import from zenodo
Browse files- README.md +50 -0
- exp/tts_train_conformer_fastspeech2_raw_phn_tacotron_g2p_en_no_space/config.yaml +288 -0
- exp/tts_train_conformer_fastspeech2_raw_phn_tacotron_g2p_en_no_space/images/backward_time.png +0 -0
- exp/tts_train_conformer_fastspeech2_raw_phn_tacotron_g2p_en_no_space/images/duration_loss.png +0 -0
- exp/tts_train_conformer_fastspeech2_raw_phn_tacotron_g2p_en_no_space/images/energy_loss.png +0 -0
- exp/tts_train_conformer_fastspeech2_raw_phn_tacotron_g2p_en_no_space/images/forward_time.png +0 -0
- exp/tts_train_conformer_fastspeech2_raw_phn_tacotron_g2p_en_no_space/images/iter_time.png +0 -0
- exp/tts_train_conformer_fastspeech2_raw_phn_tacotron_g2p_en_no_space/images/l1_loss.png +0 -0
- exp/tts_train_conformer_fastspeech2_raw_phn_tacotron_g2p_en_no_space/images/loss.png +0 -0
- exp/tts_train_conformer_fastspeech2_raw_phn_tacotron_g2p_en_no_space/images/lr_0.png +0 -0
- exp/tts_train_conformer_fastspeech2_raw_phn_tacotron_g2p_en_no_space/images/optim_step_time.png +0 -0
- exp/tts_train_conformer_fastspeech2_raw_phn_tacotron_g2p_en_no_space/images/pitch_loss.png +0 -0
- exp/tts_train_conformer_fastspeech2_raw_phn_tacotron_g2p_en_no_space/images/train_time.png +0 -0
- exp/tts_train_conformer_fastspeech2_raw_phn_tacotron_g2p_en_no_space/train.loss.ave_5best.pth +3 -0
- exp/tts_train_tacotron2_raw_phn_tacotron_g2p_en_no_space/decode_tacotron2_teacher_forcing_train.loss.best/stats/train/energy_stats.npz +0 -0
- exp/tts_train_tacotron2_raw_phn_tacotron_g2p_en_no_space/decode_tacotron2_teacher_forcing_train.loss.best/stats/train/feats_stats.npz +0 -0
- exp/tts_train_tacotron2_raw_phn_tacotron_g2p_en_no_space/decode_tacotron2_teacher_forcing_train.loss.best/stats/train/pitch_stats.npz +0 -0
- 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 |
+
- ljspeech
|
9 |
+
license: cc-by-4.0
|
10 |
+
---
|
11 |
+
## Example ESPnet2 TTS model
|
12 |
+
### `kan-bayashi/ljspeech_tts_train_conformer_fastspeech2_raw_phn_tacotron_g2p_en_no_space_train.loss.ave`
|
13 |
+
♻️ Imported from https://zenodo.org/record/4036268/
|
14 |
+
|
15 |
+
This model was trained by kan-bayashi using ljspeech/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_conformer_fastspeech2_raw_phn_tacotron_g2p_en_no_space/config.yaml
ADDED
@@ -0,0 +1,288 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
config: conf/tuning/train_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_conformer_fastspeech2_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: null
|
14 |
+
dist_rank: null
|
15 |
+
local_rank: 0
|
16 |
+
dist_master_addr: null
|
17 |
+
dist_master_port: null
|
18 |
+
dist_launcher: null
|
19 |
+
multiprocessing_distributed: false
|
20 |
+
cudnn_enabled: true
|
21 |
+
cudnn_benchmark: false
|
22 |
+
cudnn_deterministic: true
|
23 |
+
collect_stats: false
|
24 |
+
write_collected_feats: false
|
25 |
+
max_epoch: 1000
|
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: 10
|
46 |
+
no_forward_run: false
|
47 |
+
resume: true
|
48 |
+
train_dtype: float32
|
49 |
+
use_amp: false
|
50 |
+
log_interval: null
|
51 |
+
pretrain_path: []
|
52 |
+
pretrain_key: []
|
53 |
+
num_iters_per_epoch: 500
|
54 |
+
batch_size: 20
|
55 |
+
valid_batch_size: null
|
56 |
+
batch_bins: 2400000
|
57 |
+
valid_batch_bins: null
|
58 |
+
train_shape_file:
|
59 |
+
