Duplicate from k2-fsa/ZipVoice

Co-authored-by: Han Zhu <zhu-han@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,66 @@
+---
+datasets:
+- k2-fsa/OpenDialog
+- amphion/Emilia-Dataset
+- k2-fsa/TTS_eval_datasets
+language:
+- en
+- zh
+license: apache-2.0
+pipeline_tag: text-to-speech
+tags:
+- text-to-speech
+---
+
+# ZipVoice⚡: Fast and High-Quality Zero-Shot Text-to-Speech with Flow Matching</center>
+
+This model consists of checkpoints for two fast and high-quality non-autoregressive zero-shot text-to-speech models:
+
+- **ZipVoice**, for single-speaker speech generation. Details in [paper](https://arxiv.org/abs/2506.13053) and [demo](https://zipvoice.github.io).
+
+
+- **ZipVoice-Dialog**, for spoken dialogue generation. Details in [paper](https://arxiv.org/abs/2507.09318) and [demo](https://zipvoice-dialog.github.io).
+
+See our Github repository [ZipVoice](https://github.com/k2-fsa/ZipVoice) for instructions on using our models.
+
+
+## 1. Explanation of each directory
+
+| Directory                      | Model Type                | Training Data                     | Initialized from           |
+| :---------------------------- | :-----------------------: | :-------------------------------: | :------------------------: |
+| zipvoice                       | ZipVoice                  | Emilia                            | -                          |
+| zipvoice_libritts              | ZipVoice                  | LibriTTS                          | -                          |
+| zipvoice_distill               | ZipVoice-Distill          | Emilia                            | zipvoice/model.pt          |
+| zipvoice_distill_libritts      | ZipVoice-Distill          | LibriTTS                          | zipvoice_libritts/model.pt |
+| zipvoice_dialog                | ZipVoice-Dialog           | OpenDialog + in-house dataset     | zipvoice/model.pt          |
+| zipvoice_dialog_opendialog     | ZipVoice-Dialog           | OpenDialog                        | zipvoice/model.pt          |
+| zipvoice_dialog_stereo         | ZipVoice-Dialog-Stereo    | in-house dataset                  | zipvoice_dialog/model.pt   |
+
+
+## 2. Discussion & Communication
+
+You can directly discuss on [Github Issues](https://github.com/k2-fsa/ZipVoice/issues).
+
+You can also scan the QR code to join our wechat group or follow our wechat official account.
+
+| Wechat Group | Wechat Official Account |
+| ------------ | ----------------------- |
+|![wechat](https://k2-fsa.org/zh-CN/assets/pic/wechat_group.jpg) |![wechat](https://k2-fsa.org/zh-CN/assets/pic/wechat_account.jpg) |
+
+## 3. Citation
+
+```bibtex
+@article{zhu2025zipvoice,
+      title={ZipVoice: Fast and High-Quality Zero-Shot Text-to-Speech with Flow Matching},
+      author={Zhu, Han and Kang, Wei and Yao, Zengwei and Guo, Liyong and Kuang, Fangjun and Li, Zhaoqing and Zhuang, Weiji and Lin, Long and Povey, Daniel},
+      journal={arXiv preprint arXiv:2506.13053},
+      year={2025}
+}
+
+@article{zhu2025zipvoicedialog,
+      title={ZipVoice-Dialog: Non-Autoregressive Spoken Dialogue Generation with Flow Matching},
+      author={Zhu, Han and Kang, Wei and Guo, Liyong and Yao, Zengwei and Kuang, Fangjun and Zhuang, Weiji and Li, Zhaoqing and Han, Zhifeng and Zhang, Dong and Zhang, Xin and Song, Xingchen and Lin, Long and Povey, Daniel},
+      journal={arXiv preprint arXiv:2507.09318},
+      year={2025}
+}
+```

zipvoice/fm_decoder.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb57eff934f18082f9e8af8bc217b2ec296d2ea763ad3f2907a7486ef51f7712
+size 477386712

zipvoice/fm_decoder_int8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6892115f6c6d78032a9e4b2fb6ca56a08e9b44cf4b8ed32e28fb17daaa4e3e17
+size 124620066

zipvoice/model.json

@@ -0,0 +1,26 @@
+{
+  "model" : {
+    "fm_decoder_downsampling_factor" : [1,2,4,2,1],
+    "fm_decoder_num_layers" : [2,2,4,4,4],
+    "fm_decoder_cnn_module_kernel" : [31,15,7,15,31],
+    "fm_decoder_feedforward_dim" : 1536,
+    "fm_decoder_num_heads" : 4,
+    "fm_decoder_dim" : 512,
+    "text_encoder_num_layers" : 4,
+    "text_encoder_feedforward_dim" : 512,
+    "text_encoder_cnn_module_kernel" : 9,
+    "text_encoder_num_heads" : 4,
+    "text_encoder_dim" : 192,
+    "query_head_dim" : 32,
+    "value_head_dim" : 12,
+    "pos_head_dim" : 4,
+    "pos_dim" : 48,
+    "time_embed_dim" : 192,
+    "text_embed_dim" : 192,
+    "feat_dim": 100
+  },
+  "feature" : {
+    "sampling_rate": 24000,
+    "type": "vocos"
+  }
+}

zipvoice/model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99e6cc91bd13ee6ccffc0aa7c8c3bd9941423de290d057f2424ab89d6c5352f4
+size 491161451

zipvoice/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:172a20b18f41e3453ae5dc6551e9fef4924dc1ac30ecd50b763226c9538afdce
+size 490777328

zipvoice/text_encoder.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85e9b4c4a23e1464070fc72701d21a84b5df55aa182db3e5a24a33bed6cb831f
+size 17633735

