import from zenodo

README.md

@@ -0,0 +1,50 @@
+---
+tags:
+- espnet
+- audio
+- text-to-speech
+language: en
+datasets:
+- vctk
+license: cc-by-4.0
+---
+## Example ESPnet2 TTS model 
+### `kan-bayashi/vctk_gst+xvector_transformer`
+♻️ Imported from https://zenodo.org/record/4393277/
+
+This model was trained by kan-bayashi using vctk/tts1 recipe in [espnet](https://github.com/espnet/espnet/).
+### Demo: How to use in ESPnet2
+```python
+# coming soon
+```
+### Citing ESPnet
+```BibTex
+@inproceedings{watanabe2018espnet,
+  author={Shinji Watanabe and Takaaki Hori and Shigeki Karita and Tomoki Hayashi and Jiro Nishitoba and Yuya Unno and Nelson {Enrique Yalta Soplin} and Jahn Heymann and Matthew Wiesner and Nanxin Chen and Adithya Renduchintala and Tsubasa Ochiai},
+  title={{ESPnet}: End-to-End Speech Processing Toolkit},
+  year={2018},
+  booktitle={Proceedings of Interspeech},
+  pages={2207--2211},
+  doi={10.21437/Interspeech.2018-1456},
+  url={http://dx.doi.org/10.21437/Interspeech.2018-1456}
+}
+@inproceedings{hayashi2020espnet,
+  title={{Espnet-TTS}: Unified, reproducible, and integratable open source end-to-end text-to-speech toolkit},
+  author={Hayashi, Tomoki and Yamamoto, Ryuichi and Inoue, Katsuki and Yoshimura, Takenori and Watanabe, Shinji and Toda, Tomoki and Takeda, Kazuya and Zhang, Yu and Tan, Xu},
+  booktitle={Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
+  pages={7654--7658},
+  year={2020},
+  organization={IEEE}
+}
+```
+or arXiv:
+```bibtex
+@misc{watanabe2018espnet,
+      title={ESPnet: End-to-End Speech Processing Toolkit}, 
+      author={Shinji Watanabe and Takaaki Hori and Shigeki Karita and Tomoki Hayashi and Jiro Nishitoba and Yuya Unno and Nelson Enrique Yalta Soplin and Jahn Heymann and Matthew Wiesner and Nanxin Chen and Adithya Renduchintala and Tsubasa Ochiai},
+      year={2018},
+      eprint={1804.00015},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL}
+}
+```

dump/xvector/dev/spk_xvector.scp

@@ -0,0 +1,108 @@
+p225 dump/xvector/dev/spk_xvector.ark:5
+p226 dump/xvector/dev/spk_xvector.ark:2068
+p227 dump/xvector/dev/spk_xvector.ark:4131
+p228 dump/xvector/dev/spk_xvector.ark:6194
+p229 dump/xvector/dev/spk_xvector.ark:8257
+p230 dump/xvector/dev/spk_xvector.ark:10320
+p231 dump/xvector/dev/spk_xvector.ark:12383
+p232 dump/xvector/dev/spk_xvector.ark:14446
+p233 dump/xvector/dev/spk_xvector.ark:16509
+p234 dump/xvector/dev/spk_xvector.ark:18572
+p236 dump/xvector/dev/spk_xvector.ark:20635
+p237 dump/xvector/dev/spk_xvector.ark:22698
+p238 dump/xvector/dev/spk_xvector.ark:24761
+p239 dump/xvector/dev/spk_xvector.ark:26824
+p240 dump/xvector/dev/spk_xvector.ark:28887
+p241 dump/xvector/dev/spk_xvector.ark:30950
+p243 dump/xvector/dev/spk_xvector.ark:33013
+p244 dump/xvector/dev/spk_xvector.ark:35076
+p245 dump/xvector/dev/spk_xvector.ark:37139
+p246 dump/xvector/dev/spk_xvector.ark:39202
+p247 dump/xvector/dev/spk_xvector.ark:41265
