|
| 268 |
+
iu5 267
|
| 269 |
+
j0 268
|
| 270 |
+
k0 269
|
| 271 |
+
l0 270
|
| 272 |
+
m0 271
|
| 273 |
+
m1 272
|
| 274 |
+
m2 273
|
| 275 |
+
m4 274
|
| 276 |
+
m5 275
|
| 277 |
+
n0 276
|
| 278 |
+
n2 277
|
| 279 |
+
n3 278
|
| 280 |
+
n4 279
|
| 281 |
+
n5 280
|
| 282 |
+
ng5 281
|
| 283 |
+
o1 282
|
| 284 |
+
o2 283
|
| 285 |
+
o3 284
|
| 286 |
+
o4 285
|
| 287 |
+
o5 286
|
| 288 |
+
ong1 287
|
| 289 |
+
ong2 288
|
| 290 |
+
ong3 289
|
| 291 |
+
ong4 290
|
| 292 |
+
ong5 291
|
| 293 |
+
ou1 292
|
| 294 |
+
ou2 293
|
| 295 |
+
ou3 294
|
| 296 |
+
ou4 295
|
| 297 |
+
ou5 296
|
| 298 |
+
p0 297
|
| 299 |
+
q0 298
|
| 300 |
+
r0 299
|
| 301 |
+
s0 300
|
| 302 |
+
sh0 301
|
| 303 |
+
t0 302
|
| 304 |
+
u1 303
|
| 305 |
+
u2 304
|
| 306 |
+
u3 305
|
| 307 |
+
u4 306
|
| 308 |
+
u5 307
|
| 309 |
+
ua1 308
|
| 310 |
+
ua2 309
|
| 311 |
+
ua3 310
|
| 312 |
+
ua4 311
|
| 313 |
+
uai1 312
|
| 314 |
+
uai2 313
|
| 315 |
+
uai3 314
|
| 316 |
+
uai4 315
|
| 317 |
+
uai5 316
|
| 318 |
+
uan1 317
|
| 319 |
+
uan2 318
|
| 320 |
+
uan3 319
|
| 321 |
+
uan4 320
|
| 322 |
+
uan5 321
|
| 323 |
+
uang1 322
|
| 324 |
+
uang2 323
|
| 325 |
+
uang3 324
|
| 326 |
+
uang4 325
|
| 327 |
+
uang5 326
|
| 328 |
+
ue1 327
|
| 329 |
+
ue2 328
|
| 330 |
+
ue3 329
|
| 331 |
+
ue4 330
|
| 332 |
+
ui1 331
|
| 333 |
+
ui2 332
|
| 334 |
+
ui3 333
|
| 335 |
+
ui4 334
|
| 336 |
+
ui5 335
|
| 337 |
+
un1 336
|
| 338 |
+
un2 337
|
| 339 |
+
un3 338
|
| 340 |
+
un4 339
|
| 341 |
+
un5 340
|
| 342 |
+
uo1 341
|
| 343 |
+
uo2 342
|
| 344 |
+
uo3 343
|
| 345 |
+
uo4 344
|
| 346 |
+
uo5 345
|
| 347 |
+
v2 346
|
| 348 |
+
v3 347
|
| 349 |
+
v4 348
|
| 350 |
+
ve3 349
|
| 351 |
+
ve4 350
|
| 352 |
+
w0 351
|
| 353 |
+
x0 352
|
| 354 |
+
y0 353
|
| 355 |
+
z0 354
|
| 356 |
+
zh0 355
|
| 357 |
+
ê1 356
|
| 358 |
+
ê2 357
|
| 359 |
+
ê3 358
|
| 360 |
+
ê4 359
|
zipvoice_distill/fm_decoder.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:03ebb265fc76e0d778edec9c8ee47c6dc971fa8d1c39a0a14ef43c77d756aeb4
|
| 3 |
+
size 477445650
|
zipvoice_distill/fm_decoder_int8.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3d5bf8230de16051f417b47c6e8d405e4084f621d7de6044d417de56bee7e0ea