zipvoice/text_encoder_int8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1184e5e68005af4a48da274f894dae6ee6c38c9ea0cf5538518a1b7275ff999
+size 5570211

zipvoice/tokens.txt

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

zipvoice/zipvoice_base.json

@@ -0,0 +1,26 @@
+{
+  "model" : {
+    "fm_decoder_downsampling_factor" : [1,2,4,2,1],
+    "fm_decoder_num_layers" : [2,2,4,4,4],
+    "fm_decoder_cnn_module_kernel" : [31,15,7,15,31],
+    "fm_decoder_feedforward_dim" : 1536,
+    "fm_decoder_num_heads" : 4,
+    "fm_decoder_dim" : 512,
+    "text_encoder_num_layers" : 4,
+    "text_encoder_feedforward_dim" : 512,
+    "text_encoder_cnn_module_kernel" : 9,
+    "text_encoder_num_heads" : 4,
+    "text_encoder_dim" : 192,
+    "query_head_dim" : 32,
+    "value_head_dim" : 12,
+    "pos_head_dim" : 4,
+    "pos_dim" : 48,
+    "time_embed_dim" : 192,
+    "text_embed_dim" : 192,
+    "feat_dim": 100
+  },
+  "feature" : {
+    "sampling_rate": 24000,
+    "type": "vocos"
+  }
+}

zipvoice_dialog/model.json

@@ -0,0 +1,26 @@
+{
+  "model" : {
+    "fm_decoder_downsampling_factor" : [1,2,4,2,1],
+    "fm_decoder_num_layers" : [2,2,4,4,4],
+    "fm_decoder_cnn_module_kernel" : [31,15,7,15,31],
+    "fm_decoder_feedforward_dim" : 1536,
+    "fm_decoder_num_heads" : 4,
+    "fm_decoder_dim" : 512,
+    "text_encoder_num_layers" : 4,
+    "text_encoder_feedforward_dim" : 512,
+    "text_encoder_cnn_module_kernel" : 9,
+    "text_encoder_num_heads" : 4,
+    "text_encoder_dim" : 192,
+    "query_head_dim" : 32,
+    "value_head_dim" : 12,
+    "pos_head_dim" : 4,
+    "pos_dim" : 48,
+    "time_embed_dim" : 192,
+    "text_embed_dim" : 192,
+    "feat_dim": 100
+  },
+  "feature" : {
+    "sampling_rate": 24000,
+    "type": "vocos"
+  }
+}

zipvoice_dialog/model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3aac4a58f1b42482b023efd72507ea88a110228f4016d3409fe0349e90f280c5
+size 491185836