+p248 dump/xvector/dev/spk_xvector.ark:43328
+p249 dump/xvector/dev/spk_xvector.ark:45391
+p250 dump/xvector/dev/spk_xvector.ark:47454
+p251 dump/xvector/dev/spk_xvector.ark:49517
+p252 dump/xvector/dev/spk_xvector.ark:51580
+p253 dump/xvector/dev/spk_xvector.ark:53643
+p254 dump/xvector/dev/spk_xvector.ark:55706
+p255 dump/xvector/dev/spk_xvector.ark:57769
+p256 dump/xvector/dev/spk_xvector.ark:59832
+p257 dump/xvector/dev/spk_xvector.ark:61895
+p258 dump/xvector/dev/spk_xvector.ark:63958
+p259 dump/xvector/dev/spk_xvector.ark:66021
+p260 dump/xvector/dev/spk_xvector.ark:68084
+p261 dump/xvector/dev/spk_xvector.ark:70147
+p262 dump/xvector/dev/spk_xvector.ark:72210
+p263 dump/xvector/dev/spk_xvector.ark:74273
+p264 dump/xvector/dev/spk_xvector.ark:76336
+p265 dump/xvector/dev/spk_xvector.ark:78399
+p266 dump/xvector/dev/spk_xvector.ark:80462
+p267 dump/xvector/dev/spk_xvector.ark:82525
+p268 dump/xvector/dev/spk_xvector.ark:84588
+p269 dump/xvector/dev/spk_xvector.ark:86651
+p270 dump/xvector/dev/spk_xvector.ark:88714
+p271 dump/xvector/dev/spk_xvector.ark:90777
+p272 dump/xvector/dev/spk_xvector.ark:92840
+p273 dump/xvector/dev/spk_xvector.ark:94903
+p274 dump/xvector/dev/spk_xvector.ark:96966
+p275 dump/xvector/dev/spk_xvector.ark:99029
+p276 dump/xvector/dev/spk_xvector.ark:101092
+p277 dump/xvector/dev/spk_xvector.ark:103155
+p278 dump/xvector/dev/spk_xvector.ark:105218
+p279 dump/xvector/dev/spk_xvector.ark:107281
+p280 dump/xvector/dev/spk_xvector.ark:109344
+p281 dump/xvector/dev/spk_xvector.ark:111407
+p282 dump/xvector/dev/spk_xvector.ark:113470
+p283 dump/xvector/dev/spk_xvector.ark:115533
+p284 dump/xvector/dev/spk_xvector.ark:117596
+p285 dump/xvector/dev/spk_xvector.ark:119659
+p286 dump/xvector/dev/spk_xvector.ark:121722
+p287 dump/xvector/dev/spk_xvector.ark:123785
+p288 dump/xvector/dev/spk_xvector.ark:125848
+p292 dump/xvector/dev/spk_xvector.ark:127911
+p293 dump/xvector/dev/spk_xvector.ark:129974
+p294 dump/xvector/dev/spk_xvector.ark:132037
+p295 dump/xvector/dev/spk_xvector.ark:134100
+p297 dump/xvector/dev/spk_xvector.ark:136163
+p298 dump/xvector/dev/spk_xvector.ark:138226
+p299 dump/xvector/dev/spk_xvector.ark:140289
+p300 dump/xvector/dev/spk_xvector.ark:142352
+p301 dump/xvector/dev/spk_xvector.ark:144415
+p302 dump/xvector/dev/spk_xvector.ark:146478
+p303 dump/xvector/dev/spk_xvector.ark:148541
+p304 dump/xvector/dev/spk_xvector.ark:150604
+p305 dump/xvector/dev/spk_xvector.ark:152667
+p306 dump/xvector/dev/spk_xvector.ark:154730
+p307 dump/xvector/dev/spk_xvector.ark:156793
+p308 dump/xvector/dev/spk_xvector.ark:158856
+p310 dump/xvector/dev/spk_xvector.ark:160919
+p311 dump/xvector/dev/spk_xvector.ark:162982
+p312 dump/xvector/dev/spk_xvector.ark:165045
+p313 dump/xvector/dev/spk_xvector.ark:167108
+p314 dump/xvector/dev/spk_xvector.ark:169171
+p316 dump/xvector/dev/spk_xvector.ark:171234
+p317 dump/xvector/dev/spk_xvector.ark:173297
