Siddhant commited on
Commit
222bd6f
1 Parent(s): 55cc285

import from zenodo

Browse files
Files changed (24) hide show
  1. README.md +50 -0
  2. dump/xvector/dev/spk_xvector.ark +0 -0
  3. dump/xvector/dev/spk_xvector.scp +96 -0
  4. dump/xvector/eval1/spk_xvector.ark +0 -0
  5. dump/xvector/eval1/spk_xvector.scp +81 -0
  6. dump/xvector/tr_no_dev/spk_xvector.ark +0 -0
  7. dump/xvector/tr_no_dev/spk_xvector.scp +0 -0
  8. exp/tts_train_gst+xvector_conformer_fastspeech2_transformer_teacher_raw_phn_tacotron_g2p_en_no_space/config.yaml +316 -0
  9. exp/tts_train_gst+xvector_conformer_fastspeech2_transformer_teacher_raw_phn_tacotron_g2p_en_no_space/images/backward_time.png +0 -0
  10. exp/tts_train_gst+xvector_conformer_fastspeech2_transformer_teacher_raw_phn_tacotron_g2p_en_no_space/images/duration_loss.png +0 -0
  11. exp/tts_train_gst+xvector_conformer_fastspeech2_transformer_teacher_raw_phn_tacotron_g2p_en_no_space/images/energy_loss.png +0 -0
  12. exp/tts_train_gst+xvector_conformer_fastspeech2_transformer_teacher_raw_phn_tacotron_g2p_en_no_space/images/forward_time.png +0 -0
  13. exp/tts_train_gst+xvector_conformer_fastspeech2_transformer_teacher_raw_phn_tacotron_g2p_en_no_space/images/iter_time.png +0 -0
  14. exp/tts_train_gst+xvector_conformer_fastspeech2_transformer_teacher_raw_phn_tacotron_g2p_en_no_space/images/l1_loss.png +0 -0
  15. exp/tts_train_gst+xvector_conformer_fastspeech2_transformer_teacher_raw_phn_tacotron_g2p_en_no_space/images/loss.png +0 -0
  16. exp/tts_train_gst+xvector_conformer_fastspeech2_transformer_teacher_raw_phn_tacotron_g2p_en_no_space/images/lr_0.png +0 -0
  17. exp/tts_train_gst+xvector_conformer_fastspeech2_transformer_teacher_raw_phn_tacotron_g2p_en_no_space/images/optim_step_time.png +0 -0
  18. exp/tts_train_gst+xvector_conformer_fastspeech2_transformer_teacher_raw_phn_tacotron_g2p_en_no_space/images/pitch_loss.png +0 -0
  19. exp/tts_train_gst+xvector_conformer_fastspeech2_transformer_teacher_raw_phn_tacotron_g2p_en_no_space/images/train_time.png +0 -0
  20. exp/tts_train_gst+xvector_conformer_fastspeech2_transformer_teacher_raw_phn_tacotron_g2p_en_no_space/train.loss.ave_5best.pth +3 -0
  21. exp/tts_train_gst+xvector_transformer_raw_phn_tacotron_g2p_en_no_space/decode_use_teacher_forcingtrue_train.loss.ave/stats/train/energy_stats.npz +0 -0
  22. exp/tts_train_gst+xvector_transformer_raw_phn_tacotron_g2p_en_no_space/decode_use_teacher_forcingtrue_train.loss.ave/stats/train/feats_stats.npz +0 -0
  23. exp/tts_train_gst+xvector_transformer_raw_phn_tacotron_g2p_en_no_space/decode_use_teacher_forcingtrue_train.loss.ave/stats/train/pitch_stats.npz +0 -0
  24. meta.yaml +8 -0
README.md ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - espnet
4
+ - audio
5
+ - text-to-speech
6
+ language: en
7
+ datasets:
8
+ - libritts
9
+ license: cc-by-4.0
10
+ ---
11
+ ## Example ESPnet2 TTS model
12
+ ### `kan-bayashi/libritts_gst+xvector_conformer_fastspeech2`
13
+ ♻️ Imported from https://zenodo.org/record/4418774/
14
+
15
+ This model was trained by kan-bayashi using libritts/tts1 recipe in [espnet](https://github.com/espnet/espnet/).