|
| 3 |
+
size 124532425
|
zipvoice_distill/model.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model" : {
|
| 3 |
+
"fm_decoder_downsampling_factor" : "1,2,4,2,1",
|
| 4 |
+
"fm_decoder_num_layers" : "2,2,4,4,4",
|
| 5 |
+
"fm_decoder_cnn_module_kernel" : "31,15,7,15,31",
|
| 6 |
+
"fm_decoder_feedforward_dim" : 1536,
|
| 7 |
+
"fm_decoder_num_heads" : 4,
|
| 8 |
+
"fm_decoder_dim" : 512,
|
| 9 |
+
"text_encoder_downsampling_factor" : "1",
|
| 10 |
+
"text_encoder_num_layers" : "4",
|
| 11 |
+
"text_encoder_feedforward_dim" : 512,
|
| 12 |
+
"text_encoder_cnn_module_kernel" : 9,
|
| 13 |
+
"text_encoder_num_heads" : 4,
|
| 14 |
+
"text_encoder_dim" : 192,
|
| 15 |
+
"query_head_dim" : 32,
|
| 16 |
+
"value_head_dim" : 12,
|
| 17 |
+
"pos_head_dim" : 4,
|
| 18 |
+
"pos_dim" : 48,
|
| 19 |
+
"time_embed_dim" : 192,
|
| 20 |
+
"text_embed_dim" : 192
|
| 21 |
+
},
|
| 22 |
+
"feature" : {
|
| 23 |
+
"sampling_rate": 24000,
|
| 24 |
+
"feat_dim": 100,
|
| 25 |
+
"n_fft" : 1024,
|
| 26 |
+
"hop_length" : 256
|
| 27 |
+
}
|
| 28 |
+
}
|
zipvoice_distill/model.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:745855037478eb888cfa7a3603c1aa9f663f22a72d94cc1c37787228ff422095
|
| 3 |
+
size 491318136
|
zipvoice_distill/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6a2580c60d47997be75e0b945740169efa2c151cb7f4f0c1b63ddd6ab76dd789
|
| 3 |
+
size 490924896
|
zipvoice_distill/text_encoder.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:71175b0752ce7e5f5c67faff2a24e750d329e3d002ed5e0124c1011248377466
|
| 3 |
+
size 17614052
|
zipvoice_distill/text_encoder_int8.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:adcec1948b2fa335057b8e5bd0960942a73ea23e3172b39d0f89a6c595d62b99
|
| 3 |
+
size 5542574
|
zipvoice_distill/tokens.txt
ADDED
|
@@ -0,0 +1,360 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
_ 0
|
| 2 |
+
^ 1
|
| 3 |
+
$ 2
|
| 4 |
+
3
|
| 5 |
+
! 4
|
| 6 |
+
' 5
|
| 7 |
+
( 6
|
| 8 |
+
) 7
|
| 9 |
+
, 8
|
| 10 |
+
- 9
|
| 11 |
+
. 10
|
| 12 |
+
: 11
|
| 13 |
+
; 12
|
| 14 |
+
? 13
|
| 15 |
+
a 14
|
| 16 |
+
b 15
|
| 17 |
+
c 16
|
| 18 |
+