+p318 dump/xvector/dev/spk_xvector.ark:175360
+p323 dump/xvector/dev/spk_xvector.ark:177423
+p326 dump/xvector/dev/spk_xvector.ark:179486
+p329 dump/xvector/dev/spk_xvector.ark:181549
+p330 dump/xvector/dev/spk_xvector.ark:183612
+p333 dump/xvector/dev/spk_xvector.ark:185675
+p334 dump/xvector/dev/spk_xvector.ark:187738
+p335 dump/xvector/dev/spk_xvector.ark:189801
+p336 dump/xvector/dev/spk_xvector.ark:191864
+p339 dump/xvector/dev/spk_xvector.ark:193927
+p340 dump/xvector/dev/spk_xvector.ark:195990
+p341 dump/xvector/dev/spk_xvector.ark:198053
+p343 dump/xvector/dev/spk_xvector.ark:200116
+p345 dump/xvector/dev/spk_xvector.ark:202179
+p347 dump/xvector/dev/spk_xvector.ark:204242
+p351 dump/xvector/dev/spk_xvector.ark:206305
+p360 dump/xvector/dev/spk_xvector.ark:208368
+p361 dump/xvector/dev/spk_xvector.ark:210431
+p362 dump/xvector/dev/spk_xvector.ark:212494
+p363 dump/xvector/dev/spk_xvector.ark:214557
+p364 dump/xvector/dev/spk_xvector.ark:216620
+p374 dump/xvector/dev/spk_xvector.ark:218683
+p376 dump/xvector/dev/spk_xvector.ark:220746

dump/xvector/eval1/spk_xvector.scp

@@ -0,0 +1,108 @@
+p225 dump/xvector/eval1/spk_xvector.ark:5
+p226 dump/xvector/eval1/spk_xvector.ark:2068
+p227 dump/xvector/eval1/spk_xvector.ark:4131
+p228 dump/xvector/eval1/spk_xvector.ark:6194
+p229 dump/xvector/eval1/spk_xvector.ark:8257
+p230 dump/xvector/eval1/spk_xvector.ark:10320
+p231 dump/xvector/eval1/spk_xvector.ark:12383
+p232 dump/xvector/eval1/spk_xvector.ark:14446
+p233 dump/xvector/eval1/spk_xvector.ark:16509
+p234 dump/xvector/eval1/spk_xvector.ark:18572
+p236 dump/xvector/eval1/spk_xvector.ark:20635
+p237 dump/xvector/eval1/spk_xvector.ark:22698
+p238 dump/xvector/eval1/spk_xvector.ark:24761
+p239 dump/xvector/eval1/spk_xvector.ark:26824
+p240 dump/xvector/eval1/spk_xvector.ark:28887
+p241 dump/xvector/eval1/spk_xvector.ark:30950
+p243 dump/xvector/eval1/spk_xvector.ark:33013
+p244 dump/xvector/eval1/spk_xvector.ark:35076
+p245 dump/xvector/eval1/spk_xvector.ark:37139
+p246 dump/xvector/eval1/spk_xvector.ark:39202
+p247 dump/xvector/eval1/spk_xvector.ark:41265
+p248 dump/xvector/eval1/spk_xvector.ark:43328
+p249 dump/xvector/eval1/spk_xvector.ark:45391
+p250 dump/xvector/eval1/spk_xvector.ark:47454
+p251 dump/xvector/eval1/spk_xvector.ark:49517
+p252 dump/xvector/eval1/spk_xvector.ark:51580
+p253 dump/xvector/eval1/spk_xvector.ark:53643
+p254 dump/xvector/eval1/spk_xvector.ark:55706
+p255 dump/xvector/eval1/spk_xvector.ark:57769
+p256 dump/xvector/eval1/spk_xvector.ark:59832
+p257 dump/xvector/eval1/spk_xvector.ark:61895
+p258 dump/xvector/eval1/spk_xvector.ark:63958
+p259 dump/xvector/eval1/spk_xvector.ark:66021
+p260 dump/xvector/eval1/spk_xvector.ark:68084
+p261 dump/xvector/eval1/spk_xvector.ark:70147
+p262 dump/xvector/eval1/spk_xvector.ark:72210
+p263 dump/xvector/eval1/spk_xvector.ark:74273
+p264 dump/xvector/eval1/spk_xvector.ark:76336
+p265 dump/xvector/eval1/spk_xvector.ark:78399
+p266 dump/xvector/eval1/spk_xvector.ark:80462
