Siddhant commited on
Commit
6f358a9
1 Parent(s): 6f024b0

import from zenodo

Browse files
Files changed (26) hide show
  1. README.md +50 -0
  2. exp/tts_train_full_band_vits_raw_phn_jaconv_pyopenjtalk_prosody/config.yaml +356 -0
  3. exp/tts_train_full_band_vits_raw_phn_jaconv_pyopenjtalk_prosody/images/discriminator_backward_time.png +0 -0
  4. exp/tts_train_full_band_vits_raw_phn_jaconv_pyopenjtalk_prosody/images/discriminator_fake_loss.png +0 -0
  5. exp/tts_train_full_band_vits_raw_phn_jaconv_pyopenjtalk_prosody/images/discriminator_forward_time.png +0 -0
  6. exp/tts_train_full_band_vits_raw_phn_jaconv_pyopenjtalk_prosody/images/discriminator_loss.png +0 -0
  7. exp/tts_train_full_band_vits_raw_phn_jaconv_pyopenjtalk_prosody/images/discriminator_optim_step_time.png +0 -0
  8. exp/tts_train_full_band_vits_raw_phn_jaconv_pyopenjtalk_prosody/images/discriminator_real_loss.png +0 -0
  9. exp/tts_train_full_band_vits_raw_phn_jaconv_pyopenjtalk_prosody/images/discriminator_train_time.png +0 -0
  10. exp/tts_train_full_band_vits_raw_phn_jaconv_pyopenjtalk_prosody/images/generator_adv_loss.png +0 -0
  11. exp/tts_train_full_band_vits_raw_phn_jaconv_pyopenjtalk_prosody/images/generator_backward_time.png +0 -0
  12. exp/tts_train_full_band_vits_raw_phn_jaconv_pyopenjtalk_prosody/images/generator_dur_loss.png +0 -0
  13. exp/tts_train_full_band_vits_raw_phn_jaconv_pyopenjtalk_prosody/images/generator_feat_match_loss.png +0 -0
  14. exp/tts_train_full_band_vits_raw_phn_jaconv_pyopenjtalk_prosody/images/generator_forward_time.png +0 -0
  15. exp/tts_train_full_band_vits_raw_phn_jaconv_pyopenjtalk_prosody/images/generator_kl_loss.png +0 -0
  16. exp/tts_train_full_band_vits_raw_phn_jaconv_pyopenjtalk_prosody/images/generator_loss.png +0 -0
  17. exp/tts_train_full_band_vits_raw_phn_jaconv_pyopenjtalk_prosody/images/generator_mel_loss.png +0 -0
  18. exp/tts_train_full_band_vits_raw_phn_jaconv_pyopenjtalk_prosody/images/generator_optim_step_time.png +0 -0
  19. exp/tts_train_full_band_vits_raw_phn_jaconv_pyopenjtalk_prosody/images/generator_train_time.png +0 -0
  20. exp/tts_train_full_band_vits_raw_phn_jaconv_pyopenjtalk_prosody/images/gpu_max_cached_mem_GB.png +0 -0
  21. exp/tts_train_full_band_vits_raw_phn_jaconv_pyopenjtalk_prosody/images/iter_time.png +0 -0
  22. exp/tts_train_full_band_vits_raw_phn_jaconv_pyopenjtalk_prosody/images/optim0_lr0.png +0 -0
  23. exp/tts_train_full_band_vits_raw_phn_jaconv_pyopenjtalk_prosody/images/optim1_lr0.png +0 -0
  24. exp/tts_train_full_band_vits_raw_phn_jaconv_pyopenjtalk_prosody/images/train_time.png +0 -0
  25. exp/tts_train_full_band_vits_raw_phn_jaconv_pyopenjtalk_prosody/train.total_count.ave_10best.pth +3 -0
  26. meta.yaml +8 -0
README.md ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - espnet
4
+ - audio
5
+ - text-to-speech
6
+ language: ja
7
+ datasets:
8
+ - jsut
9
+ license: cc-by-4.0
10
+ ---
11
+ ## ESPnet2 TTS pretrained model
12
+ ### `kan-bayashi/jsut_full_band_vits_prosody`
13
+ ♻️ Imported from https://zenodo.org/record/5521340/