d 17
|
| 19 |
+
e 18
|
| 20 |
+
f 19
|
| 21 |
+
h 20
|
| 22 |
+
i 21
|
| 23 |
+
j 22
|
| 24 |
+
k 23
|
| 25 |
+
l 24
|
| 26 |
+
m 25
|
| 27 |
+
n 26
|
| 28 |
+
o 27
|
| 29 |
+
p 28
|
| 30 |
+
q 29
|
| 31 |
+
r 30
|
| 32 |
+
s 31
|
| 33 |
+
t 32
|
| 34 |
+
u 33
|
| 35 |
+
v 34
|
| 36 |
+
w 35
|
| 37 |
+
x 36
|
| 38 |
+
y 37
|
| 39 |
+
z 38
|
| 40 |
+
æ 39
|
| 41 |
+
ç 40
|
| 42 |
+
ð 41
|
| 43 |
+
ø 42
|
| 44 |
+
ħ 43
|
| 45 |
+
ŋ 44
|
| 46 |
+
œ 45
|
| 47 |
+
ǀ 46
|
| 48 |
+
ǁ 47
|
| 49 |
+
ǂ 48
|
| 50 |
+
ǃ 49
|
| 51 |
+
ɐ 50
|
| 52 |
+
ɑ 51
|
| 53 |
+
ɒ 52
|
| 54 |
+
ɓ 53
|
| 55 |
+
ɔ 54
|
| 56 |
+
ɕ 55
|
| 57 |
+
ɖ 56
|
| 58 |
+
ɗ 57
|
| 59 |
+
ɘ 58
|
| 60 |
+
ə 59
|
| 61 |
+
ɚ 60
|
| 62 |
+
ɛ 61
|
| 63 |
+
ɜ 62
|
| 64 |
+
ɞ 63
|
| 65 |
+
ɟ 64
|
| 66 |
+
ɠ 65
|
| 67 |
+
ɡ 66
|
| 68 |
+
ɢ 67
|
| 69 |
+
ɣ 68
|
| 70 |
+
ɤ 69
|
| 71 |
+
ɥ 70
|
| 72 |
+
ɦ 71
|
| 73 |
+
ɧ 72
|
| 74 |
+
ɨ 73
|
| 75 |
+
ɪ 74
|
| 76 |
+
ɫ 75
|
| 77 |
+
ɬ 76
|
| 78 |
+
ɭ 77
|
| 79 |
+
ɮ 78
|
| 80 |
+
ɯ 79
|
| 81 |
+
ɰ 80
|
| 82 |
+
ɱ 81
|
| 83 |
+
ɲ 82
|
| 84 |
+
ɳ 83
|
| 85 |
+
ɴ 84
|
| 86 |
+
ɵ 85
|
| 87 |
+
ɶ 86
|
| 88 |
+
ɸ 87
|
| 89 |
+
ɹ 88
|
| 90 |
+
ɺ 89
|
| 91 |
+
ɻ 90
|
| 92 |
+
ɽ 91
|
| 93 |
+
ɾ 92
|
| 94 |
+
ʀ 93
|
| 95 |
+
ʁ 94
|
| 96 |
+
ʂ 95
|
| 97 |
+
ʃ 96
|
| 98 |
+
ʄ 97
|
| 99 |
+
ʈ 98
|
| 100 |
+
ʉ 99
|
| 101 |
+
ʊ 100
|
| 102 |
+
ʋ 101
|
| 103 |
+
ʌ 102
|
| 104 |
+
ʍ 103
|
| 105 |
+
ʎ 104
|
| 106 |
+
ʏ 105
|
| 107 |
+
ʐ 106
|
| 108 |
+
ʑ 107
|
| 109 |
+
ʒ 108
|
| 110 |
+
ʔ 109
|
| 111 |
+
ʕ 110
|
| 112 |
+
ʘ 111
|
| 113 |
+
ʙ 112
|
| 114 |
+
ʛ 113
|
| 115 |
+
ʜ 114
|
| 116 |
+
ʝ 115
|
| 117 |
+
ʟ 116
|
| 118 |
+
ʡ 117
|
| 119 |
+
ʢ 118
|
| 120 |
+
ʲ 119
|
| 121 |
+
ˈ 120
|
| 122 |
+
ˌ 121
|
| 123 |
+
ː 122
|
| 124 |
+
ˑ 123
|
| 125 |
+
˞ 124
|
| 126 |
+
β 125
|
| 127 |
+
θ 126
|
| 128 |
+
χ 127
|
| 129 |
+
ᵻ 128
|
| 130 |
+
ⱱ 129
|
| 131 |
+
0 130
|
| 132 |
+
1 131
|
| 133 |
+
2 132
|
| 134 |
+
3 133
|
| 135 |
+
4 134
|
| 136 |
+
5 135
|
| 137 |
+
6 136
|
| 138 |
+
7 137
|
| 139 |
+
8 138
|
| 140 |
+
9 139
|
| 141 |
+
̧ 140
|
| 142 |
+
̃ 141
|
| 143 |
+
̪ 142
|
| 144 |
+
̯ 143
|
| 145 |
+
̩ 144
|
| 146 |