zipvoice_dialog/tokens.txt

@@ -0,0 +1,388 @@
+_	0
+^	1
+$	2
+ 	3
+!	4
+'	5
+(	6
+)	7
+,	8
+-	9
+.	10
+:	11
+;	12
+?	13
+a	14
+b	15
+c	16
+d	17
+e	18
+f	19
+h	20
+i	21
+j	22
+k	23
+l	24
+m	25
+n	26
+o	27
+p	28
+q	29
+r	30
+s	31
+t	32
+u	33
+v	34
+w	35
+x	36
+y	37
+z	38
+æ	39
+ç	40
+ð	41
+ø	42
+ħ	43
+ŋ	44
+œ	45
+ǀ	46
+ǁ	47
+ǂ	48
+ǃ	49
+ɐ	50
+ɑ	51
+ɒ	52
+ɓ	53
+ɔ	54
+ɕ	55
+ɖ	56
+ɗ	57
+ɘ	58
+ə	59
+ɚ	60
+ɛ	61
+ɜ	62
+ɞ	63
+ɟ	64
+ɠ	65
+ɡ	66
+ɢ	67
+ɣ	68
+ɤ	69
+ɥ	70
+ɦ	71
+ɧ	72
+ɨ	73
+ɪ	74
+ɫ	75
+ɬ	76
+ɭ	77
+ɮ	78
+ɯ	79
+ɰ	80
+ɱ	81
+ɲ	82
+ɳ	83
+ɴ	84
+ɵ	85
+ɶ	86
+ɸ	87
+ɹ	88
+ɺ	89
+ɻ	90
+ɽ	91
+ɾ	92
+ʀ	93
+ʁ	94
+ʂ	95
+ʃ	96
+ʄ	97
+ʈ	98
+ʉ	99
+ʊ	100
+ʋ	101
+ʌ	102
+ʍ	103
+ʎ	104
+ʏ	105
+ʐ	106
+ʑ	107
+ʒ	108
+ʔ	109
+ʕ	110
+ʘ	111
+ʙ	112
+ʛ	113
+ʜ	114
+ʝ	115
+ʟ	116
+ʡ	117
+ʢ	118
+ʲ	119
+ˈ	120
+ˌ	121
+ː	122
+ˑ	123
+˞	124
+β	125
+θ	126
+χ	127
+ᵻ	128
+ⱱ	129
+0	130
+1	131
+2	132
+3	133
+4	134
+5	135
+6	136
+7	137
+8	138
+9	139
+̧	140
+̃	141
+̪	142
+̯	143
+̩	144
+ʰ	145
+ˤ	146
+ε	147
+↓	148
+#	149
+"	150
+↑	151
+̺	152
+̻	153
+g	154
+ʦ	155
+X	156
+̝	157
+̊	158
+a1	159
+a2	160
+a3	161
+a4	162
+a5	163
+ai1	164
+ai2	165
+ai3	166
+ai4	167
+ai5	168
+an1	169
+an2	170
+an3	171
+an4	172
+an5	173
+ang1	174
+ang2	175
+ang3	176
+ang4	177
+ang5	178
+ao1	179
+ao2	180
+ao3	181
+ao4	182
+ao5	183
+b0	184
+c0	185
+ch0	186
+d0	187
+e1	188
+e2	189
+e3	190
+e4	191
+e5	192
+ei1	193
+ei2	194
+ei3	195
+ei4	196
+ei5	197
+en1	198
+en2	199
+en3	200
+en4	201
+en5	202
+eng1	203
+eng2	204
+eng3	205
+eng4	206
+eng5	207
+er2	208
+er3	209
+er4	210
+er5	211
+f0	212
+g0	213
+g2	214
+g3	215
+g4	216
+g5	217
+h0	218
+i1	219
+i2	220
+i3	221
+i4	222
+i5	223
+ia1	224
+ia2	225
+ia3	226
+ia4	227
+ia5	228
+ian1	229
+ian2	230
+ian3	231
+ian4	232
+ian5	233
+iang1	234
+iang2	235
+iang3	236
+iang4	237
+iang5	238
+iao1	239
+iao2	240
+iao3	241
+iao4	242
+iao5	243
+ie1	244
+ie2	245
+ie3	246
+ie4	247
+ie5	248
+in1	249
+in2	250
+in3	251
+in4	252
+in5	253
+ing1	254
+ing2	255
+ing3	256
+ing4	257
+ing5	258
+iong1	259
+iong2	260
+iong3	261
+iong4	262
+iu1	263
+iu2	264
+iu3	265
+iu4	266
+iu5	267
+j0	268
+k0	269
+l0	270
+m0	271
+m1	272
+m2	273
+m4	274
+m5	275
+n0	276
+n2	277
+n3	278
+n4	279
+n5	280
+ng5	281
+o1	282
+o2	283
+o3	284
+o4	285
+o5	286
+ong1	287
+ong2	288
+ong3	289
+ong4	290
+ong5	291
+ou1	292
+ou2	293
+ou3	294
+ou4	295
+ou5	296
+p0	297
+q0	298
+r0	299
+s0	300
+sh0	301
+t0	302
+u1	303
+u2	304
+u3	305
+u4	306
+u5	307
+ua1	308
+ua2	309
+ua3	310
+ua4	311
+uai1	312
+uai2	313
+uai3	314
+uai4	315
+uai5	316
+uan1	317
+uan2	318
+uan3	319
+uan4	320
+uan5	321
+uang1	322
+uang2	323
+uang3	324
+uang4	325
+uang5	326
+ue1	327
+ue2	328
+ue3	329
+ue4	330
+ui1	331
+ui2	332
+ui3	333
+ui4	334
+ui5	335
+un1	336
+un2	337
+un3	338
+un4	339
+un5	340
+uo1	341
+uo2	342
+uo3	343
+uo4	344
+uo5	345
+v2	346
+v3	347
+v4	348
+ve3	349
+ve4	350
+w0	351
+x0	352
+y0	353
+z0	354
+zh0	355
+ê1	356
+ê2	357
+ê3	358
+ê4	359
+[S1]	360
+[S2]	361
+[FIL/]	362
+[SPK/]	363
+[STA/]	364
+[NON/]	365
+[NPS/]	366
+[LAUGHS]	367
+[CLEARS THROAT]	368
+[SIGHS]	369
+[GASPS]	370
+[COUGHS]	371
+[SINGING]	372
+[SINGS]	373
+[MUMBLES]	374
+[BEEP]	375
+[GROANS]	376
+[SNIFFS]	377
+[CLAPS]	378
+[SCREAMS]	379
+[INHALES]	380
+[EXHALES]	381
+[APPLAUSE]	382
+[BURPS]	383
+[HUMMING]	384
+[SNEEZES]	385
+[CHUCKLE]	386
+[WHISTLES]	387

zipvoice_dialog/zipvoice_base.json

@@ -0,0 +1,26 @@
+{
+  "model" : {
+    "fm_decoder_downsampling_factor" : [1,2,4,2,1],
+    "fm_decoder_num_layers" : [2,2,4,4,4],
+    "fm_decoder_cnn_module_kernel" : [31,15,7,15,31],
+    "fm_decoder_feedforward_dim" : 1536,
+    "fm_decoder_num_heads" : 4,
+    "fm_decoder_dim" : 512,
+    "text_encoder_num_layers" : 4,
+    "text_encoder_feedforward_dim" : 512,
+    "text_encoder_cnn_module_kernel" : 9,
+    "text_encoder_num_heads" : 4,
+    "text_encoder_dim" : 192,
+    "query_head_dim" : 32,
+    "value_head_dim" : 12,
+    "pos_head_dim" : 4,
+    "pos_dim" : 48,
+    "time_embed_dim" : 192,
+    "text_embed_dim" : 192,
+    "feat_dim": 100
+  },
+  "feature" : {
+    "sampling_rate": 24000,
+    "type": "vocos"
+  }
+}

zipvoice_dialog_opendialog/model.json

@@ -0,0 +1,26 @@
+{
+  "model" : {
+    "fm_decoder_downsampling_factor" : [1,2,4,2,1],
+    "fm_decoder_num_layers" : [2,2,4,4,4],
+    "fm_decoder_cnn_module_kernel" : [31,15,7,15,31],
+    "fm_decoder_feedforward_dim" : 1536,
+    "fm_decoder_num_heads" : 4,
+    "fm_decoder_dim" : 512,
+    "text_encoder_num_layers" : 4,
+    "text_encoder_feedforward_dim" : 512,
+    "text_encoder_cnn_module_kernel" : 9,
+    "text_encoder_num_heads" : 4,
+    "text_encoder_dim" : 192,
+    "query_head_dim" : 32,
+    "value_head_dim" : 12,
+    "pos_head_dim" : 4,
+    "pos_dim" : 48,
+    "time_embed_dim" : 192,
+    "text_embed_dim" : 192,
+    "feat_dim": 100
+  },
+  "feature" : {
+    "sampling_rate": 24000,
+    "type": "vocos"
+  }
+}