14
+
15
+ This model was trained by kan-bayashi using jsut/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
+ ```
exp/tts_train_full_band_vits_raw_phn_jaconv_pyopenjtalk_prosody/config.yaml ADDED
@@ -0,0 +1,356 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ config: ./conf/tuning/train_full_band_vits.yaml
2
+ print_config: false
3
+ log_level: INFO
4
+ dry_run: false
5
+ iterator_type: sequence
6
+ output_dir: exp/tts_train_full_band_vits_raw_phn_jaconv_pyopenjtalk_prosody
7
+ ngpu: 1
8
+ seed: 777
9
+ num_workers: 4
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: 40363
18
+ dist_launcher: null
19
+ multiprocessing_distributed: true
20
+ unused_parameters: true
21
+ sharded_ddp: false
22
+ cudnn_enabled: true
23
+ cudnn_benchmark: false
24
+ cudnn_deterministic: false
25
+ collect_stats: false
26
+ write_collected_feats: false
27
+ max_epoch: 2000
28
+ patience: null
29
+ val_scheduler_criterion:
30
+ - valid
31
+ - loss
32
+ early_stopping_criterion:
33
+ - valid
34
+ - loss
35
+ - min
36
+ best_model_criterion:
37
+ - - train
38
+ - total_count
39
+ - max
40
+ keep_nbest_models: 10
41
+ grad_clip: -1
42
+ grad_clip_type: 2.0
43
+ grad_noise: false
44
+ accum_grad: 1
45
+ no_forward_run: false
46
+ resume: true
47
+ train_dtype: float32
48
+ use_amp: false
49
+ log_interval: 50
50
+ use_tensorboard: true
51
+ use_wandb: false
52
+ wandb_project: null
53
+ wandb_id: null
54
+ wandb_entity: null
55
+ wandb_name: null
56
+ wandb_model_log_interval: -1
57
+ detect_anomaly: false
58
+ pretrain_path: null
59
+ init_param: []
60
+ ignore_init_mismatch: false
61
+ freeze_param: []
62
+ num_iters_per_epoch: 500
63
+ batch_size: 20
64
+ valid_batch_size: null
65
+ batch_bins: 7000000
66
+ valid_batch_bins: null
67
+ train_shape_file:
68
+ - exp/tts_stats_raw_linear_spectrogram_44.1khz_phn_jaconv_pyopenjtalk_prosody/train/text_shape.phn
69
+ - exp/tts_stats_raw_linear_spectrogram_44.1khz_phn_jaconv_pyopenjtalk_prosody/train/speech_shape
70
+ valid_shape_file:
71
+ - exp/tts_stats_raw_linear_spectrogram_44.1khz_phn_jaconv_pyopenjtalk_prosody/valid/text_shape.phn
72
+ - exp/tts_stats_raw_linear_spectrogram_44.1khz_phn_jaconv_pyopenjtalk_prosody/valid/speech_shape
73
+ batch_type: numel
74
+ valid_batch_type: null
75
+ fold_length:
76
+ - 150
77
+ - 409600
78
+ sort_in_batch: descending
79
+ sort_batch: descending
80
+ multiple_iterator: false
81
+ chunk_length: 500
82
+ chunk_shift_ratio: 0.5
83
+ num_cache_chunks: 1024
84
+ train_data_path_and_name_and_type:
85
+ - - dump/44.1k/raw/tr_no_dev/text
86
+ - text
87
+ - text
88
+ - - dump/44.1k/raw/tr_no_dev/wav.scp
89
+ - speech
90
+ - sound
91
+ valid_data_path_and_name_and_type:
92
+ - - dump/44.1k/raw/dev/text
93
+ - text
94
+ - text
95
+ - - dump/44.1k/raw/dev/wav.scp
96
+ - speech
97
+ - sound
98
+ allow_variable_data_keys: false
99
+ max_cache_size: 0.0
100
+ max_cache_fd: 32
101
+ valid_max_cache_size: null
102
+ optim: adamw
103
+ optim_conf:
104
+ lr: 0.0002
105
+ betas:
106
+ - 0.8
107
+ - 0.99
108
+ eps: 1.0e-09
109