16
+ ### Demo: How to use in ESPnet2
17
+ ```python
18
+ # coming soon
19
+ ```
20
+ ### Citing ESPnet
21
+ ```BibTex
22
+ @inproceedings{watanabe2018espnet,
23
+ 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},
24
+ title={{ESPnet}: End-to-End Speech Processing Toolkit},
25
+ year={2018},
26
+ booktitle={Proceedings of Interspeech},
27
+ pages={2207--2211},
28
+ doi={10.21437/Interspeech.2018-1456},
29
+ url={http://dx.doi.org/10.21437/Interspeech.2018-1456}
30
+ }
31
+ @inproceedings{hayashi2020espnet,
32
+ title={{Espnet-TTS}: Unified, reproducible, and integratable open source end-to-end text-to-speech toolkit},
33
+ 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},
34
+ booktitle={Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
35
+ pages={7654--7658},
36
+ year={2020},
37
+ organization={IEEE}
38
+ }
39
+ ```
40
+ or arXiv:
41
+ ```bibtex
42
+ @misc{watanabe2018espnet,
43
+ title={ESPnet: End-to-End Speech Processing Toolkit},
44
+ 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},
45
+ year={2018},
46
+ eprint={1804.00015},
47
+ archivePrefix={arXiv},
48
+ primaryClass={cs.CL}
49
+ }
50
+ ```
dump/xvector/dev/spk_xvector.ark ADDED
Binary file (199 kB). View file
 
dump/xvector/dev/spk_xvector.scp ADDED
@@ -0,0 +1,96 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 1272_128104 dump/xvector/dev/spk_xvector.ark:12
2
+ 1272_135031 dump/xvector/dev/spk_xvector.ark:2082
3
+ 1272_141231 dump/xvector/dev/spk_xvector.ark:4152
4
+ 1462_170138 dump/xvector/dev/spk_xvector.ark:6222
5
+ 1462_170142 dump/xvector/dev/spk_xvector.ark:8292
6
+ 1462_170145 dump/xvector/dev/spk_xvector.ark:10362
7
+ 1673_143396 dump/xvector/dev/spk_xvector.ark:12432
8
+ 1673_143397 dump/xvector/dev/spk_xvector.ark:14502
9
+ 174_168635 dump/xvector/dev/spk_xvector.ark:16571
10
+ 174_50561 dump/xvector/dev/spk_xvector.ark:18639
11
+ 174_84280 dump/xvector/dev/spk_xvector.ark:20707
12
+ 1919_142785 dump/xvector/dev/spk_xvector.ark:22777
13
+ 1988_147956 dump/xvector/dev/spk_xvector.ark:24847
14
+ 1988_148538 dump/xvector/dev/spk_xvector.ark:26917
15
+ 1988_24833 dump/xvector/dev/spk_xvector.ark:28986
16
+ 1993_147149 dump/xvector/dev/spk_xvector.ark:31056
17
+ 1993_147964 dump/xvector/dev/spk_xvector.ark:33126
18
+ 1993_147965 dump/xvector/dev/spk_xvector.ark:35196
19
+ 1993_147966 dump/xvector/dev/spk_xvector.ark:37266
20
+ 2035_147960 dump/xvector/dev/spk_xvector.ark:39336
21
+ 2035_147961 dump/xvector/dev/spk_xvector.ark:41406
22
+ 2035_152373 dump/xvector/dev/spk_xvector.ark:43476
23
+ 2078_142845 dump/xvector/dev/spk_xvector.ark:45546
24
+ 2086_149214 dump/xvector/dev/spk_xvector.ark:47616
25
+ 2086_149220 dump/xvector/dev/spk_xvector.ark:49686
26
+ 2277_149874 dump/xvector/dev/spk_xvector.ark:51756
27
+ 2277_149896 dump/xvector/dev/spk_xvector.ark:53826
28
+ 2277_149897 dump/xvector/dev/spk_xvector.ark:55896
29
+ 2412_153947 dump/xvector/dev/spk_xvector.ark:57966
30
+ 2412_153948 dump/xvector/dev/spk_xvector.ark:60036
31
+ 2412_153954 dump/xvector/dev/spk_xvector.ark:62106
32
+ 2428_83699 dump/xvector/dev/spk_xvector.ark:64175
33
+ 2428_83705 dump/xvector/dev/spk_xvector.ark:66244
34
+ 251_118436 dump/xvector/dev/spk_xvector.ark:68313
35
+ 251_136532 dump/xvector/dev/spk_xvector.ark:70382
36
+ 251_137823 dump/xvector/dev/spk_xvector.ark:72451