+p267 dump/xvector/eval1/spk_xvector.ark:82525
+p268 dump/xvector/eval1/spk_xvector.ark:84588
+p269 dump/xvector/eval1/spk_xvector.ark:86651
+p270 dump/xvector/eval1/spk_xvector.ark:88714
+p271 dump/xvector/eval1/spk_xvector.ark:90777
+p272 dump/xvector/eval1/spk_xvector.ark:92840
+p273 dump/xvector/eval1/spk_xvector.ark:94903
+p274 dump/xvector/eval1/spk_xvector.ark:96966
+p275 dump/xvector/eval1/spk_xvector.ark:99029
+p276 dump/xvector/eval1/spk_xvector.ark:101092
+p277 dump/xvector/eval1/spk_xvector.ark:103155
+p278 dump/xvector/eval1/spk_xvector.ark:105218
+p279 dump/xvector/eval1/spk_xvector.ark:107281
+p280 dump/xvector/eval1/spk_xvector.ark:109344
+p281 dump/xvector/eval1/spk_xvector.ark:111407
+p282 dump/xvector/eval1/spk_xvector.ark:113470
+p283 dump/xvector/eval1/spk_xvector.ark:115533
+p284 dump/xvector/eval1/spk_xvector.ark:117596
+p285 dump/xvector/eval1/spk_xvector.ark:119659
+p286 dump/xvector/eval1/spk_xvector.ark:121722
+p287 dump/xvector/eval1/spk_xvector.ark:123785
+p288 dump/xvector/eval1/spk_xvector.ark:125848
+p292 dump/xvector/eval1/spk_xvector.ark:127911
+p293 dump/xvector/eval1/spk_xvector.ark:129974
+p294 dump/xvector/eval1/spk_xvector.ark:132037
+p295 dump/xvector/eval1/spk_xvector.ark:134100
+p297 dump/xvector/eval1/spk_xvector.ark:136163
+p298 dump/xvector/eval1/spk_xvector.ark:138226
+p299 dump/xvector/eval1/spk_xvector.ark:140289
+p300 dump/xvector/eval1/spk_xvector.ark:142352
+p301 dump/xvector/eval1/spk_xvector.ark:144415
+p302 dump/xvector/eval1/spk_xvector.ark:146478
+p303 dump/xvector/eval1/spk_xvector.ark:148541
+p304 dump/xvector/eval1/spk_xvector.ark:150604
+p305 dump/xvector/eval1/spk_xvector.ark:152667
+p306 dump/xvector/eval1/spk_xvector.ark:154730
+p307 dump/xvector/eval1/spk_xvector.ark:156793
+p308 dump/xvector/eval1/spk_xvector.ark:158856
+p310 dump/xvector/eval1/spk_xvector.ark:160919
+p311 dump/xvector/eval1/spk_xvector.ark:162982
+p312 dump/xvector/eval1/spk_xvector.ark:165045
+p313 dump/xvector/eval1/spk_xvector.ark:167108
+p314 dump/xvector/eval1/spk_xvector.ark:169171
+p316 dump/xvector/eval1/spk_xvector.ark:171234
+p317 dump/xvector/eval1/spk_xvector.ark:173297
+p318 dump/xvector/eval1/spk_xvector.ark:175360
+p323 dump/xvector/eval1/spk_xvector.ark:177423
+p326 dump/xvector/eval1/spk_xvector.ark:179486
+p329 dump/xvector/eval1/spk_xvector.ark:181549
+p330 dump/xvector/eval1/spk_xvector.ark:183612
+p333 dump/xvector/eval1/spk_xvector.ark:185675
+p334 dump/xvector/eval1/spk_xvector.ark:187738
+p335 dump/xvector/eval1/spk_xvector.ark:189801
+p336 dump/xvector/eval1/spk_xvector.ark:191864
+p339 dump/xvector/eval1/spk_xvector.ark:193927
+p340 dump/xvector/eval1/spk_xvector.ark:195990
+p341 dump/xvector/eval1/spk_xvector.ark:198053
+p343 dump/xvector/eval1/spk_xvector.ark:200116
+p345 dump/xvector/eval1/spk_xvector.ark:202179
+p347 dump/xvector/eval1/spk_xvector.ark:204242
+p351 dump/xvector/eval1/spk_xvector.ark:206305