+
ʰ 145
|
| 147 |
+
ˤ 146
|
| 148 |
+
ε 147
|
| 149 |
+
↓ 148
|
| 150 |
+
# 149
|
| 151 |
+
" 150
|
| 152 |
+
↑ 151
|
| 153 |
+
̺ 152
|
| 154 |
+
̻ 153
|
| 155 |
+
g 154
|
| 156 |
+
ʦ 155
|
| 157 |
+
X 156
|
| 158 |
+
̝ 157
|
| 159 |
+
̊ 158
|
| 160 |
+
a1 159
|
| 161 |
+
a2 160
|
| 162 |
+
a3 161
|
| 163 |
+
a4 162
|
| 164 |
+
a5 163
|
| 165 |
+
ai1 164
|
| 166 |
+
ai2 165
|
| 167 |
+
ai3 166
|
| 168 |
+
ai4 167
|
| 169 |
+
ai5 168
|
| 170 |
+
an1 169
|
| 171 |
+
an2 170
|
| 172 |
+
an3 171
|
| 173 |
+
an4 172
|
| 174 |
+
an5 173
|
| 175 |
+
ang1 174
|
| 176 |
+
ang2 175
|
| 177 |
+
ang3 176
|
| 178 |
+
ang4 177
|
| 179 |
+
ang5 178
|
| 180 |
+
ao1 179
|
| 181 |
+
ao2 180
|
| 182 |
+
ao3 181
|
| 183 |
+
ao4 182
|
| 184 |
+
ao5 183
|
| 185 |
+
b0 184
|
| 186 |
+
c0 185
|
| 187 |
+
ch0 186
|
| 188 |
+
d0 187
|
| 189 |
+
e1 188
|
| 190 |
+
e2 189
|
| 191 |
+
e3 190
|
| 192 |
+
e4 191
|
| 193 |
+
e5 192
|
| 194 |
+
ei1 193
|
| 195 |
+
ei2 194
|
| 196 |
+
ei3 195
|
| 197 |
+
ei4 196
|
| 198 |
+
ei5 197
|
| 199 |
+
en1 198
|
| 200 |
+
en2 199
|
| 201 |
+
en3 200
|
| 202 |
+
en4 201
|
| 203 |
+
en5 202
|
| 204 |
+
eng1 203
|
| 205 |
+
eng2 204
|
| 206 |
+
eng3 205
|
| 207 |
+
eng4 206
|
| 208 |
+
eng5 207
|
| 209 |
+
er2 208
|
| 210 |
+
er3 209
|
| 211 |
+
er4 210
|
| 212 |
+
er5 211
|
| 213 |
+
f0 212
|
| 214 |
+
g0 213
|
| 215 |
+
g2 214
|
| 216 |
+
g3 215
|
| 217 |
+
g4 216
|
| 218 |
+
g5 217
|
| 219 |
+
h0 218
|
| 220 |
+
i1 219
|
| 221 |
+
i2 220
|
| 222 |
+
i3 221
|
| 223 |
+
i4 222
|
| 224 |
+
i5 223
|
| 225 |
+
ia1 224
|
| 226 |
+
ia2 225
|
| 227 |
+
ia3 226
|
| 228 |
+
ia4 227
|
| 229 |
+
ia5 228
|
| 230 |
+
ian1 229
|
| 231 |
+
ian2 230
|
| 232 |
+
ian3 231
|
| 233 |
+
ian4 232
|
| 234 |
+
ian5 233
|
| 235 |
+
iang1 234
|
| 236 |
+
iang2 235
|
| 237 |
+
iang3 236
|
| 238 |
+
iang4 237
|
| 239 |
+
iang5 238
|
| 240 |
+
iao1 239
|
| 241 |
+
iao2 240
|
| 242 |
+
iao3 241
|
| 243 |
+
iao4 242
|
| 244 |
+
iao5 243
|
| 245 |
+
ie1 244
|
| 246 |
+
ie2 245
|
| 247 |
+
ie3 246
|
| 248 |
+
ie4 247
|
| 249 |
+
ie5 248
|
| 250 |
+
in1 249
|
| 251 |
+
in2 250
|
| 252 |
+
in3 251
|
| 253 |
+
in4 252
|