37
+ 2803_154320 dump/xvector/dev/spk_xvector.ark:74521
38
+ 2803_154328 dump/xvector/dev/spk_xvector.ark:76591
39
+ 2803_161169 dump/xvector/dev/spk_xvector.ark:78661
40
+ 2902_9006 dump/xvector/dev/spk_xvector.ark:80729
41
+ 2902_9008 dump/xvector/dev/spk_xvector.ark:82797
42
+ 3000_15664 dump/xvector/dev/spk_xvector.ark:84866
43
+ 3081_166546 dump/xvector/dev/spk_xvector.ark:86936
44
+ 3170_137482 dump/xvector/dev/spk_xvector.ark:89006
45
+ 3536_23268 dump/xvector/dev/spk_xvector.ark:91075
46
+ 3536_8226 dump/xvector/dev/spk_xvector.ark:93143
47
+ 3576_138058 dump/xvector/dev/spk_xvector.ark:95213
48
+ 3752_4943 dump/xvector/dev/spk_xvector.ark:97281
49
+ 3752_4944 dump/xvector/dev/spk_xvector.ark:99349
50
+ 3853_163249 dump/xvector/dev/spk_xvector.ark:101419
51
+ 422_122949 dump/xvector/dev/spk_xvector.ark:103488
52
+ 5338_24615 dump/xvector/dev/spk_xvector.ark:105557
53
+ 5338_24640 dump/xvector/dev/spk_xvector.ark:107626
54
+ 5338_284437 dump/xvector/dev/spk_xvector.ark:109696
55
+ 5536_43358 dump/xvector/dev/spk_xvector.ark:111765
56
+ 5536_43359 dump/xvector/dev/spk_xvector.ark:113834
57
+ 5536_43363 dump/xvector/dev/spk_xvector.ark:115903
58
+ 5694_64025 dump/xvector/dev/spk_xvector.ark:117972
59
+ 5694_64029 dump/xvector/dev/spk_xvector.ark:120041
60
+ 5694_64038 dump/xvector/dev/spk_xvector.ark:122110
61
+ 5895_34615 dump/xvector/dev/spk_xvector.ark:124179
62
+ 5895_34622 dump/xvector/dev/spk_xvector.ark:126248
63
+ 5895_34629 dump/xvector/dev/spk_xvector.ark:128317
64
+ 6241_61943 dump/xvector/dev/spk_xvector.ark:130386
65
+ 6241_61946 dump/xvector/dev/spk_xvector.ark:132455
66
+ 6241_66616 dump/xvector/dev/spk_xvector.ark:134524
67
+ 6295_244435 dump/xvector/dev/spk_xvector.ark:136594
68
+ 6295_64301 dump/xvector/dev/spk_xvector.ark:138663
69
+ 6313_66125 dump/xvector/dev/spk_xvector.ark:140732
70
+ 6313_66129 dump/xvector/dev/spk_xvector.ark:142801
71
+ 6313_76958 dump/xvector/dev/spk_xvector.ark:144870
72
+ 6319_275224 dump/xvector/dev/spk_xvector.ark:146940
73
+ 6319_57405 dump/xvector/dev/spk_xvector.ark:149009
74
+ 6319_64726 dump/xvector/dev/spk_xvector.ark:151078
75
+ 6345_64257 dump/xvector/dev/spk_xvector.ark:153147
76
+ 6345_93302 dump/xvector/dev/spk_xvector.ark:155216
77
+ 6345_93306 dump/xvector/dev/spk_xvector.ark:157285
78
+ 652_129742 dump/xvector/dev/spk_xvector.ark:159354
79
+ 652_130737 dump/xvector/dev/spk_xvector.ark:161423
80
+ 777_126732 dump/xvector/dev/spk_xvector.ark:163492
81
+ 7850_111771 dump/xvector/dev/spk_xvector.ark:165562
82
+ 7850_281318 dump/xvector/dev/spk_xvector.ark:167632
83
+ 7850_286674 dump/xvector/dev/spk_xvector.ark:169702
84
+ 7850_73752 dump/xvector/dev/spk_xvector.ark:171771
85
+ 7976_105575 dump/xvector/dev/spk_xvector.ark:173841
86
+ 7976_110124 dump/xvector/dev/spk_xvector.ark:175911
87
+ 7976_110523 dump/xvector/dev/spk_xvector.ark:177981
88
+ 8297_275154 dump/xvector/dev/spk_xvector.ark:180051
89
+ 8297_275155 dump/xvector/dev/spk_xvector.ark:182121
90
+ 8297_275156 dump/xvector/dev/spk_xvector.ark:184191
91
+ 84_121123 dump/xvector/dev/spk_xvector.ark:186259
92
+ 84_121550 dump/xvector/dev/spk_xvector.ark:188327
93
+ 8842_302196 dump/xvector/dev/spk_xvector.ark:190397
94
+ 8842_302201 dump/xvector/dev/spk_xvector.ark:192467
95
+ 8842_302203 dump/xvector/dev/spk_xvector.ark:194537