zipvoice_dialog_opendialog/model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46fb26a729bf97af293f266e6c86165796fff94656f9223fbfa5d1496baaf353
+size 491185836

zipvoice_dialog_opendialog/tokens.txt

@@ -0,0 +1,388 @@
+_	0
+^	1
+$	2
+ 	3
+!	4
+'	5
+(	6
+)	7
+,	8
+-	9
+.	10
+:	11
+;	12
+?	13
+a	14
+b	15
+c	16
+d	17
+e	18
+f	19
+h	20
+i	21
+j	22
+k	23
+l	24
+m	25
+n	26
+o	27
+p	28
+q	29
+r	30
+s	31
+t	32
+u	33
+v	34
+w	35
+x	36
+y	37
+z	38
+æ	39
+ç	40
+ð	41
+ø	42
+ħ	43
+ŋ	44
+œ	45
+ǀ	46
+ǁ	47
+ǂ	48
+ǃ	49
+ɐ	50
+ɑ	51
+ɒ	52
+ɓ	53
+ɔ	54
+ɕ	55
+ɖ	56
+ɗ	57
+ɘ	58
+ə	59
+ɚ	60
+ɛ	61
+ɜ	62
+ɞ	63
+ɟ	64
+ɠ	65
+ɡ	66
+ɢ	67
+ɣ	68
+ɤ	69
+ɥ	70
+ɦ	71
+ɧ	72
+ɨ	73
+ɪ	74
+ɫ	75
+ɬ	76
+ɭ	77
+ɮ	78
+ɯ	79
+ɰ	80
+ɱ	81
+ɲ	82
+ɳ	83
+ɴ	84
+ɵ	85
+ɶ	86
+ɸ	87
+ɹ	88
+ɺ	89
+ɻ	90
+ɽ	91
+ɾ	92
+ʀ	93
+ʁ	94
+ʂ	95
+ʃ	96
+ʄ	97
+ʈ	98
+ʉ	99
+ʊ	100
+ʋ	101
+ʌ	102
+ʍ	103
+ʎ	104
+ʏ	105
+ʐ	106
+ʑ	107
+ʒ	108
+ʔ	109
+ʕ	110
+ʘ	111
+ʙ	112
+ʛ	113
+ʜ	114
+ʝ	115
+ʟ	116
+ʡ	117
+ʢ	118
+ʲ	119
+ˈ	120
+ˌ	121
+ː	122
+ˑ	123
+˞	124
+β	125
+θ	126
+χ	127
+ᵻ	128
+ⱱ	129
+0	130
+1	131
+2	132
+3	133
+4	134
+5	135
+6	136
+7	137
+8	138
+9	139
+̧	140
+̃	141
+̪	142
+̯	143
+̩	144
+ʰ	145
+ˤ	146
+ε	147
+↓	148
+#	149
+"	150
+↑	151
+̺	152
+̻	153
+g	154
+ʦ	155
+X	156
+̝	157
+̊	158
+a1	159
+a2	160
+a3	161
+a4	162
+a5	163
+ai1	164
+ai2	165
+ai3	166
+ai4	167
+ai5	168
+an1	169
+an2	170
+an3	171
+an4	172
+an5	173
+ang1	174
+ang2	175
+ang3	176
+ang4	177
+ang5	178
+ao1	179
+ao2	180
+ao3	181
+ao4	182
+ao5	183
+b0	184
+c0	185
+ch0	186
+d0	187
+e1	188
+e2	189
+e3	190
+e4	191
+e5	192
+ei1	193
+ei2	194
+ei3	195
+ei4	196
+ei5	197
+en1	198
+en2	199
+en3	200
+en4	201
+en5	202
+eng1	203
+eng2	204
+eng3	205
+eng4	206
+eng5	207
+er2	208
+er3	209
+er4	210
+er5	211
+f0	212
+g0	213
+g2	214
+g3	215
+g4	216
+g5	217
+h0	218
+i1	219
+i2	220
+i3	221
+i4	222
+i5	223
+ia1	224
+ia2	225
+ia3	226
+ia4	227
+ia5	228
+ian1	229
+ian2	230
+ian3	231
+ian4	232
+ian5	233
+iang1	234
+iang2	235
+iang3	236
+iang4	237
+iang5	238
+iao1	239
+iao2	240
+iao3	241
+iao4	242
+iao5	243
+ie1	244
+ie2	245
+ie3	246
+ie4	247
+ie5	248
+in1	249
+in2	250
+in3	251
+in4	252
+in5	253
+ing1	254
+ing2	255
+ing3	256
+ing4	257
+ing5	258
+iong1	259
+iong2	260
+iong3	261
+iong4	262
+iu1	263
+iu2	264
+iu3	265
+iu4	266
+iu5	267
+j0	268
+k0	269
+l0	270
+m0	271
+m1	272
+m2	273
+m4	274
+m5	275
+n0	276
+n2	277
+n3	278
+n4	279
+n5	280
+ng5	281
+o1	282
+o2	283
+o3	284
+o4	285
+o5	286
+ong1	287
+ong2	288
+ong3	289
+ong4	290
+ong5	291
+ou1	292
+ou2	293
+ou3	294
+ou4	295
+ou5	296
+p0	297
+q0	298
+r0	299
+s0	300
+sh0	301
+t0	302
+u1	303
+u2	304
+u3	305
+u4	306
+u5	307
+ua1	308
+ua2	309
+ua3	310
+ua4	311
+uai1	312
+uai2	313
+uai3	314
+uai4	315
+uai5	316
+uan1	317
+uan2	318
+uan3	319
+uan4	320
+uan5	321
+uang1	322
+uang2	323
+uang3	324
+uang4	325
+uang5	326
+ue1	327
+ue2	328
+ue3	329
+ue4	330
+ui1	331
+ui2	332
+ui3	333
+ui4	334
+ui5	335
+un1	336
+un2	337
+un3	338
+un4	339
+un5	340
+uo1	341
+uo2	342
+uo3	343
+uo4	344
+uo5	345
+v2	346
+v3	347
+v4	348
+ve3	349
+ve4	350
+w0	351
+x0	352
+y0	353
+z0	354
+zh0	355
+ê1	356
+ê2	357
+ê3	358
+ê4	359
+[S1]	360
+[S2]	361
+[FIL/]	362
+[SPK/]	363
+[STA/]	364
+[NON/]	365
+[NPS/]	366
+[LAUGHS]	367
+[CLEARS THROAT]	368
+[SIGHS]	369
+[GASPS]	370
+[COUGHS]	371
+[SINGING]	372
+[SINGS]	373
+[MUMBLES]	374
+[BEEP]	375
+[GROANS]	376
+[SNIFFS]	377
+[CLAPS]	378
+[SCREAMS]	379
+[INHALES]	380
+[EXHALES]	381
+[APPLAUSE]	382
+[BURPS]	383
+[HUMMING]	384
+[SNEEZES]	385
+[CHUCKLE]	386
+[WHISTLES]	387

