Update model

README.md

@@ -11,11 +11,29 @@ license: cc-by-4.0
 
 ## ESPnet2 TTS model
 
+### `winniech/espnet2_pretrained_aishell3_vits_tts_train_raw_phn_pypinyin_g2p_phone`
+
 This model was trained by winniech using aishell3 recipe in [espnet](https://github.com/espnet/espnet/).
 
+### Demo: How to use in ESPnet2
+
+Follow the [ESPnet installation instructions](https://espnet.github.io/espnet/installation.html)
+if you haven't done that already.
+
+```bash
+cd espnet
+git checkout b4423aa582b53c780ec21540e5134917ed8c450e
+pip install -e .
+cd egs2/aishell3/tts1
+./run.sh --skip_data_prep false --skip_train true --download_model winniech/espnet2_pretrained_aishell3_vits_tts_train_raw_phn_pypinyin_g2p_phone
+```
+
+
 
 ## TTS config
 
+<details><summary>expand</summary>
+
 ```
 config: conf/train.yaml
 print_config: false
@@ -519,6 +537,7 @@ version: '202301'
 distributed: false
 ```
 
+</details>
 
 
 

dump/22k/xvector/dev/spk_xvector.scp

@@ -0,0 +1,141 @@
+SSB0009 dump/22k/xvector/dev/spk_xvector.ark:8
+SSB0011 dump/22k/xvector/dev/spk_xvector.ark:2074
+SSB0012 dump/22k/xvector/dev/spk_xvector.ark:4140
+SSB0016 dump/22k/xvector/dev/spk_xvector.ark:6206
+SSB0018 dump/22k/xvector/dev/spk_xvector.ark:8272
+SSB0033 dump/22k/xvector/dev/spk_xvector.ark:10338
+SSB0038 dump/22k/xvector/dev/spk_xvector.ark:12404
+SSB0043 dump/22k/xvector/dev/spk_xvector.ark:14470
+SSB0057 dump/22k/xvector/dev/spk_xvector.ark:16536
+SSB0073 dump/22k/xvector/dev/spk_xvector.ark:18602
+SSB0080 dump/22k/xvector/dev/spk_xvector.ark:20668
+SSB0112 dump/22k/xvector/dev/spk_xvector.ark:22734
+SSB0122 dump/22k/xvector/dev/spk_xvector.ark:24800
+SSB0133 dump/22k/xvector/dev/spk_xvector.ark:26866
+SSB0139 dump/22k/xvector/dev/spk_xvector.ark:28932
+SSB0145 dump/22k/xvector/dev/spk_xvector.ark:30998
+SSB0149 dump/22k/xvector/dev/spk_xvector.ark:33064
+SSB0193 dump/22k/xvector/dev/spk_xvector.ark:35130
+SSB0197 dump/22k/xvector/dev/spk_xvector.ark:37196
+SSB0200 dump/22k/xvector/dev/spk_xvector.ark:39262
+SSB0241 dump/22k/xvector/dev/spk_xvector.ark:41328
+SSB0246 dump/22k/xvector/dev/spk_xvector.ark:43394
+SSB0261 dump/22k/xvector/dev/spk_xvector.ark:45460
+SSB0267 dump/22k/xvector/dev/spk_xvector.ark:47526
+SSB0273 dump/22k/xvector/dev/spk_xvector.ark:49592
+SSB0287 dump/22k/xvector/dev/spk_xvector.ark:51658
+SSB0288 dump/22k/xvector/dev/spk_xvector.ark:53724
+SSB0299 dump/22k/xvector/dev/spk_xvector.ark:55790
+SSB0307 dump/22k/xvector/dev/spk_xvector.ark:57856
+SSB0309 dump/22k/xvector/dev/spk_xvector.ark:59922
+SSB0315 dump/22k/xvector/dev/spk_xvector.ark:61988
+SSB0316 dump/22k/xvector/dev/spk_xvector.ark:64054
+SSB0323 dump/22k/xvector/dev/spk_xvector.ark:66120
+SSB0338 dump/22k/xvector/dev/spk_xvector.ark:68186
+SSB0339 dump/22k/xvector/dev/spk_xvector.ark:70252
+SSB0341 dump/22k/xvector/dev/spk_xvector.ark:72318
+SSB0342 dump/22k/xvector/dev/spk_xvector.ark:74384
+SSB0354 dump/22k/xvector/dev/spk_xvector.ark:76450
+SSB0366 dump/22k/xvector/dev/spk_xvector.ark:78516
+SSB0375 dump/22k/xvector/dev/spk_xvector.ark:80582
+SSB0379 dump/22k/xvector/dev/spk_xvector.ark:82648
+SSB0380 dump/22k/xvector/dev/spk_xvector.ark:84714
+SSB0382 dump/22k/xvector/dev/spk_xvector.ark:86780
+SSB0385 dump/22k/xvector/dev/spk_xvector.ark:88846
+SSB0393 dump/22k/xvector/dev/spk_xvector.ark:90912
+SSB0394 dump/22k/xvector/dev/spk_xvector.ark:92978
+SSB0395 dump/22k/xvector/dev/spk_xvector.ark:95044
+SSB0407 dump/22k/xvector/dev/spk_xvector.ark:97110
+SSB0415 dump/22k/xvector/dev/spk_xvector.ark:99176
+SSB0426 dump/22k/xvector/dev/spk_xvector.ark:101242
+SSB0427 dump/22k/xvector/dev/spk_xvector.ark:103308
+SSB0434 dump/22k/xvector/dev/spk_xvector.ark:105374
+SSB0435 dump/22k/xvector/dev/spk_xvector.ark:107440
+SSB0470 dump/22k/xvector/dev/spk_xvector.ark:109506
+SSB0482 dump/22k/xvector/dev/spk_xvector.ark:111572
+SSB0502 dump/22k/xvector/dev/spk_xvector.ark:113638
+SSB0534 dump/22k/xvector/dev/spk_xvector.ark:115704
+SSB0535 dump/22k/xvector/dev/spk_xvector.ark:117770
+SSB0539 dump/22k/xvector/dev/spk_xvector.ark:119836
+SSB0544 dump/22k/xvector/dev/spk_xvector.ark:121902
+SSB0565 dump/22k/xvector/dev/spk_xvector.ark:123968
+SSB0570 dump/22k/xvector/dev/spk_xvector.ark:126034