96
+ 8842_304647 dump/xvector/dev/spk_xvector.ark:196607
dump/xvector/eval1/spk_xvector.ark ADDED
Binary file (168 kB). View file
 
dump/xvector/eval1/spk_xvector.scp ADDED
@@ -0,0 +1,81 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 1089_134686 dump/xvector/eval1/spk_xvector.ark:12
2
+ 1089_134691 dump/xvector/eval1/spk_xvector.ark:2082
3
+ 1188_133604 dump/xvector/eval1/spk_xvector.ark:4152
4
+ 121_121726 dump/xvector/eval1/spk_xvector.ark:6221
5
+ 121_123859 dump/xvector/eval1/spk_xvector.ark:8290
6
+ 121_127105 dump/xvector/eval1/spk_xvector.ark:10359
7
+ 1221_135766 dump/xvector/eval1/spk_xvector.ark:12429
8
+ 1221_135767 dump/xvector/eval1/spk_xvector.ark:14499
9
+ 1284_1180 dump/xvector/eval1/spk_xvector.ark:16567
10
+ 1284_1181 dump/xvector/eval1/spk_xvector.ark:18635
11
+ 1320_122612 dump/xvector/eval1/spk_xvector.ark:20705
12
+ 1320_122617 dump/xvector/eval1/spk_xvector.ark:22775
13
+ 1580_141083 dump/xvector/eval1/spk_xvector.ark:24845
14
+ 1580_141084 dump/xvector/eval1/spk_xvector.ark:26915
15
+ 1995_1826 dump/xvector/eval1/spk_xvector.ark:28983
16
+ 1995_1836 dump/xvector/eval1/spk_xvector.ark:31051
17
+ 1995_1837 dump/xvector/eval1/spk_xvector.ark:33119
18
+ 2300_131720 dump/xvector/eval1/spk_xvector.ark:35189
19
+ 237_126133 dump/xvector/eval1/spk_xvector.ark:37258
20
+ 237_134493 dump/xvector/eval1/spk_xvector.ark:39327
21
+ 237_134500 dump/xvector/eval1/spk_xvector.ark:41396
22
+ 260_123286 dump/xvector/eval1/spk_xvector.ark:43465
23
+ 260_123288 dump/xvector/eval1/spk_xvector.ark:45534
24
+ 260_123440 dump/xvector/eval1/spk_xvector.ark:47603
25
+ 2830_3979 dump/xvector/eval1/spk_xvector.ark:49671
26
+ 2830_3980 dump/xvector/eval1/spk_xvector.ark:51739
27
+ 2961_961 dump/xvector/eval1/spk_xvector.ark:53806
28
+ 3570_5694 dump/xvector/eval1/spk_xvector.ark:55874
29
+ 3570_5695 dump/xvector/eval1/spk_xvector.ark:57942
30
+ 3570_5696 dump/xvector/eval1/spk_xvector.ark:60010
31
+ 3575_170457 dump/xvector/eval1/spk_xvector.ark:62080
32
+ 3729_6852 dump/xvector/eval1/spk_xvector.ark:64148
33
+ 4077_13751 dump/xvector/eval1/spk_xvector.ark:66217
34
+ 4077_13754 dump/xvector/eval1/spk_xvector.ark:68286
35
+ 4446_2271 dump/xvector/eval1/spk_xvector.ark:70354
36
+ 4446_2273 dump/xvector/eval1/spk_xvector.ark:72422
37
+ 4446_2275 dump/xvector/eval1/spk_xvector.ark:74490
38
+ 4507_16021 dump/xvector/eval1/spk_xvector.ark:76559
39
+ 4970_29093 dump/xvector/eval1/spk_xvector.ark:78628
40
+ 4970_29095 dump/xvector/eval1/spk_xvector.ark:80697
41
+ 4992_23283 dump/xvector/eval1/spk_xvector.ark:82766
42
+ 4992_41797 dump/xvector/eval1/spk_xvector.ark:84835
43
+ 4992_41806 dump/xvector/eval1/spk_xvector.ark:86904
44
+ 5105_28233 dump/xvector/eval1/spk_xvector.ark:88973
45
+ 5105_28240 dump/xvector/eval1/spk_xvector.ark:91042
46
+ 5105_28241 dump/xvector/eval1/spk_xvector.ark:93111
47
+ 5142_33396 dump/xvector/eval1/spk_xvector.ark:95180
48
+ 5142_36377 dump/xvector/eval1/spk_xvector.ark:97249
49
+ 5142_36586 dump/xvector/eval1/spk_xvector.ark:99318
50
+ 5142_36600 dump/xvector/eval1/spk_xvector.ark:101387
51
+ 5639_40744 dump/xvector/eval1/spk_xvector.ark:103456
52
+ 5683_32865 dump/xvector/eval1/spk_xvector.ark:105525
53
+ 5683_32866 dump/xvector/eval1/spk_xvector.ark:107594
54
+ 5683_32879 dump/xvector/eval1/spk_xvector.ark:109663