+ weight_decay: 0.0
110
+ scheduler: exponentiallr
111
+ scheduler_conf:
112
+ gamma: 0.999875
113
+ optim2: adamw
114
+ optim2_conf:
115
+ lr: 0.0002
116
+ betas:
117
+ - 0.8
118
+ - 0.99
119
+ eps: 1.0e-09
120
+ weight_decay: 0.0
121
+ scheduler2: exponentiallr
122
+ scheduler2_conf:
123
+ gamma: 0.999875
124
+ generator_first: false
125
+ token_list:
126
+ - <blank>
127
+ - <unk>
128
+ - a
129
+ - o
130
+ - i
131
+ - '['
132
+ - '#'
133
+ - u
134
+ - ']'
135
+ - e
136
+ - k
137
+ - n
138
+ - t
139
+ - r
140
+ - s
141
+ - N
142
+ - m
143
+ - _
144
+ - sh
145
+ - d
146
+ - g
147
+ - ^
148
+ - $
149
+ - w
150
+ - cl
151
+ - h
152
+ - y
153
+ - b
154
+ - j
155
+ - ts
156
+ - ch
157
+ - z
158
+ - p
159
+ - f
160
+ - ky
161
+ - ry
162
+ - gy
163
+ - hy
164
+ - ny
165
+ - by
166
+ - my
167
+ - py
168
+ - v
169
+ - dy
170
+ - '?'
171
+ - ty
172
+ - <sos/eos>
173
+ odim: null
174
+ model_conf: {}
175
+ use_preprocessor: true
176
+ token_type: phn
177
+ bpemodel: null
178
+ non_linguistic_symbols: null
179
+ cleaner: jaconv
180
+ g2p: pyopenjtalk_prosody
181
+ feats_extract: linear_spectrogram
182
+ feats_extract_conf:
183
+ n_fft: 2048
184
+ hop_length: 512
185
+ win_length: null
186
+ normalize: null
187
+ normalize_conf: {}
188
+ tts: vits
189
+ tts_conf:
190
+ generator_type: vits_generator
191
+ generator_params:
192
+ hidden_channels: 192
193
+ spks: -1
194
+ global_channels: -1
195
+ segment_size: 32
196
+ text_encoder_attention_heads: 2
197
+ text_encoder_ffn_expand: 4
198
+ text_encoder_blocks: 6
199
+ text_encoder_positionwise_layer_type: conv1d
200
+ text_encoder_positionwise_conv_kernel_size: 3
201
+ text_encoder_positional_encoding_layer_type: rel_pos
202
+ text_encoder_self_attention_layer_type: rel_selfattn
203
+ text_encoder_activation_type: swish
204
+ text_encoder_normalize_before: true
205
+ text_encoder_dropout_rate: 0.1
206
+ text_encoder_positional_dropout_rate: 0.0
207
+ text_encoder_attention_dropout_rate: 0.1
208
+ use_macaron_style_in_text_encoder: true
209
+ use_conformer_conv_in_text_encoder: false
210
+ text_encoder_conformer_kernel_size: -1
211
+ decoder_kernel_size: 7
212
+ decoder_channels: 512
213
+ decoder_upsample_scales:
214
+ - 8
215
+ - 8
216
+ - 2
217
+ - 2
218
+ - 2
219
+ decoder_upsample_kernel_sizes:
220
+ - 16
221
+ - 16
222
+ - 4
223
+ - 4
224
+ - 4
225
+ decoder_resblock_kernel_sizes:
226
+ - 3
227
+ - 7
228
+ - 11
229
+ decoder_resblock_dilations:
230
+ - - 1
231
+ - 3
232
+ - 5
233
+ - - 1
234
+ - 3
235
+ - 5
236
+ - - 1
237
+ - 3
238
+ - 5
239
+ use_weight_norm_in_decoder: true
240
+ posterior_encoder_kernel_size: 5
241
+ posterior_encoder_layers: 16
242
+ posterior_encoder_stacks: 1
243
+ posterior_encoder_base_dilation: 1
244
+ posterior_encoder_dropout_rate: 0.0
245
+ use_weight_norm_in_posterior_encoder: true
246
+ flow_flows: 4
247
+ flow_kernel_size: 5
248
+ flow_base_dilation: 1
249
+ flow_layers: 4
250
+ flow_dropout_rate: 0.0
251
+ use_weight_norm_in_flow: true
252
+ use_only_mean_in_flow: true
253
+ stochastic_duration_predictor_kernel_size: 3