+SSB0578 dump/22k/xvector/dev/spk_xvector.ark:128100
+SSB0588 dump/22k/xvector/dev/spk_xvector.ark:130166
+SSB0590 dump/22k/xvector/dev/spk_xvector.ark:132232
+SSB0594 dump/22k/xvector/dev/spk_xvector.ark:134298
+SSB0599 dump/22k/xvector/dev/spk_xvector.ark:136364
+SSB0601 dump/22k/xvector/dev/spk_xvector.ark:138430
+SSB0603 dump/22k/xvector/dev/spk_xvector.ark:140496
+SSB0606 dump/22k/xvector/dev/spk_xvector.ark:142562
+SSB0607 dump/22k/xvector/dev/spk_xvector.ark:144628
+SSB0609 dump/22k/xvector/dev/spk_xvector.ark:146694
+SSB0614 dump/22k/xvector/dev/spk_xvector.ark:148760
+SSB0623 dump/22k/xvector/dev/spk_xvector.ark:150826
+SSB0629 dump/22k/xvector/dev/spk_xvector.ark:152892
+SSB0631 dump/22k/xvector/dev/spk_xvector.ark:154958
+SSB0632 dump/22k/xvector/dev/spk_xvector.ark:157024
+SSB0666 dump/22k/xvector/dev/spk_xvector.ark:159090
+SSB0668 dump/22k/xvector/dev/spk_xvector.ark:161156
+SSB0671 dump/22k/xvector/dev/spk_xvector.ark:163222
+SSB0686 dump/22k/xvector/dev/spk_xvector.ark:165288
+SSB0700 dump/22k/xvector/dev/spk_xvector.ark:167354
+SSB0710 dump/22k/xvector/dev/spk_xvector.ark:169420
+SSB0720 dump/22k/xvector/dev/spk_xvector.ark:171486
+SSB0723 dump/22k/xvector/dev/spk_xvector.ark:173552
+SSB0737 dump/22k/xvector/dev/spk_xvector.ark:175618
+SSB0746 dump/22k/xvector/dev/spk_xvector.ark:177684
+SSB0748 dump/22k/xvector/dev/spk_xvector.ark:179750
+SSB0751 dump/22k/xvector/dev/spk_xvector.ark:181816
+SSB0758 dump/22k/xvector/dev/spk_xvector.ark:183882
+SSB0760 dump/22k/xvector/dev/spk_xvector.ark:185948
+SSB0762 dump/22k/xvector/dev/spk_xvector.ark:188014
+SSB0778 dump/22k/xvector/dev/spk_xvector.ark:190080
+SSB0780 dump/22k/xvector/dev/spk_xvector.ark:192146
+SSB0784 dump/22k/xvector/dev/spk_xvector.ark:194212
+SSB0786 dump/22k/xvector/dev/spk_xvector.ark:196278
+SSB0794 dump/22k/xvector/dev/spk_xvector.ark:198344
+SSB0913 dump/22k/xvector/dev/spk_xvector.ark:200410
+SSB0919 dump/22k/xvector/dev/spk_xvector.ark:202476
+SSB0935 dump/22k/xvector/dev/spk_xvector.ark:204542
+SSB0966 dump/22k/xvector/dev/spk_xvector.ark:206608
+SSB0987 dump/22k/xvector/dev/spk_xvector.ark:208674
+SSB1020 dump/22k/xvector/dev/spk_xvector.ark:210740
+SSB1024 dump/22k/xvector/dev/spk_xvector.ark:212806
+SSB1056 dump/22k/xvector/dev/spk_xvector.ark:214872
+SSB1072 dump/22k/xvector/dev/spk_xvector.ark:216938
+SSB1096 dump/22k/xvector/dev/spk_xvector.ark:219004
+SSB1100 dump/22k/xvector/dev/spk_xvector.ark:221070
+SSB1115 dump/22k/xvector/dev/spk_xvector.ark:223136
+SSB1125 dump/22k/xvector/dev/spk_xvector.ark:225202
+SSB1131 dump/22k/xvector/dev/spk_xvector.ark:227268
+SSB1136 dump/22k/xvector/dev/spk_xvector.ark:229334
+SSB1161 dump/22k/xvector/dev/spk_xvector.ark:231400
+SSB1203 dump/22k/xvector/dev/spk_xvector.ark:233466
+SSB1218 dump/22k/xvector/dev/spk_xvector.ark:235532
+SSB1253 dump/22k/xvector/dev/spk_xvector.ark:237598
+SSB1341 dump/22k/xvector/dev/spk_xvector.ark:239664
+SSB1366 dump/22k/xvector/dev/spk_xvector.ark:241730
+SSB1448 dump/22k/xvector/dev/spk_xvector.ark:243796
+SSB1555 dump/22k/xvector/dev/spk_xvector.ark:245862
+SSB1563 dump/22k/xvector/dev/spk_xvector.ark:247928
+SSB1567 dump/22k/xvector/dev/spk_xvector.ark:249994
+SSB1575 dump/22k/xvector/dev/spk_xvector.ark:252060
+SSB1585 dump/22k/xvector/dev/spk_xvector.ark:254126
+SSB1593 dump/22k/xvector/dev/spk_xvector.ark:256192
+SSB1607 dump/22k/xvector/dev/spk_xvector.ark:258258
+SSB1624 dump/22k/xvector/dev/spk_xvector.ark:260324
+SSB1625 dump/22k/xvector/dev/spk_xvector.ark:262390
+SSB1650 dump/22k/xvector/dev/spk_xvector.ark:264456
+SSB1670 dump/22k/xvector/dev/spk_xvector.ark:266522
+SSB1684 dump/22k/xvector/dev/spk_xvector.ark:268588
+SSB1686 dump/22k/xvector/dev/spk_xvector.ark:270654
+SSB1699 dump/22k/xvector/dev/spk_xvector.ark:272720
+SSB1711 dump/22k/xvector/dev/spk_xvector.ark:274786
+SSB1828 dump/22k/xvector/dev/spk_xvector.ark:276852
+SSB1832 dump/22k/xvector/dev/spk_xvector.ark:278918
+SSB1837 dump/22k/xvector/dev/spk_xvector.ark:280984
+SSB1863 dump/22k/xvector/dev/spk_xvector.ark:283050
+SSB1935 dump/22k/xvector/dev/spk_xvector.ark:285116
+SSB1939 dump/22k/xvector/dev/spk_xvector.ark:287182
+SSB1956 dump/22k/xvector/dev/spk_xvector.ark:289248