+p360 dump/xvector/eval1/spk_xvector.ark:208368
+p361 dump/xvector/eval1/spk_xvector.ark:210431
+p362 dump/xvector/eval1/spk_xvector.ark:212494
+p363 dump/xvector/eval1/spk_xvector.ark:214557
+p364 dump/xvector/eval1/spk_xvector.ark:216620
+p374 dump/xvector/eval1/spk_xvector.ark:218683
+p376 dump/xvector/eval1/spk_xvector.ark:220746

dump/xvector/tr_no_dev/spk_xvector.scp

@@ -0,0 +1,108 @@
+p225 dump/xvector/tr_no_dev/spk_xvector.ark:5
+p226 dump/xvector/tr_no_dev/spk_xvector.ark:2068
+p227 dump/xvector/tr_no_dev/spk_xvector.ark:4131
+p228 dump/xvector/tr_no_dev/spk_xvector.ark:6194
+p229 dump/xvector/tr_no_dev/spk_xvector.ark:8257
+p230 dump/xvector/tr_no_dev/spk_xvector.ark:10320
+p231 dump/xvector/tr_no_dev/spk_xvector.ark:12383
+p232 dump/xvector/tr_no_dev/spk_xvector.ark:14446
+p233 dump/xvector/tr_no_dev/spk_xvector.ark:16509
+p234 dump/xvector/tr_no_dev/spk_xvector.ark:18572
+p236 dump/xvector/tr_no_dev/spk_xvector.ark:20635
+p237 dump/xvector/tr_no_dev/spk_xvector.ark:22698
+p238 dump/xvector/tr_no_dev/spk_xvector.ark:24761
+p239 dump/xvector/tr_no_dev/spk_xvector.ark:26824
+p240 dump/xvector/tr_no_dev/spk_xvector.ark:28887
+p241 dump/xvector/tr_no_dev/spk_xvector.ark:30950
+p243 dump/xvector/tr_no_dev/spk_xvector.ark:33013
+p244 dump/xvector/tr_no_dev/spk_xvector.ark:35076
+p245 dump/xvector/tr_no_dev/spk_xvector.ark:37139
+p246 dump/xvector/tr_no_dev/spk_xvector.ark:39202
+p247 dump/xvector/tr_no_dev/spk_xvector.ark:41265
+p248 dump/xvector/tr_no_dev/spk_xvector.ark:43328
+p249 dump/xvector/tr_no_dev/spk_xvector.ark:45391
+p250 dump/xvector/tr_no_dev/spk_xvector.ark:47454
+p251 dump/xvector/tr_no_dev/spk_xvector.ark:49517
+p252 dump/xvector/tr_no_dev/spk_xvector.ark:51580
+p253 dump/xvector/tr_no_dev/spk_xvector.ark:53643
+p254 dump/xvector/tr_no_dev/spk_xvector.ark:55706
+p255 dump/xvector/tr_no_dev/spk_xvector.ark:57769
+p256 dump/xvector/tr_no_dev/spk_xvector.ark:59832
+p257 dump/xvector/tr_no_dev/spk_xvector.ark:61895
+p258 dump/xvector/tr_no_dev/spk_xvector.ark:63958
+p259 dump/xvector/tr_no_dev/spk_xvector.ark:66021
+p260 dump/xvector/tr_no_dev/spk_xvector.ark:68084
+p261 dump/xvector/tr_no_dev/spk_xvector.ark:70147
+p262 dump/xvector/tr_no_dev/spk_xvector.ark:72210
+p263 dump/xvector/tr_no_dev/spk_xvector.ark:74273
+p264 dump/xvector/tr_no_dev/spk_xvector.ark:76336
+p265 dump/xvector/tr_no_dev/spk_xvector.ark:78399
+p266 dump/xvector/tr_no_dev/spk_xvector.ark:80462
+p267 dump/xvector/tr_no_dev/spk_xvector.ark:82525
+p268 dump/xvector/tr_no_dev/spk_xvector.ark:84588
+p269 dump/xvector/tr_no_dev/spk_xvector.ark:86651
+p270 dump/xvector/tr_no_dev/spk_xvector.ark:88714
+p271 dump/xvector/tr_no_dev/spk_xvector.ark:90777
+p272 dump/xvector/tr_no_dev/spk_xvector.ark:92840
+p273 dump/xvector/tr_no_dev/spk_xvector.ark:94903
+p274 dump/xvector/tr_no_dev/spk_xvector.ark:96966
+p275 dump/xvector/tr_no_dev/spk_xvector.ark:99029
+p276 dump/xvector/tr_no_dev/spk_xvector.ark:101092