254
+ stochastic_duration_predictor_dropout_rate: 0.5
255
+ stochastic_duration_predictor_flows: 4
256
+ stochastic_duration_predictor_dds_conv_layers: 3
257
+ vocabs: 47
258
+ aux_channels: 1025
259
+ discriminator_type: hifigan_multi_scale_multi_period_discriminator
260
+ discriminator_params:
261
+ scales: 1
262
+ scale_downsample_pooling: AvgPool1d
263
+ scale_downsample_pooling_params:
264
+ kernel_size: 4
265
+ stride: 2
266
+ padding: 2
267
+ scale_discriminator_params:
268
+ in_channels: 1
269
+ out_channels: 1
270
+ kernel_sizes:
271
+ - 15
272
+ - 41
273
+ - 5
274
+ - 3
275
+ channels: 128
276
+ max_downsample_channels: 1024
277
+ max_groups: 16
278
+ bias: true
279
+ downsample_scales:
280
+ - 2
281
+ - 2
282
+ - 4
283
+ - 4
284
+ - 1
285
+ nonlinear_activation: LeakyReLU
286
+ nonlinear_activation_params:
287
+ negative_slope: 0.1
288
+ use_weight_norm: true
289
+ use_spectral_norm: false
290
+ follow_official_norm: false
291
+ periods:
292
+ - 2
293
+ - 3
294
+ - 5
295
+ - 7
296
+ - 11
297
+ period_discriminator_params:
298
+ in_channels: 1
299
+ out_channels: 1
300
+ kernel_sizes:
301
+ - 5
302
+ - 3
303
+ channels: 32
304
+ downsample_scales:
305
+ - 3
306
+ - 3
307
+ - 3
308
+ - 3
309
+ - 1
310
+ max_downsample_channels: 1024
311
+ bias: true
312
+ nonlinear_activation: LeakyReLU
313
+ nonlinear_activation_params:
314
+ negative_slope: 0.1
315
+ use_weight_norm: true
316
+ use_spectral_norm: false
317
+ generator_adv_loss_params:
318
+ average_by_discriminators: false
319
+ loss_type: mse
320
+ discriminator_adv_loss_params:
321
+ average_by_discriminators: false
322
+ loss_type: mse
323
+ feat_match_loss_params:
324
+ average_by_discriminators: false
325
+ average_by_layers: false
326
+ include_final_outputs: true
327
+ mel_loss_params:
328
+ fs: 44100
329
+ n_fft: 2048
330
+ hop_length: 512
331
+ win_length: null
332
+ window: hann
333
+ n_mels: 80
334
+ fmin: 0
335
+ fmax: null
336
+ log_base: null
337
+ lambda_adv: 1.0
338
+ lambda_mel: 45.0
339
+ lambda_feat_match: 2.0
340
+ lambda_dur: 1.0
341
+ lambda_kl: 1.0
342
+ sampling_rate: 44100
343
+ cache_generator_outputs: true
344
+ pitch_extract: null
345
+ pitch_extract_conf: {}
346
+ pitch_normalize: null
347
+ pitch_normalize_conf: {}
348
+ energy_extract: null
349
+ energy_extract_conf: {}
350
+ energy_normalize: null
351
+ energy_normalize_conf: {}
352
+ required:
353
+ - output_dir
354
+ - token_list
355
+ version: 0.10.3a2
356
+ distributed: true
exp/tts_train_full_band_vits_raw_phn_jaconv_pyopenjtalk_prosody/images/discriminator_backward_time.png ADDED
Binary file (30 kB). View file
exp/tts_train_full_band_vits_raw_phn_jaconv_pyopenjtalk_prosody/images/discriminator_fake_loss.png ADDED
Binary file (56.7 kB). View file
exp/tts_train_full_band_vits_raw_phn_jaconv_pyopenjtalk_prosody/images/discriminator_forward_time.png ADDED
Binary file (30.8 kB). View file
exp/tts_train_full_band_vits_raw_phn_jaconv_pyopenjtalk_prosody/images/discriminator_loss.png ADDED
Binary file (51.2 kB). View file