- exp/tts_train_tacotron2_raw_phn_tacotron_g2p_en_no_space/decode_tacotron2_teacher_forcing_train.loss.best/stats/train/text_shape.phn
|
60 |
+
- exp/tts_train_tacotron2_raw_phn_tacotron_g2p_en_no_space/decode_tacotron2_teacher_forcing_train.loss.best/stats/train/speech_shape
|
61 |
+
valid_shape_file:
|
62 |
+
- exp/tts_train_tacotron2_raw_phn_tacotron_g2p_en_no_space/decode_tacotron2_teacher_forcing_train.loss.best/stats/valid/text_shape.phn
|
63 |
+
- exp/tts_train_tacotron2_raw_phn_tacotron_g2p_en_no_space/decode_tacotron2_teacher_forcing_train.loss.best/stats/valid/speech_shape
|
64 |
+
batch_type: numel
|
65 |
+
valid_batch_type: null
|
66 |
+
fold_length:
|
67 |
+
- 150
|
68 |
+
- 204800
|
69 |
+
sort_in_batch: descending
|
70 |
+
sort_batch: descending
|
71 |
+
multiple_iterator: false
|
72 |
+
chunk_length: 500
|
73 |
+
chunk_shift_ratio: 0.5
|
74 |
+
num_cache_chunks: 1024
|
75 |
+
train_data_path_and_name_and_type:
|
76 |
+
- - dump/raw/tr_no_dev/text
|
77 |
+
- text
|
78 |
+
- text
|
79 |
+
- - exp/tts_train_tacotron2_raw_phn_tacotron_g2p_en_no_space/decode_tacotron2_teacher_forcing_train.loss.best/tr_no_dev/durations
|
80 |
+
- durations
|
81 |
+
- text_int
|
82 |
+
- - dump/raw/tr_no_dev/wav.scp
|
83 |
+
- speech
|
84 |
+
- sound
|
85 |
+
- - exp/tts_train_tacotron2_raw_phn_tacotron_g2p_en_no_space/decode_tacotron2_teacher_forcing_train.loss.best/stats/train/collect_feats/pitch.scp
|
86 |
+
- pitch
|
87 |
+
- npy
|
88 |
+
- - exp/tts_train_tacotron2_raw_phn_tacotron_g2p_en_no_space/decode_tacotron2_teacher_forcing_train.loss.best/stats/train/collect_feats/energy.scp
|
89 |
+
- energy
|
90 |
+
- npy
|
91 |
+
valid_data_path_and_name_and_type:
|
92 |
+
- - dump/raw/dev/text
|
93 |
+
- text
|
94 |
+
- text
|
95 |
+
- - exp/tts_train_tacotron2_raw_phn_tacotron_g2p_en_no_space/decode_tacotron2_teacher_forcing_train.loss.best/dev/durations
|
96 |
+
- durations
|
97 |
+
- text_int
|
98 |
+
- - dump/raw/dev/wav.scp
|
99 |
+
- speech
|
100 |
+
- sound
|
101 |
+
- - exp/tts_train_tacotron2_raw_phn_tacotron_g2p_en_no_space/decode_tacotron2_teacher_forcing_train.loss.best/stats/valid/collect_feats/pitch.scp
|
102 |
+
- pitch
|
103 |
+
- npy
|
104 |
+
- - exp/tts_train_tacotron2_raw_phn_tacotron_g2p_en_no_space/decode_tacotron2_teacher_forcing_train.loss.best/stats/valid/collect_feats/energy.scp
|
105 |
+
- energy
|
106 |
+
- npy
|
107 |
+
allow_variable_data_keys: false
|
108 |
+
max_cache_size: 0.0
|
109 |
+
valid_max_cache_size: null
|
110 |
+
optim: adam
|
111 |
+
optim_conf:
|
112 |
+
lr: 1.0
|
113 |
+
scheduler: noamlr
|
114 |
+
scheduler_conf:
|
115 |
+
model_size: 384
|
116 |
+
warmup_steps: 4000
|
117 |
+
token_list:
|
118 |
+
- <blank>
|
119 |
+
- <unk>
|
120 |
+
- ..
|
121 |
+
- OY0
|
122 |
+
- UH0
|
123 |
+
- AW0
|
124 |
+
- '!'
|
125 |
+
- OY2
|
126 |
+
- '?'
|
127 |
+
- UH2
|
128 |
+
- ER2
|
129 |
+
- ''''
|
130 |
+
- AA0
|
131 |
+
- IY2
|
132 |
+
- AW2
|
133 |
+
- AY0
|
134 |
+
- AH2
|
135 |
+
- UW2
|
136 |
+
- AE0
|
137 |
+
- OW2
|
138 |
+
- ZH
|
139 |
+
- AO2
|
140 |
+
- EY0
|
141 |
+
- OY1
|
142 |
+
- EH0
|
143 |
+
- UW0
|
144 |
+
- AA2
|
145 |
+
- AY2
|
146 |
+
- AE2
|
147 |
+
- IH2
|
148 |
+
- AO0
|
149 |
+
- EY2
|
150 |
+
- OW0
|
151 |
+
- EH2
|
152 |
+
- UH1
|
153 |
+
- TH
|
154 |
+
- AW1
|
155 |
+
- Y
|
156 |
+
- JH
|
157 |
+
- CH
|
158 |
+
- ER1
|
159 |
+
- G
|
160 |
+
- NG
|
161 |
+
- SH
|
162 |
+
- OW1
|
163 |
+
- .