| 254 |
+
in5 253
|
| 255 |
+
ing1 254
|
| 256 |
+
ing2 255
|
| 257 |
+
ing3 256
|
| 258 |
+
ing4 257
|
| 259 |
+
ing5 258
|
| 260 |
+
iong1 259
|
| 261 |
+
iong2 260
|
| 262 |
+
iong3 261
|
| 263 |
+
iong4 262
|
| 264 |
+
iu1 263
|
| 265 |
+
iu2 264
|
| 266 |
+
iu3 265
|
| 267 |
+
iu4 266
|
| 268 |
+
iu5 267
|
| 269 |
+
j0 268
|
| 270 |
+
k0 269
|
| 271 |
+
l0 270
|
| 272 |
+
m0 271
|
| 273 |
+
m1 272
|
| 274 |
+
m2 273
|
| 275 |
+
m4 274
|
| 276 |
+
m5 275
|
| 277 |
+
n0 276
|
| 278 |
+
n2 277
|
| 279 |
+
n3 278
|
| 280 |
+
n4 279
|
| 281 |
+
n5 280
|
| 282 |
+
ng5 281
|
| 283 |
+
o1 282
|
| 284 |
+
o2 283
|
| 285 |
+
o3 284
|
| 286 |
+
o4 285
|
| 287 |
+
o5 286
|
| 288 |
+
ong1 287
|
| 289 |
+
ong2 288
|
| 290 |
+
ong3 289
|
| 291 |
+
ong4 290
|
| 292 |
+
ong5 291
|
| 293 |
+
ou1 292
|
| 294 |
+
ou2 293
|
| 295 |
+
ou3 294
|
| 296 |
+
ou4 295
|
| 297 |
+
ou5 296
|
| 298 |
+
p0 297
|
| 299 |
+
q0 298
|
| 300 |
+
r0 299
|
| 301 |
+
s0 300
|
| 302 |
+
sh0 301
|
| 303 |
+
t0 302
|
| 304 |
+
u1 303
|
| 305 |
+
u2 304
|
| 306 |
+
u3 305
|
| 307 |
+
u4 306
|
| 308 |
+
u5 307
|
| 309 |
+
ua1 308
|
| 310 |
+
ua2 309
|
| 311 |
+
ua3 310
|
| 312 |
+
ua4 311
|
| 313 |
+
uai1 312
|
| 314 |
+
uai2 313
|
| 315 |
+
uai3 314
|
| 316 |
+
uai4 315
|
| 317 |
+
uai5 316
|
| 318 |
+
uan1 317
|
| 319 |
+
uan2 318
|
| 320 |
+
uan3 319
|
| 321 |
+
uan4 320
|
| 322 |
+
uan5 321
|
| 323 |
+
uang1 322
|
| 324 |
+
uang2 323
|
| 325 |
+
uang3 324
|
| 326 |
+
uang4 325
|
| 327 |
+
uang5 326
|
| 328 |
+
ue1 327
|
| 329 |
+
ue2 328
|
| 330 |
+
ue3 329
|
| 331 |
+
ue4 330
|
| 332 |
+
ui1 331
|
| 333 |
+
ui2 332
|
| 334 |
+
ui3 333
|
| 335 |
+
ui4 334
|
| 336 |
+
ui5 335
|
| 337 |
+
un1 336
|
| 338 |
+
un2 337
|
| 339 |
+
un3 338
|
| 340 |
+
un4 339
|
| 341 |
+
un5 340
|
| 342 |
+
uo1 341
|
| 343 |
+
uo2 342
|
| 344 |
+
uo3 343
|
| 345 |
+
uo4 344
|
| 346 |
+
uo5 345
|
| 347 |
+
v2 346
|
| 348 |
+
v3 347
|
| 349 |
+
v4 348
|
| 350 |
+
ve3 349
|
| 351 |
+
ve4 350
|
| 352 |
+
w0 351
|
| 353 |
+
x0 352
|
| 354 |
+
y0 353
|
| 355 |
+
z0 354
|
| 356 |
+
zh0 355
|
| 357 |
+
ê1 356
|
| 358 |
+
ê2 357
|
| 359 |
+
ê3 358
|
| 360 |
+
ê4 359
|