+p277 dump/xvector/tr_no_dev/spk_xvector.ark:103155
+p278 dump/xvector/tr_no_dev/spk_xvector.ark:105218
+p279 dump/xvector/tr_no_dev/spk_xvector.ark:107281
+p280 dump/xvector/tr_no_dev/spk_xvector.ark:109344
+p281 dump/xvector/tr_no_dev/spk_xvector.ark:111407
+p282 dump/xvector/tr_no_dev/spk_xvector.ark:113470
+p283 dump/xvector/tr_no_dev/spk_xvector.ark:115533
+p284 dump/xvector/tr_no_dev/spk_xvector.ark:117596
+p285 dump/xvector/tr_no_dev/spk_xvector.ark:119659
+p286 dump/xvector/tr_no_dev/spk_xvector.ark:121722
+p287 dump/xvector/tr_no_dev/spk_xvector.ark:123785
+p288 dump/xvector/tr_no_dev/spk_xvector.ark:125848
+p292 dump/xvector/tr_no_dev/spk_xvector.ark:127911
+p293 dump/xvector/tr_no_dev/spk_xvector.ark:129974
+p294 dump/xvector/tr_no_dev/spk_xvector.ark:132037
+p295 dump/xvector/tr_no_dev/spk_xvector.ark:134100
+p297 dump/xvector/tr_no_dev/spk_xvector.ark:136163
+p298 dump/xvector/tr_no_dev/spk_xvector.ark:138226
+p299 dump/xvector/tr_no_dev/spk_xvector.ark:140289
+p300 dump/xvector/tr_no_dev/spk_xvector.ark:142352
+p301 dump/xvector/tr_no_dev/spk_xvector.ark:144415
+p302 dump/xvector/tr_no_dev/spk_xvector.ark:146478
+p303 dump/xvector/tr_no_dev/spk_xvector.ark:148541
+p304 dump/xvector/tr_no_dev/spk_xvector.ark:150604
+p305 dump/xvector/tr_no_dev/spk_xvector.ark:152667
+p306 dump/xvector/tr_no_dev/spk_xvector.ark:154730
+p307 dump/xvector/tr_no_dev/spk_xvector.ark:156793
+p308 dump/xvector/tr_no_dev/spk_xvector.ark:158856
+p310 dump/xvector/tr_no_dev/spk_xvector.ark:160919
+p311 dump/xvector/tr_no_dev/spk_xvector.ark:162982
+p312 dump/xvector/tr_no_dev/spk_xvector.ark:165045
+p313 dump/xvector/tr_no_dev/spk_xvector.ark:167108
+p314 dump/xvector/tr_no_dev/spk_xvector.ark:169171
+p316 dump/xvector/tr_no_dev/spk_xvector.ark:171234
+p317 dump/xvector/tr_no_dev/spk_xvector.ark:173297
+p318 dump/xvector/tr_no_dev/spk_xvector.ark:175360
+p323 dump/xvector/tr_no_dev/spk_xvector.ark:177423
+p326 dump/xvector/tr_no_dev/spk_xvector.ark:179486
+p329 dump/xvector/tr_no_dev/spk_xvector.ark:181549
+p330 dump/xvector/tr_no_dev/spk_xvector.ark:183612
+p333 dump/xvector/tr_no_dev/spk_xvector.ark:185675
+p334 dump/xvector/tr_no_dev/spk_xvector.ark:187738
+p335 dump/xvector/tr_no_dev/spk_xvector.ark:189801
+p336 dump/xvector/tr_no_dev/spk_xvector.ark:191864
+p339 dump/xvector/tr_no_dev/spk_xvector.ark:193927
+p340 dump/xvector/tr_no_dev/spk_xvector.ark:195990
+p341 dump/xvector/tr_no_dev/spk_xvector.ark:198053
+p343 dump/xvector/tr_no_dev/spk_xvector.ark:200116
+p345 dump/xvector/tr_no_dev/spk_xvector.ark:202179
+p347 dump/xvector/tr_no_dev/spk_xvector.ark:204242
+p351 dump/xvector/tr_no_dev/spk_xvector.ark:206305
+p360 dump/xvector/tr_no_dev/spk_xvector.ark:208368
+p361 dump/xvector/tr_no_dev/spk_xvector.ark:210431
+p362 dump/xvector/tr_no_dev/spk_xvector.ark:212494
+p363 dump/xvector/tr_no_dev/spk_xvector.ark:214557
+p364 dump/xvector/tr_no_dev/spk_xvector.ark:216620
+p374 dump/xvector/tr_no_dev/spk_xvector.ark:218683