55
+ 61_70970 dump/xvector/eval1/spk_xvector.ark:111730
56
+ 672_122797 dump/xvector/eval1/spk_xvector.ark:113799
57
+ 6829_68769 dump/xvector/eval1/spk_xvector.ark:115868
58
+ 6829_68771 dump/xvector/eval1/spk_xvector.ark:117937
59
+ 6930_75918 dump/xvector/eval1/spk_xvector.ark:120006
60
+ 6930_76324 dump/xvector/eval1/spk_xvector.ark:122075
61
+ 6930_81414 dump/xvector/eval1/spk_xvector.ark:124144
62
+ 7021_79730 dump/xvector/eval1/spk_xvector.ark:126213
63
+ 7021_79740 dump/xvector/eval1/spk_xvector.ark:128282
64
+ 7021_79759 dump/xvector/eval1/spk_xvector.ark:130351
65
+ 7021_85628 dump/xvector/eval1/spk_xvector.ark:132420
66
+ 7127_75946 dump/xvector/eval1/spk_xvector.ark:134489
67
+ 7127_75947 dump/xvector/eval1/spk_xvector.ark:136558
68
+ 7176_88083 dump/xvector/eval1/spk_xvector.ark:138627
69
+ 7176_92135 dump/xvector/eval1/spk_xvector.ark:140696
70
+ 7729_102255 dump/xvector/eval1/spk_xvector.ark:142766
71
+ 8224_274384 dump/xvector/eval1/spk_xvector.ark:144836
72
+ 8230_279154 dump/xvector/eval1/spk_xvector.ark:146906
73
+ 8455_210777 dump/xvector/eval1/spk_xvector.ark:148976
74
+ 8463_287645 dump/xvector/eval1/spk_xvector.ark:151046
75
+ 8463_294825 dump/xvector/eval1/spk_xvector.ark:153116
76
+ 8463_294828 dump/xvector/eval1/spk_xvector.ark:155186
77
+ 8555_284447 dump/xvector/eval1/spk_xvector.ark:157256
78
+ 8555_284449 dump/xvector/eval1/spk_xvector.ark:159326
79
+ 8555_292519 dump/xvector/eval1/spk_xvector.ark:161396
80
+ 908_157963 dump/xvector/eval1/spk_xvector.ark:163465
81
+ 908_31957 dump/xvector/eval1/spk_xvector.ark:165533
dump/xvector/tr_no_dev/spk_xvector.ark ADDED
Binary file (5.3 MB). View file
 
dump/xvector/tr_no_dev/spk_xvector.scp ADDED
The diff for this file is too large to render. See raw diff
 
exp/tts_train_gst+xvector_conformer_fastspeech2_transformer_teacher_raw_phn_tacotron_g2p_en_no_space/config.yaml ADDED
@@ -0,0 +1,316 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ config: conf/tuning/train_gst+xvector_conformer_fastspeech2.yaml
2
+ print_config: false
3
+ log_level: INFO
4
+ dry_run: false
5
+ iterator_type: sequence
6
+ output_dir: exp/tts_train_gst+xvector_conformer_fastspeech2_transformer_teacher_raw_phn_tacotron_g2p_en_no_space
7
+ ngpu: 1
8
+ seed: 0
9
+ num_workers: 1
10
+ num_att_plot: 3
11
+ dist_backend: nccl
12
+ dist_init_method: env://
13
+ dist_world_size: 4
14
+ dist_rank: 0
15
+ local_rank: 0
16
+ dist_master_addr: localhost
17
+ dist_master_port: 42200
18
+ dist_launcher: null
19
+ multiprocessing_distributed: true
20
+ cudnn_enabled: true
21
+ cudnn_benchmark: false
22
+ cudnn_deterministic: true
23
+ collect_stats: false
24
+ write_collected_feats: false
25
+ max_epoch: 500
26
+ patience: null
27
+ val_scheduler_criterion:
28
+ - valid
29
+ - loss
30
+ early_stopping_criterion:
31
+ - valid
32
+ - loss
33
+ - min
34
+ best_model_criterion:
35
+ - - valid
36
+ - loss
37
+ - min
38
+ - - train
39
+ - loss
40
+ - min
41
+ keep_nbest_models: 5
42
+ grad_clip: 1.0
43
+ grad_clip_type: 2.0
44
+ grad_noise: false
45
+ accum_grad: 1
46
+ no_forward_run: false
47
+ resume: true
48
+ train_dtype: float32
49
+ use_amp: false
50
+ log_interval: null
51
+ unused_parameters: false
52
+ use_tensorboard: true
53
+ use_wandb: false
54
+ wandb_project: null
55
+ wandb_id: null
56
+ pretrain_path: null