dump/22k/xvector/test/spk_xvector.scp

@@ -0,0 +1,214 @@
+SSB0005 dump/22k/xvector/test/spk_xvector.ark:8
+SSB0009 dump/22k/xvector/test/spk_xvector.ark:2074
+SSB0011 dump/22k/xvector/test/spk_xvector.ark:4140
+SSB0012 dump/22k/xvector/test/spk_xvector.ark:6206
+SSB0016 dump/22k/xvector/test/spk_xvector.ark:8272
+SSB0018 dump/22k/xvector/test/spk_xvector.ark:10338
+SSB0033 dump/22k/xvector/test/spk_xvector.ark:12404
+SSB0038 dump/22k/xvector/test/spk_xvector.ark:14470
+SSB0043 dump/22k/xvector/test/spk_xvector.ark:16536
+SSB0057 dump/22k/xvector/test/spk_xvector.ark:18602
+SSB0073 dump/22k/xvector/test/spk_xvector.ark:20668
+SSB0080 dump/22k/xvector/test/spk_xvector.ark:22734
+SSB0112 dump/22k/xvector/test/spk_xvector.ark:24800
+SSB0122 dump/22k/xvector/test/spk_xvector.ark:26866
+SSB0133 dump/22k/xvector/test/spk_xvector.ark:28932
+SSB0139 dump/22k/xvector/test/spk_xvector.ark:30998
+SSB0145 dump/22k/xvector/test/spk_xvector.ark:33064
+SSB0149 dump/22k/xvector/test/spk_xvector.ark:35130
+SSB0193 dump/22k/xvector/test/spk_xvector.ark:37196
+SSB0197 dump/22k/xvector/test/spk_xvector.ark:39262
+SSB0200 dump/22k/xvector/test/spk_xvector.ark:41328
+SSB0241 dump/22k/xvector/test/spk_xvector.ark:43394
+SSB0246 dump/22k/xvector/test/spk_xvector.ark:45460
+SSB0261 dump/22k/xvector/test/spk_xvector.ark:47526
+SSB0267 dump/22k/xvector/test/spk_xvector.ark:49592
+SSB0273 dump/22k/xvector/test/spk_xvector.ark:51658
+SSB0287 dump/22k/xvector/test/spk_xvector.ark:53724
+SSB0288 dump/22k/xvector/test/spk_xvector.ark:55790
+SSB0299 dump/22k/xvector/test/spk_xvector.ark:57856
+SSB0307 dump/22k/xvector/test/spk_xvector.ark:59922
+SSB0309 dump/22k/xvector/test/spk_xvector.ark:61988
+SSB0315 dump/22k/xvector/test/spk_xvector.ark:64054
+SSB0316 dump/22k/xvector/test/spk_xvector.ark:66120
+SSB0323 dump/22k/xvector/test/spk_xvector.ark:68186
+SSB0338 dump/22k/xvector/test/spk_xvector.ark:70252
+SSB0339 dump/22k/xvector/test/spk_xvector.ark:72318
+SSB0341 dump/22k/xvector/test/spk_xvector.ark:74384
+SSB0342 dump/22k/xvector/test/spk_xvector.ark:76450
+SSB0354 dump/22k/xvector/test/spk_xvector.ark:78516
+SSB0366 dump/22k/xvector/test/spk_xvector.ark:80582
+SSB0375 dump/22k/xvector/test/spk_xvector.ark:82648
+SSB0379 dump/22k/xvector/test/spk_xvector.ark:84714
+SSB0380 dump/22k/xvector/test/spk_xvector.ark:86780
+SSB0382 dump/22k/xvector/test/spk_xvector.ark:88846
+SSB0385 dump/22k/xvector/test/spk_xvector.ark:90912
+SSB0393 dump/22k/xvector/test/spk_xvector.ark:92978
+SSB0394 dump/22k/xvector/test/spk_xvector.ark:95044
+SSB0395 dump/22k/xvector/test/spk_xvector.ark:97110
+SSB0407 dump/22k/xvector/test/spk_xvector.ark:99176
+SSB0415 dump/22k/xvector/test/spk_xvector.ark:101242
+SSB0427 dump/22k/xvector/test/spk_xvector.ark:103308
+SSB0434 dump/22k/xvector/test/spk_xvector.ark:105374
+SSB0435 dump/22k/xvector/test/spk_xvector.ark:107440
+SSB0470 dump/22k/xvector/test/spk_xvector.ark:109506
+SSB0482 dump/22k/xvector/test/spk_xvector.ark:111572
+SSB0502 dump/22k/xvector/test/spk_xvector.ark:113638
+SSB0534 dump/22k/xvector/test/spk_xvector.ark:115704
+SSB0535 dump/22k/xvector/test/spk_xvector.ark:117770
+SSB0539 dump/22k/xvector/test/spk_xvector.ark:119836
+SSB0544 dump/22k/xvector/test/spk_xvector.ark:121902
+SSB0565 dump/22k/xvector/test/spk_xvector.ark:123968
+SSB0570 dump/22k/xvector/test/spk_xvector.ark:126034
+SSB0578 dump/22k/xvector/test/spk_xvector.ark:128100
+SSB0588 dump/22k/xvector/test/spk_xvector.ark:130166
+SSB0590 dump/22k/xvector/test/spk_xvector.ark:132232
+SSB0594 dump/22k/xvector/test/spk_xvector.ark:134298
+SSB0599 dump/22k/xvector/test/spk_xvector.ark:136364
+SSB0601 dump/22k/xvector/test/spk_xvector.ark:138430
+SSB0603 dump/22k/xvector/test/spk_xvector.ark:140496
+SSB0606 dump/22k/xvector/test/spk_xvector.ark:142562
+SSB0607 dump/22k/xvector/test/spk_xvector.ark:144628
+SSB0609 dump/22k/xvector/test/spk_xvector.ark:146694
+SSB0614 dump/22k/xvector/test/spk_xvector.ark:148760
+SSB0623 dump/22k/xvector/test/spk_xvector.ark:150826
+SSB0629 dump/22k/xvector/test/spk_xvector.ark:152892
+SSB0631 dump/22k/xvector/test/spk_xvector.ark:154958
+SSB0632 dump/22k/xvector/test/spk_xvector.ark:157024
+SSB0666 dump/22k/xvector/test/spk_xvector.ark:159090
+SSB0668 dump/22k/xvector/test/spk_xvector.ark:161156
+SSB0671 dump/22k/xvector/test/spk_xvector.ark:163222
+SSB0686 dump/22k/xvector/test/spk_xvector.ark:165288
+SSB0693 dump/22k/xvector/test/spk_xvector.ark:167354
+SSB0700 dump/22k/xvector/test/spk_xvector.ark:169420
+SSB0702 dump/22k/xvector/test/spk_xvector.ark:171486
+SSB0710 dump/22k/xvector/test/spk_xvector.ark:173552
+SSB0711 dump/22k/xvector/test/spk_xvector.ark:175618
+SSB0716 dump/22k/xvector/test/spk_xvector.ark:177684
+SSB0717 dump/22k/xvector/test/spk_xvector.ark:179750
+SSB0720 dump/22k/xvector/test/spk_xvector.ark:181816
+SSB0723 dump/22k/xvector/test/spk_xvector.ark:183882
+SSB0736 dump/22k/xvector/test/spk_xvector.ark:185948
+SSB0737 dump/22k/xvector/test/spk_xvector.ark:188014
+SSB0746 dump/22k/xvector/test/spk_xvector.ark:190080
+SSB0749 dump/22k/xvector/test/spk_xvector.ark:192146
+SSB0751 dump/22k/xvector/test/spk_xvector.ark:194212
+SSB0758 dump/22k/xvector/test/spk_xvector.ark:196278
+SSB0760 dump/22k/xvector/test/spk_xvector.ark:198344
+SSB0762 dump/22k/xvector/test/spk_xvector.ark:200410
+SSB0778 dump/22k/xvector/test/spk_xvector.ark:202476
+SSB0780 dump/22k/xvector/test/spk_xvector.ark:204542
+SSB0784 dump/22k/xvector/test/spk_xvector.ark:206608
+SSB0786 dump/22k/xvector/test/spk_xvector.ark:208674
+SSB0794 dump/22k/xvector/test/spk_xvector.ark:210740
+SSB0809 dump/22k/xvector/test/spk_xvector.ark:212806
+SSB0817 dump/22k/xvector/test/spk_xvector.ark:214872
+SSB0822 dump/22k/xvector/test/spk_xvector.ark:216938
+SSB0851 dump/22k/xvector/test/spk_xvector.ark:219004