zipvoice_dialog_opendialog/zipvoice_base.json

@@ -0,0 +1,26 @@
+{
+  "model" : {
+    "fm_decoder_downsampling_factor" : [1,2,4,2,1],
+    "fm_decoder_num_layers" : [2,2,4,4,4],
+    "fm_decoder_cnn_module_kernel" : [31,15,7,15,31],
+    "fm_decoder_feedforward_dim" : 1536,
+    "fm_decoder_num_heads" : 4,
+    "fm_decoder_dim" : 512,
+    "text_encoder_num_layers" : 4,
+    "text_encoder_feedforward_dim" : 512,
+    "text_encoder_cnn_module_kernel" : 9,
+    "text_encoder_num_heads" : 4,
+    "text_encoder_dim" : 192,
+    "query_head_dim" : 32,
+    "value_head_dim" : 12,
+    "pos_head_dim" : 4,
+    "pos_dim" : 48,
+    "time_embed_dim" : 192,
+    "text_embed_dim" : 192,
+    "feat_dim": 100
+  },
+  "feature" : {
+    "sampling_rate": 24000,
+    "type": "vocos"
+  }
+}

zipvoice_dialog_stereo/model.json

@@ -0,0 +1,26 @@
+{
+  "model" : {
+    "fm_decoder_downsampling_factor" : [1,2,4,2,1],
+    "fm_decoder_num_layers" : [2,2,4,4,4],
+    "fm_decoder_cnn_module_kernel" : [31,15,7,15,31],
+    "fm_decoder_feedforward_dim" : 1536,
+    "fm_decoder_num_heads" : 4,
+    "fm_decoder_dim" : 512,
+    "text_encoder_num_layers" : 4,
+    "text_encoder_feedforward_dim" : 512,
+    "text_encoder_cnn_module_kernel" : 9,
+    "text_encoder_num_heads" : 4,
+    "text_encoder_dim" : 192,
+    "query_head_dim" : 32,
+    "value_head_dim" : 12,
+    "pos_head_dim" : 4,
+    "pos_dim" : 48,
+    "time_embed_dim" : 192,
+    "text_embed_dim" : 192,
+    "feat_dim": 100
+  },
+  "feature" : {
+    "sampling_rate": 24000,
+    "type": "vocos"
+  }
+}

zipvoice_dialog_stereo/model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78d90e3d6375be18dcf9d8a7461c0c6ecba79a37b8d433429759a6757fca31ef
+size 492622790