57
+ init_param: []
58
+ freeze_param: []
59
+ num_iters_per_epoch: 500
60
+ batch_size: 20
61
+ valid_batch_size: null
62
+ batch_bins: 18000000
63
+ valid_batch_bins: null
64
+ train_shape_file:
65
+ - exp/tts_train_gst+xvector_transformer_raw_phn_tacotron_g2p_en_no_space/decode_use_teacher_forcingtrue_train.loss.ave/stats/train/text_shape.phn
66
+ - exp/tts_train_gst+xvector_transformer_raw_phn_tacotron_g2p_en_no_space/decode_use_teacher_forcingtrue_train.loss.ave/stats/train/speech_shape
67
+ valid_shape_file:
68
+ - exp/tts_train_gst+xvector_transformer_raw_phn_tacotron_g2p_en_no_space/decode_use_teacher_forcingtrue_train.loss.ave/stats/valid/text_shape.phn
69
+ - exp/tts_train_gst+xvector_transformer_raw_phn_tacotron_g2p_en_no_space/decode_use_teacher_forcingtrue_train.loss.ave/stats/valid/speech_shape
70
+ batch_type: numel
71
+ valid_batch_type: null
72
+ fold_length:
73
+ - 150
74
+ - 240000
75
+ sort_in_batch: descending
76
+ sort_batch: descending
77
+ multiple_iterator: false
78
+ chunk_length: 500
79
+ chunk_shift_ratio: 0.5
80
+ num_cache_chunks: 1024
81
+ train_data_path_and_name_and_type:
82
+ - - dump/raw/tr_no_dev/text
83
+ - text
84
+ - text
85
+ - - exp/tts_train_gst+xvector_transformer_raw_phn_tacotron_g2p_en_no_space/decode_use_teacher_forcingtrue_train.loss.ave/tr_no_dev/durations
86
+ - durations
87
+ - text_int
88
+ - - dump/raw/tr_no_dev/wav.scp
89
+ - speech
90
+ - sound
91
+ - - exp/tts_train_gst+xvector_transformer_raw_phn_tacotron_g2p_en_no_space/decode_use_teacher_forcingtrue_train.loss.ave/stats/train/collect_feats/pitch.scp
92
+ - pitch
93
+ - npy
94
+ - - exp/tts_train_gst+xvector_transformer_raw_phn_tacotron_g2p_en_no_space/decode_use_teacher_forcingtrue_train.loss.ave/stats/train/collect_feats/energy.scp
95
+ - energy
96
+ - npy
97
+ - - dump/xvector/tr_no_dev/xvector.scp
98
+ - spembs
99
+ - kaldi_ark
100
+ valid_data_path_and_name_and_type:
101
+ - - dump/raw/dev/text
102
+ - text
103
+ - text
104
+ - - exp/tts_train_gst+xvector_transformer_raw_phn_tacotron_g2p_en_no_space/decode_use_teacher_forcingtrue_train.loss.ave/dev/durations
105
+ - durations
106
+ - text_int
107
+ - - dump/raw/dev/wav.scp
108
+ - speech
109
+ - sound
110
+ - - exp/tts_train_gst+xvector_transformer_raw_phn_tacotron_g2p_en_no_space/decode_use_teacher_forcingtrue_train.loss.ave/stats/valid/collect_feats/pitch.scp
111
+ - pitch
112
+ - npy
113
+ - - exp/tts_train_gst+xvector_transformer_raw_phn_tacotron_g2p_en_no_space/decode_use_teacher_forcingtrue_train.loss.ave/stats/valid/collect_feats/energy.scp
114
+ - energy
115
+ - npy
116
+ - - dump/xvector/dev/xvector.scp
117
+ - spembs
118
+ - kaldi_ark
119
+ allow_variable_data_keys: false
120
+ max_cache_size: 0.0
121
+ max_cache_fd: 32
122
+ valid_max_cache_size: null
123
+ optim: adam
124
+ optim_conf:
125
+ lr: 1.0
126
+ scheduler: noamlr
127
+ scheduler_conf:
128
+ model_size: 384
129
+ warmup_steps: 4000
130
+ token_list:
131
+ - <blank>
132
+ - <unk>
133
+ - AH0
134
+ - T
135
+ - N
136
+ - D
137
+ - S
138
+ - R
139
+ - L
140
+ - IH1
141
+ - DH
142
+ - M
143
+ - K
144
+ - Z
145
+ - EH1
146
+ - AE1
147
+ - IH0
148
+ - AH1
149
+ - W
150
+ - ','
151
+ - HH
152
+ - ER0
153
+ - P
154
+ - IY1
155
+ - V
156
+ - F
157
+ - B
158
+ - UW1
159
+ - AA1
160
+ - AY1
161
+ - AO1
162
+ - .