+p376 dump/xvector/tr_no_dev/spk_xvector.ark:220746

exp/tts_train_gst+xvector_transformer_raw_phn_tacotron_g2p_en_no_space/config.yaml

@@ -0,0 +1,271 @@
+config: conf/tuning/train_gst+xvector_transformer.yaml
+print_config: false
+log_level: INFO
+dry_run: false
+iterator_type: sequence
+output_dir: exp/tts_train_gst+xvector_transformer_raw_phn_tacotron_g2p_en_no_space
+ngpu: 1
+seed: 0
+num_workers: 1
+num_att_plot: 3
+dist_backend: nccl
+dist_init_method: env://
+dist_world_size: 4
+dist_rank: 0
+local_rank: 0
+dist_master_addr: localhost
+dist_master_port: 46493
+dist_launcher: null
+multiprocessing_distributed: true
+cudnn_enabled: true
+cudnn_benchmark: false
+cudnn_deterministic: true
+collect_stats: false
+write_collected_feats: false
+max_epoch: 500
+patience: null
+val_scheduler_criterion:
+- valid
+- loss
+early_stopping_criterion:
+- valid
+- loss
+- min
+best_model_criterion:
+-   - valid
+    - loss
+    - min
+-   - train
+    - loss
+    - min
+keep_nbest_models: 5
+grad_clip: 1.0
+grad_clip_type: 2.0
+grad_noise: false
+accum_grad: 2
+no_forward_run: false
+resume: true
+train_dtype: float32
+use_amp: false
+log_interval: null
+unused_parameters: false
+use_tensorboard: true
+use_wandb: false
+wandb_project: null
+wandb_id: null
+pretrain_path: null
+init_param: []
+freeze_param: []
+num_iters_per_epoch: 1000
+batch_size: 20
+valid_batch_size: null
+batch_bins: 9000000
+valid_batch_bins: null
+train_shape_file:
+- exp/tts_stats_raw_phn_tacotron_g2p_en_no_space/train/text_shape.phn
+- exp/tts_stats_raw_phn_tacotron_g2p_en_no_space/train/speech_shape
+valid_shape_file:
+- exp/tts_stats_raw_phn_tacotron_g2p_en_no_space/valid/text_shape.phn
+- exp/tts_stats_raw_phn_tacotron_g2p_en_no_space/valid/speech_shape
+batch_type: numel
+valid_batch_type: null
+fold_length:
+- 150
+- 240000
+sort_in_batch: descending
+sort_batch: descending
+multiple_iterator: false
+chunk_length: 500
+chunk_shift_ratio: 0.5
+num_cache_chunks: 1024
+train_data_path_and_name_and_type:
+-   - dump/raw/tr_no_dev/text
+    - text
+    - text
+-   - dump/raw/tr_no_dev/wav.scp
+    - speech
+    - sound
+-   - dump/xvector/tr_no_dev/xvector.scp
+    - spembs
+    - kaldi_ark
+valid_data_path_and_name_and_type:
+-   - dump/raw/dev/text
+    - text
+    - text
+-   - dump/raw/dev/wav.scp
+    - speech
+    - sound
+-   - dump/xvector/dev/xvector.scp
+    - spembs
+    - kaldi_ark
+allow_variable_data_keys: false
+max_cache_size: 0.0
+max_cache_fd: 32
+valid_max_cache_size: null
+optim: adam
+optim_conf:
+    lr: 1.0
+scheduler: noamlr
+scheduler_conf:
+    model_size: 512
+    warmup_steps: 12000
+token_list:
+- <blank>
+- <unk>
+- AH0
+- T
+- N
+- S
+- R
+- IH1
+- D
+- L
+- .
+- Z
+- DH
+- K
+- W
+- M
+- AE1
+- EH1
+- AA1
+- IH0
+- IY1
+- AH1
+- B
+- P
+- V
+- ER0
+- F
+- HH
+- AY1
+- EY1
+- UW1
+- IY0
+- AO1
+- OW1
+- G
+- ','
+- NG
+- SH
+- Y
+- JH
+- AW1
+- UH1
+- TH
+- ER1
+- CH
+- '?'