+SSB0863 dump/22k/xvector/test/spk_xvector.ark:221070
+SSB0871 dump/22k/xvector/test/spk_xvector.ark:223136
+SSB0887 dump/22k/xvector/test/spk_xvector.ark:225202
+SSB0913 dump/22k/xvector/test/spk_xvector.ark:227268
+SSB0915 dump/22k/xvector/test/spk_xvector.ark:229334
+SSB0919 dump/22k/xvector/test/spk_xvector.ark:231400
+SSB0935 dump/22k/xvector/test/spk_xvector.ark:233466
+SSB0966 dump/22k/xvector/test/spk_xvector.ark:235532
+SSB0987 dump/22k/xvector/test/spk_xvector.ark:237598
+SSB0993 dump/22k/xvector/test/spk_xvector.ark:239664
+SSB0997 dump/22k/xvector/test/spk_xvector.ark:241730
+SSB1000 dump/22k/xvector/test/spk_xvector.ark:243796
+SSB1001 dump/22k/xvector/test/spk_xvector.ark:245862
+SSB1002 dump/22k/xvector/test/spk_xvector.ark:247928
+SSB1008 dump/22k/xvector/test/spk_xvector.ark:249994
+SSB1020 dump/22k/xvector/test/spk_xvector.ark:252060
+SSB1024 dump/22k/xvector/test/spk_xvector.ark:254126
+SSB1050 dump/22k/xvector/test/spk_xvector.ark:256192
+SSB1055 dump/22k/xvector/test/spk_xvector.ark:258258
+SSB1056 dump/22k/xvector/test/spk_xvector.ark:260324
+SSB1064 dump/22k/xvector/test/spk_xvector.ark:262390
+SSB1072 dump/22k/xvector/test/spk_xvector.ark:264456
+SSB1091 dump/22k/xvector/test/spk_xvector.ark:266522
+SSB1100 dump/22k/xvector/test/spk_xvector.ark:268588
+SSB1108 dump/22k/xvector/test/spk_xvector.ark:270654
+SSB1110 dump/22k/xvector/test/spk_xvector.ark:272720
+SSB1115 dump/22k/xvector/test/spk_xvector.ark:274786
+SSB1125 dump/22k/xvector/test/spk_xvector.ark:276852
+SSB1126 dump/22k/xvector/test/spk_xvector.ark:278918
+SSB1131 dump/22k/xvector/test/spk_xvector.ark:280984
+SSB1135 dump/22k/xvector/test/spk_xvector.ark:283050
+SSB1136 dump/22k/xvector/test/spk_xvector.ark:285116
+SSB1138 dump/22k/xvector/test/spk_xvector.ark:287182
+SSB1161 dump/22k/xvector/test/spk_xvector.ark:289248
+SSB1176 dump/22k/xvector/test/spk_xvector.ark:291314
+SSB1187 dump/22k/xvector/test/spk_xvector.ark:293380
+SSB1197 dump/22k/xvector/test/spk_xvector.ark:295446
+SSB1203 dump/22k/xvector/test/spk_xvector.ark:297512
+SSB1204 dump/22k/xvector/test/spk_xvector.ark:299578
+SSB1215 dump/22k/xvector/test/spk_xvector.ark:301644
+SSB1216 dump/22k/xvector/test/spk_xvector.ark:303710
+SSB1218 dump/22k/xvector/test/spk_xvector.ark:305776
+SSB1219 dump/22k/xvector/test/spk_xvector.ark:307842
+SSB1221 dump/22k/xvector/test/spk_xvector.ark:309908
+SSB1239 dump/22k/xvector/test/spk_xvector.ark:311974
+SSB1253 dump/22k/xvector/test/spk_xvector.ark:314040
+SSB1274 dump/22k/xvector/test/spk_xvector.ark:316106
+SSB1302 dump/22k/xvector/test/spk_xvector.ark:318172
+SSB1320 dump/22k/xvector/test/spk_xvector.ark:320238
+SSB1322 dump/22k/xvector/test/spk_xvector.ark:322304
+SSB1328 dump/22k/xvector/test/spk_xvector.ark:324370
+SSB1340 dump/22k/xvector/test/spk_xvector.ark:326436
+SSB1341 dump/22k/xvector/test/spk_xvector.ark:328502
+SSB1365 dump/22k/xvector/test/spk_xvector.ark:330568
+SSB1366 dump/22k/xvector/test/spk_xvector.ark:332634
+SSB1377 dump/22k/xvector/test/spk_xvector.ark:334700
+SSB1382 dump/22k/xvector/test/spk_xvector.ark:336766
+SSB1383 dump/22k/xvector/test/spk_xvector.ark:338832
+SSB1385 dump/22k/xvector/test/spk_xvector.ark:340898
+SSB1392 dump/22k/xvector/test/spk_xvector.ark:342964
+SSB1393 dump/22k/xvector/test/spk_xvector.ark:345030
+SSB1399 dump/22k/xvector/test/spk_xvector.ark:347096
+SSB1402 dump/22k/xvector/test/spk_xvector.ark:349162
+SSB1408 dump/22k/xvector/test/spk_xvector.ark:351228
+SSB1431 dump/22k/xvector/test/spk_xvector.ark:353294
+SSB1437 dump/22k/xvector/test/spk_xvector.ark:355360
+SSB1448 dump/22k/xvector/test/spk_xvector.ark:357426
+SSB1452 dump/22k/xvector/test/spk_xvector.ark:359492
+SSB1457 dump/22k/xvector/test/spk_xvector.ark:361558
+SSB1555 dump/22k/xvector/test/spk_xvector.ark:363624
+SSB1563 dump/22k/xvector/test/spk_xvector.ark:365690
+SSB1575 dump/22k/xvector/test/spk_xvector.ark:367756
+SSB1585 dump/22k/xvector/test/spk_xvector.ark:369822
+SSB1593 dump/22k/xvector/test/spk_xvector.ark:371888
+SSB1607 dump/22k/xvector/test/spk_xvector.ark:373954
+SSB1624 dump/22k/xvector/test/spk_xvector.ark:376020
+SSB1625 dump/22k/xvector/test/spk_xvector.ark:378086
+SSB1630 dump/22k/xvector/test/spk_xvector.ark:380152
+SSB1650 dump/22k/xvector/test/spk_xvector.ark:382218
+SSB1670 dump/22k/xvector/test/spk_xvector.ark:384284
+SSB1684 dump/22k/xvector/test/spk_xvector.ark:386350
+SSB1686 dump/22k/xvector/test/spk_xvector.ark:388416
+SSB1699 dump/22k/xvector/test/spk_xvector.ark:390482
+SSB1711 dump/22k/xvector/test/spk_xvector.ark:392548
+SSB1728 dump/22k/xvector/test/spk_xvector.ark:394614
+SSB1739 dump/22k/xvector/test/spk_xvector.ark:396680
+SSB1745 dump/22k/xvector/test/spk_xvector.ark:398746
+SSB1759 dump/22k/xvector/test/spk_xvector.ark:400812
+SSB1781 dump/22k/xvector/test/spk_xvector.ark:402878
+SSB1782 dump/22k/xvector/test/spk_xvector.ark:404944
+SSB1806 dump/22k/xvector/test/spk_xvector.ark:407010
+SSB1809 dump/22k/xvector/test/spk_xvector.ark:409076
+SSB1810 dump/22k/xvector/test/spk_xvector.ark:411142
+SSB1828 dump/22k/xvector/test/spk_xvector.ark:413208
+SSB1831 dump/22k/xvector/test/spk_xvector.ark:415274
+SSB1832 dump/22k/xvector/test/spk_xvector.ark:417340
+SSB1837 dump/22k/xvector/test/spk_xvector.ark:419406
+SSB1846 dump/22k/xvector/test/spk_xvector.ark:421472
+SSB1863 dump/22k/xvector/test/spk_xvector.ark:423538
+SSB1872 dump/22k/xvector/test/spk_xvector.ark:425604
+SSB1878 dump/22k/xvector/test/spk_xvector.ark:427670
+SSB1891 dump/22k/xvector/test/spk_xvector.ark:429736
+SSB1902 dump/22k/xvector/test/spk_xvector.ark:431802
+SSB1918 dump/22k/xvector/test/spk_xvector.ark:433868
+SSB1935 dump/22k/xvector/test/spk_xvector.ark:435934
+SSB1939 dump/22k/xvector/test/spk_xvector.ark:438000
+SSB1956 dump/22k/xvector/test/spk_xvector.ark:440066