163
+ - EY1
164
+ - IY0
165
+ - OW1
166
+ - NG
167
+ - G
168
+ - SH
169
+ - Y
170
+ - AW1
171
+ - CH
172
+ - ER1
173
+ - UH1
174
+ - TH
175
+ - JH
176
+ - ''''
177
+ - '?'
178
+ - OW0
179
+ - EH2
180
+ - '!'
181
+ - IH2
182
+ - OY1
183
+ - EY2
184
+ - AY2
185
+ - EH0
186
+ - UW0
187
+ - AA2
188
+ - AE2
189
+ - OW2
190
+ - AO2
191
+ - AE0
192
+ - AH2
193
+ - ZH
194
+ - AA0
195
+ - UW2
196
+ - IY2
197
+ - AY0
198
+ - AO0
199
+ - AW2
200
+ - EY0
201
+ - UH2
202
+ - ER2
203
+ - AW0
204
+ - '...'
205
+ - UH0
206
+ - OY2
207
+ - . . .
208
+ - OY0
209
+ - . . . .
210
+ - ..
211
+ - . ...
212
+ - . .
213
+ - . . . . .
214
+ - .. ..
215
+ - '... .'
216
+ - <sos/eos>
217
+ odim: null
218
+ model_conf: {}
219
+ use_preprocessor: true
220
+ token_type: phn
221
+ bpemodel: null
222
+ non_linguistic_symbols: null
223
+ cleaner: tacotron
224
+ g2p: g2p_en_no_space
225
+ feats_extract: fbank
226
+ feats_extract_conf:
227
+ fs: 24000
228
+ fmin: 80
229
+ fmax: 7600
230
+ n_mels: 80
231
+ hop_length: 300
232
+ n_fft: 2048
233
+ win_length: 1200
234
+ normalize: global_mvn
235
+ normalize_conf:
236
+ stats_file: exp/tts_train_gst+xvector_transformer_raw_phn_tacotron_g2p_en_no_space/decode_use_teacher_forcingtrue_train.loss.ave/stats/train/feats_stats.npz
237
+ tts: fastspeech2
238
+ tts_conf:
239
+ adim: 384
240
+ aheads: 2
241
+ elayers: 4
242
+ eunits: 1536
243
+ dlayers: 4
244
+ dunits: 1536
245
+ positionwise_layer_type: conv1d
246
+ positionwise_conv_kernel_size: 3
247
+ duration_predictor_layers: 2
248
+ duration_predictor_chans: 256
249
+ duration_predictor_kernel_size: 3
250
+ postnet_layers: 5
251
+ postnet_filts: 5
252
+ postnet_chans: 256
253
+ use_masking: true
254
+ encoder_normalize_before: true
255
+ decoder_normalize_before: true
256
+ reduction_factor: 1
257
+ encoder_type: conformer
258
+ decoder_type: conformer
259
+ conformer_pos_enc_layer_type: rel_pos
260
+ conformer_self_attn_layer_type: rel_selfattn
261
+ conformer_activation_type: swish
262
+ use_macaron_style_in_conformer: true
263
+ use_cnn_in_conformer: true
264
+ conformer_enc_kernel_size: 7
265
+ conformer_dec_kernel_size: 31
266
+ init_type: xavier_uniform
267
+ transformer_enc_dropout_rate: 0.2
268
+ transformer_enc_positional_dropout_rate: 0.2
269
+ transformer_enc_attn_dropout_rate: 0.2
270
+ transformer_dec_dropout_rate: 0.2
271
+ transformer_dec_positional_dropout_rate: 0.2
272
+ transformer_dec_attn_dropout_rate: 0.2
273
+ pitch_predictor_layers: 5
274
+ pitch_predictor_chans: 256
275
+ pitch_predictor_kernel_size: 5
276
+ pitch_predictor_dropout: 0.5
277
+ pitch_embed_kernel_size: 1
278
+ pitch_embed_dropout: 0.0
279
+ stop_gradient_from_pitch_predictor: true
280
+ energy_predictor_layers: 2
281
+ energy_predictor_chans: 256
282
+ energy_predictor_kernel_size: 3
283
+ energy_predictor_dropout: 0.5
284
+ energy_embed_kernel_size: 1
285
+ energy_embed_dropout: 0.0
286
+ stop_gradient_from_energy_predictor: false
287
+ spk_embed_dim: 512
288
+ spk_embed_integration_type: add
289
+ use_gst: true
290
+ gst_heads: 4
291
+ gst_tokens: 16
292
+ pitch_extract: dio
293
+ pitch_extract_conf:
294
+ fs: 24000
295
+ n_fft: 2048
296
+ hop_length: 300
297
+ f0max: 400
298
+ f0min: 80
299
+ reduction_factor: 1
300
+ pitch_normalize: global_mvn
301
+ pitch_normalize_conf:
302