zipvoice_dialog_stereo/tokens.txt

@@ -0,0 +1,388 @@
+_	0
+^	1
+$	2
+ 	3
+!	4
+'	5
+(	6
+)	7
+,	8
+-	9
+.	10
+:	11
+;	12
+?	13
+a	14
+b	15
+c	16
+d	17
+e	18
+f	19
+h	20
+i	21
+j	22
+k	23
+l	24
+m	25
+n	26
+o	27
+p	28
+q	29
+r	30
+s	31
+t	32
+u	33
+v	34
+w	35
+x	36
+y	37
+z	38
+æ	39
+ç	40
+ð	41
+ø	42
+ħ	43
+ŋ	44
+œ	45
+ǀ	46
+ǁ	47
+ǂ	48
+ǃ	49
+ɐ	50
+ɑ	51
+ɒ	52
+ɓ	53
+ɔ	54
+ɕ	55
+ɖ	56
+ɗ	57
+ɘ	58
+ə	59
+ɚ	60
+ɛ	61
+ɜ	62
+ɞ	63
+ɟ	64
+ɠ	65
+ɡ	66
+ɢ	67
+ɣ	68
+ɤ	69
+ɥ	70
+ɦ	71
+ɧ	72
+ɨ	73
+ɪ	74
+ɫ	75
+ɬ	76
+ɭ	77
+ɮ	78
+ɯ	79
+ɰ	80
+ɱ	81
+ɲ	82
+ɳ	83
+ɴ	84
+ɵ	85
+ɶ	86
+ɸ	87
+ɹ	88
+ɺ	89
+ɻ	90
+ɽ	91
+ɾ	92
+ʀ	93
+ʁ	94
+ʂ	95
+ʃ	96
+ʄ	97
+ʈ	98
+ʉ	99
+ʊ	100
+ʋ	101
+ʌ	102
+ʍ	103
+ʎ	104
+ʏ	105
+ʐ	106
+ʑ	107
+ʒ	108
+ʔ	109
+ʕ	110
+ʘ	111
+ʙ	112
+ʛ	113
+ʜ	114
+ʝ	115
+ʟ	116
+ʡ	117
+ʢ	118
+ʲ	119
+ˈ	120
+ˌ	121
+ː	122
+ˑ	123
+˞	124
+β	125
+θ	126
+χ	127
+ᵻ	128
+ⱱ	129
+0	130
+1	131
+2	132
+3	133
+4	134
+5	135
+6	136
+7	137
+8	138
+9	139
+̧	140
+̃	141
+̪	142
+̯	143
+̩	144
+ʰ	145
+ˤ	146
+ε	147
+↓	148
+#	149
+"	150
+↑	151
+̺	152
+̻	153
+g	154
+ʦ	155
+X	156
+̝	157
+̊	158
+a1	159
+a2	160
+a3	161
+a4	162
+a5	163
+ai1	164
+ai2	165
+ai3	166
+ai4	167
+ai5	168
+an1	169
+an2	170
+an3	171
+an4	172
+an5	173
+ang1	174
+ang2	175
+ang3	176
+ang4	177
+ang5	178
+ao1	179
+ao2	180
+ao3	181
+ao4	182
+ao5	183
+b0	184
+c0	185
+ch0	186
+d0	187
+e1	188
+e2	189
+e3	190
+e4	191
+e5	192
+ei1	193
+ei2	194
+ei3	195
+ei4	196
+ei5	197
+en1	198
+en2	199
+en3	200
+en4	201
+en5	202
+eng1	203
+eng2	204
+eng3	205
+eng4	206
+eng5	207
+er2	208
+er3	209
+er4	210
+er5	211
+f0	212
+g0	213
+g2	214
+g3	215
+g4	216
+g5	217
+h0	218
+i1	219
+i2	220
+i3	221
+i4	222
+i5	223
+ia1	224
+ia2	225
+ia3	226
+ia4	227
+ia5	228
+ian1	229
+ian2	230
+ian3	231
+ian4	232
+ian5	233
+iang1	234
+iang2	235
+iang3	236
+iang4	237
+iang5	238
+iao1	239
+iao2	240
+iao3	241
+iao4	242
+iao5	243
+ie1	244
+ie2	245
+ie3	246
+ie4	247
+ie5	248
+in1	249
+in2	250
+in3	251
+in4	252
+in5	253
+ing1	254
+ing2	255
+ing3	256
+ing4	257
+ing5	258
+iong1	259
+iong2	260
+iong3	261
+iong4	262
+iu1	263
+iu2	264
+iu3	265
+iu4	266
+iu5	267
+j0	268
+k0	269
+l0	270
+m0	271
+m1	272
+m2	273
+m4	274
+m5	275
+n0	276
+n2	277
+n3	278
+n4	279
+n5	280
+ng5	281
+o1	282
+o2	283
+o3	284
+o4	285
+o5	286
+ong1	287
+ong2	288
+ong3	289
+ong4	290
+ong5	291
+ou1	292
+ou2	293
+ou3	294
+ou4	295
+ou5	296
+p0	297
+q0	298
+r0	299
+s0	300
+sh0	301
+t0	302
+u1	303
+u2	304
+u3	305
+u4	306
+u5	307
+ua1	308
+ua2	309
+ua3	310
+ua4	311
+uai1	312
+uai2	313
+uai3	314
+uai4	315
+uai5	316
+uan1	317
+uan2	318
+uan3	319
+uan4	320
+uan5	321
+uang1	322
+uang2	323
+uang3	324
+uang4	325
+uang5	326
+ue1	327
+ue2	328
+ue3	329
+ue4	330
+ui1	331
+ui2	332
+ui3	333
+ui4	334
+ui5	335
+un1	336
+un2	337
+un3	338
+un4	339
+un5	340
+uo1	341
+uo2	342
+uo3	343
+uo4	344
+uo5	345
+v2	346
+v3	347
+v4	348
+ve3	349
+ve4	350
+w0	351
+x0	352
+y0	353
+z0	354
+zh0	355
+ê1	356
+ê2	357
+ê3	358
+ê4	359
+[S1]	360
+[S2]	361
+[FIL/]	362
+[SPK/]	363
+[STA/]	364
+[NON/]	365
+[NPS/]	366
+[LAUGHS]	367
+[CLEARS THROAT]	368
+[SIGHS]	369
+[GASPS]	370
+[COUGHS]	371
+[SINGING]	372
+[SINGS]	373
+[MUMBLES]	374
+[BEEP]	375
+[GROANS]	376
+[SNIFFS]	377
+[CLAPS]	378
+[SCREAMS]	379
+[INHALES]	380
+[EXHALES]	381
+[APPLAUSE]	382
+[BURPS]	383
+[HUMMING]	384
+[SNEEZES]	385
+[CHUCKLE]	386
+[WHISTLES]	387