dump/22k/xvector/train_no_dev/spk_xvector.scp

@@ -0,0 +1,174 @@
+SSB0005 dump/22k/xvector/train_no_dev/spk_xvector.ark:8
+SSB0009 dump/22k/xvector/train_no_dev/spk_xvector.ark:2074
+SSB0011 dump/22k/xvector/train_no_dev/spk_xvector.ark:4140
+SSB0012 dump/22k/xvector/train_no_dev/spk_xvector.ark:6206
+SSB0016 dump/22k/xvector/train_no_dev/spk_xvector.ark:8272
+SSB0018 dump/22k/xvector/train_no_dev/spk_xvector.ark:10338
+SSB0033 dump/22k/xvector/train_no_dev/spk_xvector.ark:12404
+SSB0038 dump/22k/xvector/train_no_dev/spk_xvector.ark:14470
+SSB0043 dump/22k/xvector/train_no_dev/spk_xvector.ark:16536
+SSB0057 dump/22k/xvector/train_no_dev/spk_xvector.ark:18602
+SSB0073 dump/22k/xvector/train_no_dev/spk_xvector.ark:20668
+SSB0080 dump/22k/xvector/train_no_dev/spk_xvector.ark:22734
+SSB0112 dump/22k/xvector/train_no_dev/spk_xvector.ark:24800
+SSB0122 dump/22k/xvector/train_no_dev/spk_xvector.ark:26866
+SSB0133 dump/22k/xvector/train_no_dev/spk_xvector.ark:28932
+SSB0139 dump/22k/xvector/train_no_dev/spk_xvector.ark:30998
+SSB0145 dump/22k/xvector/train_no_dev/spk_xvector.ark:33064
+SSB0149 dump/22k/xvector/train_no_dev/spk_xvector.ark:35130
+SSB0193 dump/22k/xvector/train_no_dev/spk_xvector.ark:37196
+SSB0197 dump/22k/xvector/train_no_dev/spk_xvector.ark:39262
+SSB0200 dump/22k/xvector/train_no_dev/spk_xvector.ark:41328
+SSB0241 dump/22k/xvector/train_no_dev/spk_xvector.ark:43394
+SSB0246 dump/22k/xvector/train_no_dev/spk_xvector.ark:45460
+SSB0261 dump/22k/xvector/train_no_dev/spk_xvector.ark:47526
+SSB0267 dump/22k/xvector/train_no_dev/spk_xvector.ark:49592
+SSB0273 dump/22k/xvector/train_no_dev/spk_xvector.ark:51658
+SSB0287 dump/22k/xvector/train_no_dev/spk_xvector.ark:53724
+SSB0288 dump/22k/xvector/train_no_dev/spk_xvector.ark:55790
+SSB0299 dump/22k/xvector/train_no_dev/spk_xvector.ark:57856
+SSB0307 dump/22k/xvector/train_no_dev/spk_xvector.ark:59922
+SSB0309 dump/22k/xvector/train_no_dev/spk_xvector.ark:61988
+SSB0315 dump/22k/xvector/train_no_dev/spk_xvector.ark:64054
+SSB0316 dump/22k/xvector/train_no_dev/spk_xvector.ark:66120
+SSB0323 dump/22k/xvector/train_no_dev/spk_xvector.ark:68186
+SSB0338 dump/22k/xvector/train_no_dev/spk_xvector.ark:70252
+SSB0339 dump/22k/xvector/train_no_dev/spk_xvector.ark:72318
+SSB0341 dump/22k/xvector/train_no_dev/spk_xvector.ark:74384
+SSB0342 dump/22k/xvector/train_no_dev/spk_xvector.ark:76450
+SSB0354 dump/22k/xvector/train_no_dev/spk_xvector.ark:78516
+SSB0366 dump/22k/xvector/train_no_dev/spk_xvector.ark:80582
+SSB0375 dump/22k/xvector/train_no_dev/spk_xvector.ark:82648
+SSB0379 dump/22k/xvector/train_no_dev/spk_xvector.ark:84714
+SSB0380 dump/22k/xvector/train_no_dev/spk_xvector.ark:86780
+SSB0382 dump/22k/xvector/train_no_dev/spk_xvector.ark:88846
+SSB0385 dump/22k/xvector/train_no_dev/spk_xvector.ark:90912
+SSB0393 dump/22k/xvector/train_no_dev/spk_xvector.ark:92978
+SSB0394 dump/22k/xvector/train_no_dev/spk_xvector.ark:95044
+SSB0395 dump/22k/xvector/train_no_dev/spk_xvector.ark:97110
+SSB0407 dump/22k/xvector/train_no_dev/spk_xvector.ark:99176
+SSB0415 dump/22k/xvector/train_no_dev/spk_xvector.ark:101242
+SSB0426 dump/22k/xvector/train_no_dev/spk_xvector.ark:103308
+SSB0427 dump/22k/xvector/train_no_dev/spk_xvector.ark:105374
+SSB0434 dump/22k/xvector/train_no_dev/spk_xvector.ark:107440
+SSB0435 dump/22k/xvector/train_no_dev/spk_xvector.ark:109506
+SSB0470 dump/22k/xvector/train_no_dev/spk_xvector.ark:111572
+SSB0482 dump/22k/xvector/train_no_dev/spk_xvector.ark:113638
+SSB0502 dump/22k/xvector/train_no_dev/spk_xvector.ark:115704
+SSB0534 dump/22k/xvector/train_no_dev/spk_xvector.ark:117770
+SSB0535 dump/22k/xvector/train_no_dev/spk_xvector.ark:119836
+SSB0539 dump/22k/xvector/train_no_dev/spk_xvector.ark:121902
+SSB0544 dump/22k/xvector/train_no_dev/spk_xvector.ark:123968
+SSB0565 dump/22k/xvector/train_no_dev/spk_xvector.ark:126034
+SSB0570 dump/22k/xvector/train_no_dev/spk_xvector.ark:128100
+SSB0578 dump/22k/xvector/train_no_dev/spk_xvector.ark:130166
+SSB0588 dump/22k/xvector/train_no_dev/spk_xvector.ark:132232
+SSB0590 dump/22k/xvector/train_no_dev/spk_xvector.ark:134298
+SSB0594 dump/22k/xvector/train_no_dev/spk_xvector.ark:136364
+SSB0599 dump/22k/xvector/train_no_dev/spk_xvector.ark:138430
+SSB0601 dump/22k/xvector/train_no_dev/spk_xvector.ark:140496
+SSB0603 dump/22k/xvector/train_no_dev/spk_xvector.ark:142562
+SSB0606 dump/22k/xvector/train_no_dev/spk_xvector.ark:144628
+SSB0607 dump/22k/xvector/train_no_dev/spk_xvector.ark:146694
+SSB0609 dump/22k/xvector/train_no_dev/spk_xvector.ark:148760
+SSB0614 dump/22k/xvector/train_no_dev/spk_xvector.ark:150826
+SSB0623 dump/22k/xvector/train_no_dev/spk_xvector.ark:152892
+SSB0629 dump/22k/xvector/train_no_dev/spk_xvector.ark:154958
+SSB0631 dump/22k/xvector/train_no_dev/spk_xvector.ark:157024
+SSB0632 dump/22k/xvector/train_no_dev/spk_xvector.ark:159090
+SSB0666 dump/22k/xvector/train_no_dev/spk_xvector.ark:161156
+SSB0668 dump/22k/xvector/train_no_dev/spk_xvector.ark:163222
+SSB0671 dump/22k/xvector/train_no_dev/spk_xvector.ark:165288
+SSB0686 dump/22k/xvector/train_no_dev/spk_xvector.ark:167354
+SSB0700 dump/22k/xvector/train_no_dev/spk_xvector.ark:169420
+SSB0710 dump/22k/xvector/train_no_dev/spk_xvector.ark:171486
+SSB0720 dump/22k/xvector/train_no_dev/spk_xvector.ark:173552
+SSB0723 dump/22k/xvector/train_no_dev/spk_xvector.ark:175618
+SSB0737 dump/22k/xvector/train_no_dev/spk_xvector.ark:177684