exp/tts_train_full_band_vits_raw_phn_jaconv_pyopenjtalk_prosody/images/discriminator_optim_step_time.png ADDED
Binary file (69.4 kB). View file
exp/tts_train_full_band_vits_raw_phn_jaconv_pyopenjtalk_prosody/images/discriminator_real_loss.png ADDED
Binary file (64.1 kB). View file
exp/tts_train_full_band_vits_raw_phn_jaconv_pyopenjtalk_prosody/images/discriminator_train_time.png ADDED
Binary file (27.5 kB). View file
exp/tts_train_full_band_vits_raw_phn_jaconv_pyopenjtalk_prosody/images/generator_adv_loss.png ADDED
Binary file (54.3 kB). View file
exp/tts_train_full_band_vits_raw_phn_jaconv_pyopenjtalk_prosody/images/generator_backward_time.png ADDED
Binary file (28.7 kB). View file
exp/tts_train_full_band_vits_raw_phn_jaconv_pyopenjtalk_prosody/images/generator_dur_loss.png ADDED
Binary file (44.6 kB). View file
exp/tts_train_full_band_vits_raw_phn_jaconv_pyopenjtalk_prosody/images/generator_feat_match_loss.png ADDED
Binary file (40.2 kB). View file
exp/tts_train_full_band_vits_raw_phn_jaconv_pyopenjtalk_prosody/images/generator_forward_time.png ADDED
Binary file (45.1 kB). View file
exp/tts_train_full_band_vits_raw_phn_jaconv_pyopenjtalk_prosody/images/generator_kl_loss.png ADDED
Binary file (25.4 kB). View file
exp/tts_train_full_band_vits_raw_phn_jaconv_pyopenjtalk_prosody/images/generator_loss.png ADDED
Binary file (30.4 kB). View file
exp/tts_train_full_band_vits_raw_phn_jaconv_pyopenjtalk_prosody/images/generator_mel_loss.png ADDED
Binary file (32.8 kB). View file
exp/tts_train_full_band_vits_raw_phn_jaconv_pyopenjtalk_prosody/images/generator_optim_step_time.png ADDED
Binary file (65.8 kB). View file
exp/tts_train_full_band_vits_raw_phn_jaconv_pyopenjtalk_prosody/images/generator_train_time.png ADDED
Binary file (29.8 kB). View file
exp/tts_train_full_band_vits_raw_phn_jaconv_pyopenjtalk_prosody/images/gpu_max_cached_mem_GB.png ADDED
Binary file (29 kB). View file
exp/tts_train_full_band_vits_raw_phn_jaconv_pyopenjtalk_prosody/images/iter_time.png ADDED
Binary file (29 kB). View file
exp/tts_train_full_band_vits_raw_phn_jaconv_pyopenjtalk_prosody/images/optim0_lr0.png ADDED
Binary file (25.2 kB). View file
exp/tts_train_full_band_vits_raw_phn_jaconv_pyopenjtalk_prosody/images/optim1_lr0.png ADDED
Binary file (25 kB). View file
exp/tts_train_full_band_vits_raw_phn_jaconv_pyopenjtalk_prosody/images/train_time.png ADDED
Binary file (29 kB). View file
exp/tts_train_full_band_vits_raw_phn_jaconv_pyopenjtalk_prosody/train.total_count.ave_10best.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8cfd4d7324826303845bbac274b071b40e2379da996fc46ad2489585ea8d4bf
3
+ size 373255824
meta.yaml ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
1
+ espnet: 0.10.3a2
2
+ files:
3
+ model_file: exp/tts_train_full_band_vits_raw_phn_jaconv_pyopenjtalk_prosody/train.total_count.ave_10best.pth
4
+ python: "3.7.3 (default, Mar 27 2019, 22:11:17) \n[GCC 7.3.0]"
5
+ timestamp: 1632316679.464766
6
+ torch: 1.7.1
7
+ yaml_files:
8
+ train_config: exp/tts_train_full_band_vits_raw_phn_jaconv_pyopenjtalk_prosody/config.yaml