zipvoice_dialog_stereo/zipvoice_base.json

@@ -0,0 +1,26 @@
+{
+  "model" : {
+    "fm_decoder_downsampling_factor" : [1,2,4,2,1],
+    "fm_decoder_num_layers" : [2,2,4,4,4],
+    "fm_decoder_cnn_module_kernel" : [31,15,7,15,31],
+    "fm_decoder_feedforward_dim" : 1536,
+    "fm_decoder_num_heads" : 4,
+    "fm_decoder_dim" : 512,
+    "text_encoder_num_layers" : 4,
+    "text_encoder_feedforward_dim" : 512,
+    "text_encoder_cnn_module_kernel" : 9,
+    "text_encoder_num_heads" : 4,
+    "text_encoder_dim" : 192,
+    "query_head_dim" : 32,
+    "value_head_dim" : 12,
+    "pos_head_dim" : 4,
+    "pos_dim" : 48,
+    "time_embed_dim" : 192,
+    "text_embed_dim" : 192,
+    "feat_dim": 100
+  },
+  "feature" : {
+    "sampling_rate": 24000,
+    "type": "vocos"
+  }
+}

zipvoice_distill/fm_decoder.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4510d4f5f049f14ef80207fca695e13c820e2cea61635f402954950bc62b1e3c
+size 477534010

zipvoice_distill/fm_decoder_int8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cc2e08a96610d7ea1b227398e97cdbbe0414499741d3aec0b8113db2a2ab251
+size 124657100

zipvoice_distill/model.json

@@ -0,0 +1,26 @@
+{
+  "model" : {
+    "fm_decoder_downsampling_factor" : [1,2,4,2,1],
+    "fm_decoder_num_layers" : [2,2,4,4,4],
+    "fm_decoder_cnn_module_kernel" : [31,15,7,15,31],
+    "fm_decoder_feedforward_dim" : 1536,
+    "fm_decoder_num_heads" : 4,
+    "fm_decoder_dim" : 512,
+    "text_encoder_num_layers" : 4,
+    "text_encoder_feedforward_dim" : 512,
+    "text_encoder_cnn_module_kernel" : 9,
+    "text_encoder_num_heads" : 4,
+    "text_encoder_dim" : 192,
+    "query_head_dim" : 32,
+    "value_head_dim" : 12,
+    "pos_head_dim" : 4,
+    "pos_dim" : 48,
+    "time_embed_dim" : 192,
+    "text_embed_dim" : 192,
+    "feat_dim": 100
+  },
+  "feature" : {
+    "sampling_rate": 24000,
+    "type": "vocos"
+  }
+}

zipvoice_distill/model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:745855037478eb888cfa7a3603c1aa9f663f22a72d94cc1c37787228ff422095
+size 491318136

zipvoice_distill/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a2580c60d47997be75e0b945740169efa2c151cb7f4f0c1b63ddd6ab76dd789
+size 490924896

zipvoice_distill/text_encoder.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:495eca2d5f8a911f5c361bcce5bd55cdd2508ccdd26ce3e9bf1d3c29eb974861
+size 17633735

zipvoice_distill/text_encoder_int8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2de9a761a85e5ddd125dee6e05bad1c7ee92c11b83b4d775dab216a6aa41379
+size 5570211

zipvoice_distill/tokens.txt

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

zipvoice_distill/zipvoice_base.json

@@ -0,0 +1,26 @@
+{
+  "model" : {
+    "fm_decoder_downsampling_factor" : [1,2,4,2,1],
+    "fm_decoder_num_layers" : [2,2,4,4,4],
+    "fm_decoder_cnn_module_kernel" : [31,15,7,15,31],
+    "fm_decoder_feedforward_dim" : 1536,
+    "fm_decoder_num_heads" : 4,
+    "fm_decoder_dim" : 512,
+    "text_encoder_num_layers" : 4,
+    "text_encoder_feedforward_dim" : 512,
+    "text_encoder_cnn_module_kernel" : 9,
+    "text_encoder_num_heads" : 4,
+    "text_encoder_dim" : 192,
+    "query_head_dim" : 32,
+    "value_head_dim" : 12,
+    "pos_head_dim" : 4,
+    "pos_dim" : 48,
+    "time_embed_dim" : 192,
+    "text_embed_dim" : 192,
+    "feat_dim": 100
+  },
+  "feature" : {
+    "sampling_rate": 24000,
+    "type": "vocos"
+  }
+}

zipvoice_distill_libritts/model.json

@@ -0,0 +1,26 @@
+{
+  "model" : {
+    "fm_decoder_downsampling_factor" : [1,2,4,2,1],
+    "fm_decoder_num_layers" : [2,2,4,4,4],
+    "fm_decoder_cnn_module_kernel" : [31,15,7,15,31],
+    "fm_decoder_feedforward_dim" : 1536,
+    "fm_decoder_num_heads" : 4,
+    "fm_decoder_dim" : 512,
+    "text_encoder_num_layers" : 4,
+    "text_encoder_feedforward_dim" : 512,
+    "text_encoder_cnn_module_kernel" : 9,
+    "text_encoder_num_heads" : 4,
+    "text_encoder_dim" : 192,
+    "query_head_dim" : 32,
+    "value_head_dim" : 12,
+    "pos_head_dim" : 4,
+    "pos_dim" : 48,
+    "time_embed_dim" : 192,
+    "text_embed_dim" : 192,
+    "feat_dim": 100
+  },
+  "feature" : {
+    "sampling_rate": 24000,
+    "type": "vocos"
+  }
+}

zipvoice_distill_libritts/model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a02e60235678b7ca34cf70bfefd77dbb900267d7e119a63d71bcb5195a07d18f
+size 491092530