+SSB0746 dump/22k/xvector/train_no_dev/spk_xvector.ark:179750
+SSB0748 dump/22k/xvector/train_no_dev/spk_xvector.ark:181816
+SSB0751 dump/22k/xvector/train_no_dev/spk_xvector.ark:183882
+SSB0758 dump/22k/xvector/train_no_dev/spk_xvector.ark:185948
+SSB0760 dump/22k/xvector/train_no_dev/spk_xvector.ark:188014
+SSB0762 dump/22k/xvector/train_no_dev/spk_xvector.ark:190080
+SSB0778 dump/22k/xvector/train_no_dev/spk_xvector.ark:192146
+SSB0780 dump/22k/xvector/train_no_dev/spk_xvector.ark:194212
+SSB0784 dump/22k/xvector/train_no_dev/spk_xvector.ark:196278
+SSB0786 dump/22k/xvector/train_no_dev/spk_xvector.ark:198344
+SSB0794 dump/22k/xvector/train_no_dev/spk_xvector.ark:200410
+SSB0817 dump/22k/xvector/train_no_dev/spk_xvector.ark:202476
+SSB0851 dump/22k/xvector/train_no_dev/spk_xvector.ark:204542
+SSB0863 dump/22k/xvector/train_no_dev/spk_xvector.ark:206608
+SSB0871 dump/22k/xvector/train_no_dev/spk_xvector.ark:208674
+SSB0887 dump/22k/xvector/train_no_dev/spk_xvector.ark:210740
+SSB0913 dump/22k/xvector/train_no_dev/spk_xvector.ark:212806
+SSB0915 dump/22k/xvector/train_no_dev/spk_xvector.ark:214872
+SSB0919 dump/22k/xvector/train_no_dev/spk_xvector.ark:216938
+SSB0935 dump/22k/xvector/train_no_dev/spk_xvector.ark:219004
+SSB0966 dump/22k/xvector/train_no_dev/spk_xvector.ark:221070
+SSB0987 dump/22k/xvector/train_no_dev/spk_xvector.ark:223136
+SSB1008 dump/22k/xvector/train_no_dev/spk_xvector.ark:225202
+SSB1020 dump/22k/xvector/train_no_dev/spk_xvector.ark:227268
+SSB1024 dump/22k/xvector/train_no_dev/spk_xvector.ark:229334
+SSB1050 dump/22k/xvector/train_no_dev/spk_xvector.ark:231400
+SSB1055 dump/22k/xvector/train_no_dev/spk_xvector.ark:233466
+SSB1056 dump/22k/xvector/train_no_dev/spk_xvector.ark:235532
+SSB1064 dump/22k/xvector/train_no_dev/spk_xvector.ark:237598
+SSB1072 dump/22k/xvector/train_no_dev/spk_xvector.ark:239664
+SSB1091 dump/22k/xvector/train_no_dev/spk_xvector.ark:241730
+SSB1096 dump/22k/xvector/train_no_dev/spk_xvector.ark:243796
+SSB1100 dump/22k/xvector/train_no_dev/spk_xvector.ark:245862
+SSB1108 dump/22k/xvector/train_no_dev/spk_xvector.ark:247928
+SSB1115 dump/22k/xvector/train_no_dev/spk_xvector.ark:249994
+SSB1125 dump/22k/xvector/train_no_dev/spk_xvector.ark:252060
+SSB1131 dump/22k/xvector/train_no_dev/spk_xvector.ark:254126
+SSB1136 dump/22k/xvector/train_no_dev/spk_xvector.ark:256192
+SSB1138 dump/22k/xvector/train_no_dev/spk_xvector.ark:258258
+SSB1161 dump/22k/xvector/train_no_dev/spk_xvector.ark:260324
+SSB1203 dump/22k/xvector/train_no_dev/spk_xvector.ark:262390
+SSB1204 dump/22k/xvector/train_no_dev/spk_xvector.ark:264456
+SSB1218 dump/22k/xvector/train_no_dev/spk_xvector.ark:266522
+SSB1221 dump/22k/xvector/train_no_dev/spk_xvector.ark:268588
+SSB1253 dump/22k/xvector/train_no_dev/spk_xvector.ark:270654
+SSB1320 dump/22k/xvector/train_no_dev/spk_xvector.ark:272720
+SSB1341 dump/22k/xvector/train_no_dev/spk_xvector.ark:274786
+SSB1366 dump/22k/xvector/train_no_dev/spk_xvector.ark:276852
+SSB1377 dump/22k/xvector/train_no_dev/spk_xvector.ark:278918
+SSB1383 dump/22k/xvector/train_no_dev/spk_xvector.ark:280984
+SSB1385 dump/22k/xvector/train_no_dev/spk_xvector.ark:283050
+SSB1392 dump/22k/xvector/train_no_dev/spk_xvector.ark:285116
+SSB1393 dump/22k/xvector/train_no_dev/spk_xvector.ark:287182
+SSB1408 dump/22k/xvector/train_no_dev/spk_xvector.ark:289248
+SSB1431 dump/22k/xvector/train_no_dev/spk_xvector.ark:291314
+SSB1437 dump/22k/xvector/train_no_dev/spk_xvector.ark:293380
+SSB1448 dump/22k/xvector/train_no_dev/spk_xvector.ark:295446
+SSB1555 dump/22k/xvector/train_no_dev/spk_xvector.ark:297512
+SSB1563 dump/22k/xvector/train_no_dev/spk_xvector.ark:299578
+SSB1567 dump/22k/xvector/train_no_dev/spk_xvector.ark:301644
+SSB1575 dump/22k/xvector/train_no_dev/spk_xvector.ark:303710
+SSB1585 dump/22k/xvector/train_no_dev/spk_xvector.ark:305776
+SSB1593 dump/22k/xvector/train_no_dev/spk_xvector.ark:307842
+SSB1607 dump/22k/xvector/train_no_dev/spk_xvector.ark:309908
+SSB1624 dump/22k/xvector/train_no_dev/spk_xvector.ark:311974
+SSB1625 dump/22k/xvector/train_no_dev/spk_xvector.ark:314040
+SSB1630 dump/22k/xvector/train_no_dev/spk_xvector.ark:316106
+SSB1650 dump/22k/xvector/train_no_dev/spk_xvector.ark:318172
+SSB1670 dump/22k/xvector/train_no_dev/spk_xvector.ark:320238
+SSB1684 dump/22k/xvector/train_no_dev/spk_xvector.ark:322304
+SSB1686 dump/22k/xvector/train_no_dev/spk_xvector.ark:324370
+SSB1699 dump/22k/xvector/train_no_dev/spk_xvector.ark:326436
+SSB1711 dump/22k/xvector/train_no_dev/spk_xvector.ark:328502
+SSB1759 dump/22k/xvector/train_no_dev/spk_xvector.ark:330568
+SSB1806 dump/22k/xvector/train_no_dev/spk_xvector.ark:332634
+SSB1828 dump/22k/xvector/train_no_dev/spk_xvector.ark:334700
+SSB1831 dump/22k/xvector/train_no_dev/spk_xvector.ark:336766
+SSB1832 dump/22k/xvector/train_no_dev/spk_xvector.ark:338832
+SSB1837 dump/22k/xvector/train_no_dev/spk_xvector.ark:340898
+SSB1846 dump/22k/xvector/train_no_dev/spk_xvector.ark:342964
+SSB1863 dump/22k/xvector/train_no_dev/spk_xvector.ark:345030
+SSB1878 dump/22k/xvector/train_no_dev/spk_xvector.ark:347096
+SSB1891 dump/22k/xvector/train_no_dev/spk_xvector.ark:349162
+SSB1918 dump/22k/xvector/train_no_dev/spk_xvector.ark:351228
+SSB1935 dump/22k/xvector/train_no_dev/spk_xvector.ark:353294
+SSB1939 dump/22k/xvector/train_no_dev/spk_xvector.ark:355360
+SSB1956 dump/22k/xvector/train_no_dev/spk_xvector.ark:357426