+ stats_file: exp/tts_train_gst+xvector_transformer_raw_phn_tacotron_g2p_en_no_space/decode_use_teacher_forcingtrue_train.loss.ave/stats/train/pitch_stats.npz
303
+ energy_extract: energy
304
+ energy_extract_conf:
305
+ fs: 24000
306
+ n_fft: 2048
307
+ hop_length: 300
308
+ win_length: 1200
309
+ reduction_factor: 1
310
+ energy_normalize: global_mvn
311
+ energy_normalize_conf:
312
+ stats_file: exp/tts_train_gst+xvector_transformer_raw_phn_tacotron_g2p_en_no_space/decode_use_teacher_forcingtrue_train.loss.ave/stats/train/energy_stats.npz
313
+ required:
314
+ - output_dir
315
+ - token_list
316
+ distributed: true
exp/tts_train_gst+xvector_conformer_fastspeech2_transformer_teacher_raw_phn_tacotron_g2p_en_no_space/images/backward_time.png ADDED
exp/tts_train_gst+xvector_conformer_fastspeech2_transformer_teacher_raw_phn_tacotron_g2p_en_no_space/images/duration_loss.png ADDED
exp/tts_train_gst+xvector_conformer_fastspeech2_transformer_teacher_raw_phn_tacotron_g2p_en_no_space/images/energy_loss.png ADDED
exp/tts_train_gst+xvector_conformer_fastspeech2_transformer_teacher_raw_phn_tacotron_g2p_en_no_space/images/forward_time.png ADDED
exp/tts_train_gst+xvector_conformer_fastspeech2_transformer_teacher_raw_phn_tacotron_g2p_en_no_space/images/iter_time.png ADDED
exp/tts_train_gst+xvector_conformer_fastspeech2_transformer_teacher_raw_phn_tacotron_g2p_en_no_space/images/l1_loss.png ADDED
exp/tts_train_gst+xvector_conformer_fastspeech2_transformer_teacher_raw_phn_tacotron_g2p_en_no_space/images/loss.png ADDED
exp/tts_train_gst+xvector_conformer_fastspeech2_transformer_teacher_raw_phn_tacotron_g2p_en_no_space/images/lr_0.png ADDED
exp/tts_train_gst+xvector_conformer_fastspeech2_transformer_teacher_raw_phn_tacotron_g2p_en_no_space/images/optim_step_time.png ADDED
exp/tts_train_gst+xvector_conformer_fastspeech2_transformer_teacher_raw_phn_tacotron_g2p_en_no_space/images/pitch_loss.png ADDED
exp/tts_train_gst+xvector_conformer_fastspeech2_transformer_teacher_raw_phn_tacotron_g2p_en_no_space/images/train_time.png ADDED
exp/tts_train_gst+xvector_conformer_fastspeech2_transformer_teacher_raw_phn_tacotron_g2p_en_no_space/train.loss.ave_5best.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3183a5e0bf35aef8e6e1d7020036e0c17b89ecb3c80ad5e2956257e0f002cd3b
3
+ size 285154860
exp/tts_train_gst+xvector_transformer_raw_phn_tacotron_g2p_en_no_space/decode_use_teacher_forcingtrue_train.loss.ave/stats/train/energy_stats.npz ADDED
Binary file (770 Bytes). View file
 
exp/tts_train_gst+xvector_transformer_raw_phn_tacotron_g2p_en_no_space/decode_use_teacher_forcingtrue_train.loss.ave/stats/train/feats_stats.npz ADDED
Binary file (1.4 kB). View file
 
exp/tts_train_gst+xvector_transformer_raw_phn_tacotron_g2p_en_no_space/decode_use_teacher_forcingtrue_train.loss.ave/stats/train/pitch_stats.npz ADDED
Binary file (770 Bytes). View file
 
meta.yaml ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ espnet: 0.8.0
2
+ files:
3
+ model_file: exp/tts_train_gst+xvector_conformer_fastspeech2_transformer_teacher_raw_phn_tacotron_g2p_en_no_space/train.loss.ave_5best.pth
4
+ python: "3.7.3 (default, Mar 27 2019, 22:11:17) \n[GCC 7.3.0]"
5
+ timestamp: 1609825010.451726
6
+ torch: 1.5.1
7
+ yaml_files:
8
+ train_config: exp/tts_train_gst+xvector_conformer_fastspeech2_transformer_teacher_raw_phn_tacotron_g2p_en_no_space/config.yaml