|
164 |
+
- AY1
|
165 |
+
- EY1
|
166 |
+
- AO1
|
167 |
+
- IY0
|
168 |
+
- UW1
|
169 |
+
- IY1
|
170 |
+
- HH
|
171 |
+
- B
|
172 |
+
- AA1
|
173 |
+
- ','
|
174 |
+
- F
|
175 |
+
- ER0
|
176 |
+
- V
|
177 |
+
- AH1
|
178 |
+
- AE1
|
179 |
+
- P
|
180 |
+
- W
|
181 |
+
- EH1
|
182 |
+
- M
|
183 |
+
- IH0
|
184 |
+
- IH1
|
185 |
+
- Z
|
186 |
+
- K
|
187 |
+
- DH
|
188 |
+
- L
|
189 |
+
- R
|
190 |
+
- S
|
191 |
+
- D
|
192 |
+
- T
|
193 |
+
- N
|
194 |
+
- AH0
|
195 |
+
- <sos/eos>
|
196 |
+
odim: null
|
197 |
+
model_conf: {}
|
198 |
+
use_preprocessor: true
|
199 |
+
token_type: phn
|
200 |
+
bpemodel: null
|
201 |
+
non_linguistic_symbols: null
|
202 |
+
cleaner: tacotron
|
203 |
+
g2p: g2p_en_no_space
|
204 |
+
feats_extract: fbank
|
205 |
+
feats_extract_conf:
|
206 |
+
fs: 22050
|
207 |
+
fmin: 80
|
208 |
+
fmax: 7600
|
209 |
+
n_mels: 80
|
210 |
+
hop_length: 256
|
211 |
+
n_fft: 1024
|
212 |
+
win_length: null
|
213 |
+
normalize: global_mvn
|
214 |
+
normalize_conf:
|
215 |
+
stats_file: exp/tts_train_tacotron2_raw_phn_tacotron_g2p_en_no_space/decode_tacotron2_teacher_forcing_train.loss.best/stats/train/feats_stats.npz
|
216 |
+
tts: fastspeech2
|
217 |
+
tts_conf:
|
218 |
+
adim: 384
|
219 |
+
aheads: 2
|
220 |
+
elayers: 4
|
221 |
+
eunits: 1536
|
222 |
+
dlayers: 4
|
223 |
+
dunits: 1536
|
224 |
+
positionwise_layer_type: conv1d
|
225 |
+
positionwise_conv_kernel_size: 3
|
226 |
+
duration_predictor_layers: 2
|
227 |
+
duration_predictor_chans: 256
|
228 |
+
duration_predictor_kernel_size: 3
|
229 |
+
postnet_layers: 5
|
230 |
+
postnet_filts: 5
|
231 |
+
postnet_chans: 256
|
232 |
+
use_masking: true
|
233 |
+
encoder_normalize_before: false
|
234 |
+
decoder_normalize_before: false
|
235 |
+
reduction_factor: 1
|
236 |
+
encoder_type: conformer
|
237 |
+
decoder_type: conformer
|
238 |
+
conformer_pos_enc_layer_type: rel_pos
|
239 |
+
conformer_self_attn_layer_type: rel_selfattn
|
240 |
+
conformer_activation_type: swish
|
241 |
+
use_macaron_style_in_conformer: true
|
242 |
+
use_cnn_in_conformer: true
|
243 |
+
conformer_enc_kernel_size: 7
|
244 |
+
conformer_dec_kernel_size: 31
|
245 |
+
init_type: xavier_uniform
|
246 |
+
transformer_enc_dropout_rate: 0.2
|
247 |
+
transformer_enc_positional_dropout_rate: 0.2
|
248 |
+
transformer_enc_attn_dropout_rate: 0.2
|
249 |
+
transformer_dec_dropout_rate: 0.2
|
250 |
+
transformer_dec_positional_dropout_rate: 0.2
|
251 |
+
transformer_dec_attn_dropout_rate: 0.2
|
252 |
+
pitch_predictor_layers: 5
|
253 |
+
pitch_predictor_chans: 256
|
254 |
+
pitch_predictor_kernel_size: 5
|
255 |
+
pitch_predictor_dropout: 0.5
|
256 |
+
pitch_embed_kernel_size: 1
|
257 |
+
pitch_embed_dropout: 0.0
|
258 |
+
stop_gradient_from_pitch_predictor: true
|
259 |
+
energy_predictor_layers: 2
|
260 |
+
energy_predictor_chans: 256
|
261 |
+
energy_predictor_kernel_size: 3
|
262 |
+
energy_predictor_dropout: 0.5
|
263 |
+
energy_embed_kernel_size: 1
|
264 |
+
energy_embed_dropout: 0.0
|
265 |
+