exp/22k/tts_train_raw_phn_pypinyin_g2p_phone/1000epoch.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a19654bc48e80bbc400d437620ba51800a3f74f2b4ffee43deb8f51b77721bfb
+size 386540402

exp/22k/tts_train_raw_phn_pypinyin_g2p_phone/config.yaml

@@ -0,0 +1,500 @@
+config: conf/train.yaml
+print_config: false
+log_level: INFO
+dry_run: false
+iterator_type: sequence
+output_dir: exp/22k/tts_train_raw_phn_pypinyin_g2p_phone
+ngpu: 1
+seed: 777
+num_workers: 4
+num_att_plot: 3
+dist_backend: nccl
+dist_init_method: env://
+dist_world_size: null
+dist_rank: null
+local_rank: 0
+dist_master_addr: null
+dist_master_port: null
+dist_launcher: null
+multiprocessing_distributed: false
+unused_parameters: true
+sharded_ddp: false
+cudnn_enabled: true
+cudnn_benchmark: false
+cudnn_deterministic: false
+collect_stats: false
+write_collected_feats: false
+max_epoch: 1000
+patience: null
+val_scheduler_criterion:
+- valid
+- loss
+early_stopping_criterion:
+- valid
+- loss
+- min
+best_model_criterion:
+-   - train
+    - total_count
+    - max
+keep_nbest_models: 10
+nbest_averaging_interval: 0
+grad_clip: -1
+grad_clip_type: 2.0
+grad_noise: false
+accum_grad: 1
+no_forward_run: false
+resume: true
+train_dtype: float32
+use_amp: false
+log_interval: 50
+use_matplotlib: true
+use_tensorboard: true
+create_graph_in_tensorboard: false
+use_wandb: false
+wandb_project: null
+wandb_id: null
+wandb_entity: null
+wandb_name: null
+wandb_model_log_interval: -1
+detect_anomaly: false
+pretrain_path: null
+init_param: []
+ignore_init_mismatch: false
+freeze_param: []
+num_iters_per_epoch: 1000
+batch_size: 20
+valid_batch_size: null
+batch_bins: 1250000
+valid_batch_bins: null
+train_shape_file:
+- exp/22k/tts_stats_raw_linear_spectrogram_phn_pypinyin_g2p_phone/train/text_shape.phn
+- exp/22k/tts_stats_raw_linear_spectrogram_phn_pypinyin_g2p_phone/train/speech_shape
+valid_shape_file:
+- exp/22k/tts_stats_raw_linear_spectrogram_phn_pypinyin_g2p_phone/valid/text_shape.phn
+- exp/22k/tts_stats_raw_linear_spectrogram_phn_pypinyin_g2p_phone/valid/speech_shape
+batch_type: numel
+valid_batch_type: null
+fold_length:
+- 150
+- 204800
+sort_in_batch: descending
+sort_batch: descending
+multiple_iterator: false
+chunk_length: 500
+chunk_shift_ratio: 0.5
+num_cache_chunks: 1024
+chunk_excluded_key_prefixes: []
+train_data_path_and_name_and_type:
+-   - dump/22k/raw/train_no_dev/text
+    - text
+    - text
+-   - dump/22k/raw/train_no_dev/wav.scp
+    - speech
+    - sound
+-   - dump/22k/xvector/train_no_dev/xvector.scp
+    - spembs
+    - kaldi_ark
+valid_data_path_and_name_and_type:
+-   - dump/22k/raw/dev/text
+    - text
+    - text
+-   - dump/22k/raw/dev/wav.scp
+    - speech
+    - sound
+-   - dump/22k/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
+exclude_weight_decay: false
+exclude_weight_decay_conf: {}
+optim: adamw
+optim_conf:
+    lr: 0.0002
+    betas:
+    - 0.8
+    - 0.99
+    eps: 1.0e-09
+    weight_decay: 0.0
+scheduler: exponentiallr
+scheduler_conf:
+    gamma: 0.999875
+optim2: adamw
+optim2_conf:
+    lr: 0.0002
+    betas:
+    - 0.8
+    - 0.99
+    eps: 1.0e-09
+    weight_decay: 0.0
+scheduler2: exponentiallr
+scheduler2_conf:
+    gamma: 0.999875
+generator_first: false
+token_list:
+- <blank>
+- <unk>
+- d
+- sh
+- j
+- i4
+- zh
+- l
+- x
+- e
+- b
+- g
+- i1
+- h
+- q
+- m
+- t
+- i2
+- u4
+- z
+- ch
+- i3
+- f
+- s
+- n
+- iou3
+- r
+- ian4
+- ong1
+- uei4
+- e4
+- en2
+- ai4
+- k
+- ing2
+- a1
+- uo3
+- u3
+- ao4
+- p
+- an1
+- eng2
+- e2
+- in1
+- c
+- ai2
+- an4
+- ian2
+- u2
+- ang4
+- ian1
+- ai3
+- ing1
+- ao3
+- uo4
+- ian3
+- ing4
+- ü4
+- ang1
+- u1
+- iao4
+- eng1
+- iou4
+- a4
+- üan2
+- ie4
+- ou4
+- er4
+- en1
+- ong2
+- e1
+- an3
+- ei4
+- uo2
+- ou3
+- ang2
+- iang4
+- ou1
+- ang3
+- an2
+- eng4
+- ong4
+- uan4
+- a3
+- ia4
+- ia1
+- iao1
+- iang1
+- iou2
+- uo1
+- ei3
+- iao3
+- in4
+- e3
+- ü3
+- iang3
+- uei2
+- en3
+- uan1
+- ie3
+- ao1
+- ai1
+- üe4
+- ü2
+- ing3
+- en4
+- uei1
+- er2
+- uan3
+- ü1
+- in3
+- en
+- üe2
+- ie2
+- ei2
+- ua4
+- uan2
+- in2
+- a2
+- ie1
+- iang2
+- ou2
+- ong3
+- uang3
+- eng3
+- uen1
+- uai4
+- ün4
+- uang4
+- uei3
+- uen2
+- uen4
+- i
+- iong4
+- v3
+- iao2
+- üan4
+- uang1
+- ei1
+- o2
+- iou1
+- uang2
+- a
+- ao2
+- o1
+- ua2
+- uen3
+- ua1
+- v4
+- üan3
+- ün1
+- üe1
+- ün2
+- o4
+- er3
+- iong3
+- üan1
+- ia3
+- ia2
+- iong1
+- üe3
+- ve4
+- iong2
+- uai2
+- er
+- ua3
+- uai1
+- ou
+- ün3
+- uai3
+- ia
+- uo
+- o3
+- v2
+- ueng1
+- o
+- ei
+- ua
+- io1
+- <sos/eos>
+odim: null
+model_conf: {}
+use_preprocessor: true
+token_type: phn
+bpemodel: null
+non_linguistic_symbols: null
+cleaner: null
+g2p: pypinyin_g2p_phone
+feats_extract: linear_spectrogram
+feats_extract_conf:
+    n_fft: 1024
+    hop_length: 256
+    win_length: null
+normalize: null
+normalize_conf: {}
+tts: vits
+tts_conf:
+    generator_type: vits_generator