zipvoice_distill_libritts/tokens.txt

@@ -0,0 +1,79 @@
+_	0
+ 	1
+e	2
+t	3
+a	4
+o	5
+n	6
+h	7
+i	8
+s	9
+r	10
+d	11
+l	12
+u	13
+m	14
+c	15
+w	16
+f	17
+y	18
+g	19
+,	20
+p	21
+b	22
+.	23
+v	24
+k	25
+"	26
+I	27
+'	28
+T	29
+A	30
+H	31
+S	32
+;	33
+W	34
+-	35
+x	36
+B	37
+?	38
+M	39
+C	40
+!	41
+j	42
+q	43
+N	44
+E	45
+O	46
+P	47
+D	48
+L	49
+G	50
+R	51
+Y	52
+F	53
+z	54
+:	55
+J	56
+K	57
+U	58
+V	59
+)	60
+(	61
+Q	62
+Z	63
+X	64
+]	65
+[	66
+—	67
+/	68
+æ	69
+é	70
+ñ	71
+œ	72
+}	73
+{	74
+ê	75
+¯	76
+è	77
+ô	78

zipvoice_distill_libritts/zipvoice_base.json

@@ -0,0 +1,26 @@
+{
+  "model" : {
+    "fm_decoder_downsampling_factor" : [1,2,4,2,1],
+    "fm_decoder_num_layers" : [2,2,4,4,4],
+    "fm_decoder_cnn_module_kernel" : [31,15,7,15,31],
+    "fm_decoder_feedforward_dim" : 1536,
+    "fm_decoder_num_heads" : 4,
+    "fm_decoder_dim" : 512,
+    "text_encoder_num_layers" : 4,
+    "text_encoder_feedforward_dim" : 512,
+    "text_encoder_cnn_module_kernel" : 9,
+    "text_encoder_num_heads" : 4,
+    "text_encoder_dim" : 192,
+    "query_head_dim" : 32,
+    "value_head_dim" : 12,
+    "pos_head_dim" : 4,
+    "pos_dim" : 48,
+    "time_embed_dim" : 192,
+    "text_embed_dim" : 192,
+    "feat_dim": 100
+  },
+  "feature" : {
+    "sampling_rate": 24000,
+    "type": "vocos"
+  }
+}

zipvoice_libritts/model.json

@@ -0,0 +1,26 @@
+{
+  "model" : {
+    "fm_decoder_downsampling_factor" : [1,2,4,2,1],
+    "fm_decoder_num_layers" : [2,2,4,4,4],
+    "fm_decoder_cnn_module_kernel" : [31,15,7,15,31],
+    "fm_decoder_feedforward_dim" : 1536,
+    "fm_decoder_num_heads" : 4,
+    "fm_decoder_dim" : 512,
+    "text_encoder_num_layers" : 4,
+    "text_encoder_feedforward_dim" : 512,
+    "text_encoder_cnn_module_kernel" : 9,
+    "text_encoder_num_heads" : 4,
+    "text_encoder_dim" : 192,
+    "query_head_dim" : 32,
+    "value_head_dim" : 12,
+    "pos_head_dim" : 4,
+    "pos_dim" : 48,
+    "time_embed_dim" : 192,
+    "text_embed_dim" : 192,
+    "feat_dim": 100
+  },
+  "feature" : {
+    "sampling_rate": 24000,
+    "type": "vocos"
+  }
+}

zipvoice_libritts/model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb09917068d1b05796597a4249b7f44a576c45aa60e54fae8c730e1e48d3fd82
+size 490946536

zipvoice_libritts/tokens.txt

@@ -0,0 +1,79 @@
+_	0
+ 	1
+e	2
+t	3
+a	4
+o	5
+n	6
+h	7
+i	8
+s	9
+r	10
+d	11
+l	12
+u	13
+m	14
+c	15
+w	16
+f	17
+y	18
+g	19
+,	20
+p	21
+b	22
+.	23
+v	24
+k	25
+"	26
+I	27
+'	28
+T	29
+A	30
+H	31
+S	32
+;	33
+W	34
+-	35
+x	36
+B	37
+?	38
+M	39
+C	40
+!	41
+j	42
+q	43
+N	44
+E	45
+O	46
+P	47
+D	48
+L	49
+G	50
+R	51
+Y	52
+F	53
+z	54
+:	55
+J	56
+K	57
+U	58
+V	59
+)	60
+(	61
+Q	62
+Z	63
+X	64
+]	65
+[	66
+—	67
+/	68
+æ	69
+é	70
+ñ	71
+œ	72
+}	73
+{	74
+ê	75
+¯	76
+è	77
+ô	78

zipvoice_libritts/zipvoice_base.json

@@ -0,0 +1,26 @@
+{
+  "model" : {
+    "fm_decoder_downsampling_factor" : [1,2,4,2,1],
+    "fm_decoder_num_layers" : [2,2,4,4,4],
+    "fm_decoder_cnn_module_kernel" : [31,15,7,15,31],
+    "fm_decoder_feedforward_dim" : 1536,
+    "fm_decoder_num_heads" : 4,
+    "fm_decoder_dim" : 512,
+    "text_encoder_num_layers" : 4,
+    "text_encoder_feedforward_dim" : 512,
+    "text_encoder_cnn_module_kernel" : 9,
+    "text_encoder_num_heads" : 4,
+    "text_encoder_dim" : 192,
+    "query_head_dim" : 32,
+    "value_head_dim" : 12,
+    "pos_head_dim" : 4,
+    "pos_dim" : 48,
+    "time_embed_dim" : 192,
+    "text_embed_dim" : 192,
+    "feat_dim": 100
+  },
+  "feature" : {
+    "sampling_rate": 24000,
+    "type": "vocos"
+  }
+}