+- OW0
+- OW2
+- EH2
+- EY2
+- UW0
+- IH2
+- OY1
+- AY2
+- ZH
+- AW2
+- EH0
+- IY2
+- AA2
+- AE0
+- AH2
+- AE2
+- AO0
+- AO2
+- AY0
+- UW2
+- UH2
+- AA0
+- AW0
+- EY0
+- '!'
+- UH0
+- ER2
+- OY2
+- ''''
+- OY0
+- <sos/eos>
+odim: null
+model_conf: {}
+use_preprocessor: true
+token_type: phn
+bpemodel: null
+non_linguistic_symbols: null
+cleaner: tacotron
+g2p: g2p_en_no_space
+feats_extract: fbank
+feats_extract_conf:
+    fs: 24000
+    fmin: 80
+    fmax: 7600
+    n_mels: 80
+    hop_length: 300
+    n_fft: 2048
+    win_length: 1200
+normalize: global_mvn
+normalize_conf:
+    stats_file: exp/tts_stats_raw_phn_tacotron_g2p_en_no_space/train/feats_stats.npz
+tts: transformer
+tts_conf:
+    embed_dim: 0
+    eprenet_conv_layers: 0
+    eprenet_conv_filts: 0
+    eprenet_conv_chans: 0
+    dprenet_layers: 2
+    dprenet_units: 256
+    adim: 512
+    aheads: 8
+    elayers: 6
+    eunits: 1024
+    dlayers: 6
+    dunits: 1024
+    positionwise_layer_type: conv1d
+    positionwise_conv_kernel_size: 1
+    postnet_layers: 5
+    postnet_filts: 5
+    postnet_chans: 256
+    spk_embed_dim: 512
+    spk_embed_integration_type: add
+    use_gst: true
+    gst_heads: 4
+    gst_tokens: 16
+    use_masking: true
+    bce_pos_weight: 5.0
+    use_scaled_pos_enc: true
+    encoder_normalize_before: true
+    decoder_normalize_before: true
+    reduction_factor: 1
+    init_type: xavier_uniform
+    init_enc_alpha: 1.0
+    init_dec_alpha: 1.0
+    eprenet_dropout_rate: 0.0
+    dprenet_dropout_rate: 0.5
+    postnet_dropout_rate: 0.5
+    transformer_enc_dropout_rate: 0.1
+    transformer_enc_positional_dropout_rate: 0.1
+    transformer_enc_attn_dropout_rate: 0.1
+    transformer_dec_dropout_rate: 0.1
+    transformer_dec_positional_dropout_rate: 0.1
+    transformer_dec_attn_dropout_rate: 0.1
+    transformer_enc_dec_attn_dropout_rate: 0.1
+    use_guided_attn_loss: true
+    num_heads_applied_guided_attn: 2
+    num_layers_applied_guided_attn: 2
+    modules_applied_guided_attn:
+    - encoder-decoder
+    guided_attn_loss_sigma: 0.4
+    guided_attn_loss_lambda: 10.0
+pitch_extract: null
+pitch_extract_conf: {}
+pitch_normalize: null
+pitch_normalize_conf: {}
+energy_extract: null
+energy_extract_conf: {}
+energy_normalize: null
+energy_normalize_conf: {}
+required:
+- output_dir
+- token_list
+distributed: true

exp/tts_train_gst+xvector_transformer_raw_phn_tacotron_g2p_en_no_space/train.loss.ave_5best.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f28cdd90a174c8241118db93389021484d1548ccf429d8cb7ef154a68c2dc3e5
+size 137197841

meta.yaml

@@ -0,0 +1,8 @@
+espnet: 0.8.0
+files:
+  model_file: exp/tts_train_gst+xvector_transformer_raw_phn_tacotron_g2p_en_no_space/train.loss.ave_5best.pth
+python: "3.7.3 (default, Mar 27 2019, 22:11:17) \n[GCC 7.3.0]"
+timestamp: 1608877602.794003
+torch: 1.5.1
+yaml_files:
+  train_config: exp/tts_train_gst+xvector_transformer_raw_phn_tacotron_g2p_en_no_space/config.yaml