stop_gradient_from_energy_predictor: false
|
266 |
+
pitch_extract: dio
|
267 |
+
pitch_extract_conf:
|
268 |
+
fs: 22050
|
269 |
+
n_fft: 1024
|
270 |
+
hop_length: 256
|
271 |
+
f0max: 400
|
272 |
+
f0min: 80
|
273 |
+
pitch_normalize: global_mvn
|
274 |
+
pitch_normalize_conf:
|
275 |
+
stats_file: exp/tts_train_tacotron2_raw_phn_tacotron_g2p_en_no_space/decode_tacotron2_teacher_forcing_train.loss.best/stats/train/pitch_stats.npz
|
276 |
+
energy_extract: energy
|
277 |
+
energy_extract_conf:
|
278 |
+
fs: 22050
|
279 |
+
n_fft: 1024
|
280 |
+
hop_length: 256
|
281 |
+
win_length: null
|
282 |
+
energy_normalize: global_mvn
|
283 |
+
energy_normalize_conf:
|
284 |
+
stats_file: exp/tts_train_tacotron2_raw_phn_tacotron_g2p_en_no_space/decode_tacotron2_teacher_forcing_train.loss.best/stats/train/energy_stats.npz
|
285 |
+
required:
|
286 |
+
- output_dir
|
287 |
+
- token_list
|
288 |
+
distributed: false
|
exp/tts_train_conformer_fastspeech2_raw_phn_tacotron_g2p_en_no_space/images/backward_time.png
ADDED
![]() |
exp/tts_train_conformer_fastspeech2_raw_phn_tacotron_g2p_en_no_space/images/duration_loss.png
ADDED
![]() |
exp/tts_train_conformer_fastspeech2_raw_phn_tacotron_g2p_en_no_space/images/energy_loss.png
ADDED
![]() |
exp/tts_train_conformer_fastspeech2_raw_phn_tacotron_g2p_en_no_space/images/forward_time.png
ADDED
![]() |
exp/tts_train_conformer_fastspeech2_raw_phn_tacotron_g2p_en_no_space/images/iter_time.png
ADDED
![]() |
exp/tts_train_conformer_fastspeech2_raw_phn_tacotron_g2p_en_no_space/images/l1_loss.png
ADDED
![]() |
exp/tts_train_conformer_fastspeech2_raw_phn_tacotron_g2p_en_no_space/images/loss.png
ADDED
![]() |
exp/tts_train_conformer_fastspeech2_raw_phn_tacotron_g2p_en_no_space/images/lr_0.png
ADDED
![]() |
exp/tts_train_conformer_fastspeech2_raw_phn_tacotron_g2p_en_no_space/images/optim_step_time.png
ADDED
![]() |
exp/tts_train_conformer_fastspeech2_raw_phn_tacotron_g2p_en_no_space/images/pitch_loss.png
ADDED
![]() |
exp/tts_train_conformer_fastspeech2_raw_phn_tacotron_g2p_en_no_space/images/train_time.png
ADDED
![]() |
exp/tts_train_conformer_fastspeech2_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 sha256:02b3f1af8dc9af8bee03999683092029d93dc21c6690044bc80b7ace59bec16a
|
3 |
+
size 281405749
|
exp/tts_train_tacotron2_raw_phn_tacotron_g2p_en_no_space/decode_tacotron2_teacher_forcing_train.loss.best/stats/train/energy_stats.npz
ADDED
Binary file (770 Bytes). View file
|
|
exp/tts_train_tacotron2_raw_phn_tacotron_g2p_en_no_space/decode_tacotron2_teacher_forcing_train.loss.best/stats/train/feats_stats.npz
ADDED
Binary file (1.4 kB). View file
|
|
exp/tts_train_tacotron2_raw_phn_tacotron_g2p_en_no_space/decode_tacotron2_teacher_forcing_train.loss.best/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_conformer_fastspeech2_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: 1600432937.488829
|
6 |
+
torch: 1.6.0
|
7 |
+
yaml_files:
|
8 |
+
train_config: exp/tts_train_conformer_fastspeech2_raw_phn_tacotron_g2p_en_no_space/config.yaml
|