+    generator_params:
+        hidden_channels: 192
+        spks: -1
+        spk_embed_dim: 512
+        global_channels: 256
+        segment_size: 32
+        text_encoder_attention_heads: 2
+        text_encoder_ffn_expand: 4
+        text_encoder_blocks: 6
+        text_encoder_positionwise_layer_type: conv1d
+        text_encoder_positionwise_conv_kernel_size: 3
+        text_encoder_positional_encoding_layer_type: rel_pos
+        text_encoder_self_attention_layer_type: rel_selfattn
+        text_encoder_activation_type: swish
+        text_encoder_normalize_before: true
+        text_encoder_dropout_rate: 0.1
+        text_encoder_positional_dropout_rate: 0.0
+        text_encoder_attention_dropout_rate: 0.1
+        use_macaron_style_in_text_encoder: true
+        use_conformer_conv_in_text_encoder: false
+        text_encoder_conformer_kernel_size: -1
+        decoder_kernel_size: 7
+        decoder_channels: 512
+        decoder_upsample_scales:
+        - 8
+        - 8
+        - 2
+        - 2
+        decoder_upsample_kernel_sizes:
+        - 16
+        - 16
+        - 4
+        - 4
+        decoder_resblock_kernel_sizes:
+        - 3
+        - 7
+        - 11
+        decoder_resblock_dilations:
+        -   - 1
+            - 3
+            - 5
+        -   - 1
+            - 3
+            - 5
+        -   - 1
+            - 3
+            - 5
+        use_weight_norm_in_decoder: true
+        posterior_encoder_kernel_size: 5
+        posterior_encoder_layers: 16
+        posterior_encoder_stacks: 1
+        posterior_encoder_base_dilation: 1
+        posterior_encoder_dropout_rate: 0.0
+        use_weight_norm_in_posterior_encoder: true
+        flow_flows: 4
+        flow_kernel_size: 5
+        flow_base_dilation: 1
+        flow_layers: 4
+        flow_dropout_rate: 0.0
+        use_weight_norm_in_flow: true
+        use_only_mean_in_flow: true
+        stochastic_duration_predictor_kernel_size: 3
+        stochastic_duration_predictor_dropout_rate: 0.5
+        stochastic_duration_predictor_flows: 4
+        stochastic_duration_predictor_dds_conv_layers: 3
+        vocabs: 180
+        aux_channels: 513
+    discriminator_type: hifigan_multi_scale_multi_period_discriminator
+    discriminator_params:
+        scales: 1
+        scale_downsample_pooling: AvgPool1d
+        scale_downsample_pooling_params:
+            kernel_size: 4
+            stride: 2
+            padding: 2
+        scale_discriminator_params:
+            in_channels: 1
+            out_channels: 1
+            kernel_sizes:
+            - 15
+            - 41
+            - 5
+            - 3
+            channels: 128
+            max_downsample_channels: 1024
+            max_groups: 16
+            bias: true
+            downsample_scales:
+            - 2
+            - 2
+            - 4
+            - 4
+            - 1
+            nonlinear_activation: LeakyReLU
+            nonlinear_activation_params:
+                negative_slope: 0.1
+            use_weight_norm: true
+            use_spectral_norm: false
+        follow_official_norm: false
+        periods:
+        - 2
+        - 3
+        - 5
+        - 7
+        - 11
+        period_discriminator_params:
+            in_channels: 1
+            out_channels: 1
+            kernel_sizes:
+            - 5
+            - 3
+            channels: 32
+            downsample_scales:
+            - 3
+            - 3
+            - 3
+            - 3
+            - 1
+            max_downsample_channels: 1024
+            bias: true
+            nonlinear_activation: LeakyReLU
+            nonlinear_activation_params:
+                negative_slope: 0.1
+            use_weight_norm: true
+            use_spectral_norm: false
+    generator_adv_loss_params:
+        average_by_discriminators: false
+        loss_type: mse
+    discriminator_adv_loss_params:
+        average_by_discriminators: false
+        loss_type: mse
+    feat_match_loss_params:
+        average_by_discriminators: false
+        average_by_layers: false
+        include_final_outputs: true
+    mel_loss_params:
+        fs: 22050
+        n_fft: 1024
+        hop_length: 256
+        win_length: null
+        window: hann
+        n_mels: 80
+        fmin: 0
+        fmax: null
+        log_base: null
+    lambda_adv: 1.0
+    lambda_mel: 45.0
+    lambda_feat_match: 2.0
+    lambda_dur: 1.0
+    lambda_kl: 1.0
+    sampling_rate: 22050
+    cache_generator_outputs: true
+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
+version: '202301'
+distributed: false

meta.yaml

@@ -0,0 +1,8 @@
+espnet: '202301'
+files:
+  model_file: exp/22k/tts_train_raw_phn_pypinyin_g2p_phone/1000epoch.pth
+python: "3.9.16 (main, Mar  8 2023, 14:00:05) \n[GCC 11.2.0]"
+timestamp: 1685075843.891187
+torch: 1.12.1
+yaml_files:
+  train_config: exp/22k/tts_train_raw_phn_pypinyin_g2p_phone/config.yaml