Update model
Browse files- README.md +773 -0
- data/token_list/bpe_unigram500/bpe.model +3 -0
- exp/asr_stats_raw_bpe500/train/feats_stats.npz +0 -0
- exp/asr_train_asr_transformer_specaug_raw_bpe500/56epoch.pth +3 -0
- exp/asr_train_asr_transformer_specaug_raw_bpe500/RESULTS.md +29 -0
- exp/asr_train_asr_transformer_specaug_raw_bpe500/config.yaml +676 -0
- exp/asr_train_asr_transformer_specaug_raw_bpe500/images/acc.png +0 -0
- exp/asr_train_asr_transformer_specaug_raw_bpe500/images/backward_time.png +0 -0
- exp/asr_train_asr_transformer_specaug_raw_bpe500/images/cer.png +0 -0
- exp/asr_train_asr_transformer_specaug_raw_bpe500/images/cer_ctc.png +0 -0
- exp/asr_train_asr_transformer_specaug_raw_bpe500/images/forward_time.png +0 -0
- exp/asr_train_asr_transformer_specaug_raw_bpe500/images/gpu_max_cached_mem_GB.png +0 -0
- exp/asr_train_asr_transformer_specaug_raw_bpe500/images/iter_time.png +0 -0
- exp/asr_train_asr_transformer_specaug_raw_bpe500/images/loss.png +0 -0
- exp/asr_train_asr_transformer_specaug_raw_bpe500/images/loss_att.png +0 -0
- exp/asr_train_asr_transformer_specaug_raw_bpe500/images/loss_ctc.png +0 -0
- exp/asr_train_asr_transformer_specaug_raw_bpe500/images/optim0_lr0.png +0 -0
- exp/asr_train_asr_transformer_specaug_raw_bpe500/images/optim_step_time.png +0 -0
- exp/asr_train_asr_transformer_specaug_raw_bpe500/images/train_time.png +0 -0
- exp/asr_train_asr_transformer_specaug_raw_bpe500/images/wer.png +0 -0
- meta.yaml +8 -0
README.md
ADDED
@@ -0,0 +1,773 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- espnet
|
4 |
+
- audio
|
5 |
+
- automatic-speech-recognition
|
6 |
+
language: noinfo
|
7 |
+
datasets:
|
8 |
+
- yolo_mixtec
|
9 |
+
license: cc-by-4.0
|
10 |
+
---
|
11 |
+
|
12 |
+
## ESPnet2 ASR model
|
13 |
+
|
14 |
+
### `espnet/ftshijt_espnet2_asr_yolo_mixtec_transformer`
|
15 |
+
|
16 |
+
This model was trained by ftshijt using yolo_mixtec recipe in [espnet](https://github.com/espnet/espnet/).
|
17 |
+
|
18 |
+
### Demo: How to use in ESPnet2
|
19 |
+
|
20 |
+
```bash
|
21 |
+
cd espnet
|
22 |
+
|
23 |
+
pip install -e .
|
24 |
+
cd els/yolo_mixtec/asr1
|
25 |
+
./run.sh --skip_data_prep false --skip_train true --download_model espnet/ftshijt_espnet2_asr_yolo_mixtec_transformer
|
26 |
+
```
|
27 |
+
|
28 |
+
<!-- Generated by scripts/utils/show_asr_result.sh -->
|
29 |
+
# RESULTS
|
30 |
+
## Environments
|
31 |
+
- date: `Wed Nov 10 02:59:39 EST 2021`
|
32 |
+
- python version: `3.9.7 (default, Sep 16 2021, 13:09:58) [GCC 7.5.0]`
|
33 |
+
- espnet version: `espnet 0.10.4a1`
|
34 |
+
- pytorch version: `pytorch 1.9.0`
|
35 |
+
- Git hash: ``
|
36 |
+
- Commit date: ``
|
37 |
+
|
38 |
+
## asr_train_asr_transformer_specaug_raw_bpe500
|
39 |
+
### WER
|
40 |
+
|
41 |
+
|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
|
42 |
+
|---|---|---|---|---|---|---|---|---|
|
43 |
+
|decode_asr_lm_lm_train_bpe500_valid.loss.ave_asr_model_valid.acc.best/test|4985|81348|84.1|11.8|4.1|2.5|18.3|82.5|
|
44 |
+
|
45 |
+
### CER
|
46 |
+
|
47 |
+
|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
|
48 |
+
|---|---|---|---|---|---|---|---|---|
|
49 |
+
|decode_asr_lm_lm_train_bpe500_valid.loss.ave_asr_model_valid.acc.best/test|4985|626187|93.4|2.2|4.4|2.4|9.0|82.5|
|
50 |
+
|
51 |
+
### TER
|
52 |
+
|
53 |
+
|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
|
54 |
+
|---|---|---|---|---|---|---|---|---|
|
55 |
+
|decode_asr_lm_lm_train_bpe500_valid.loss.ave_asr_model_valid.acc.best/test|4985|325684|90.7|5.2|4.1|2.2|11.5|82.5|
|
56 |
+
|
57 |
+
## ASR config
|
58 |
+
|
59 |
+
<details><summary>expand</summary>
|
60 |
+
|
61 |
+
```
|
62 |
+
config: conf/tuning/train_asr_transformer_specaug.yaml
|
63 |
+
print_config: false
|
64 |
+
log_level: INFO
|
65 |
+
dry_run: false
|
66 |
+
iterator_type: sequence
|
67 |
+
output_dir: exp/asr_train_asr_transformer_specaug_raw_bpe500
|
68 |
+
ngpu: 1
|
69 |
+
seed: 0
|
70 |
+
num_workers: 1
|
71 |
+
num_att_plot: 3
|
72 |
+
dist_backend: nccl
|
73 |
+
dist_init_method: env://
|
74 |
+
dist_world_size: null
|
75 |
+
dist_rank: null
|
76 |
+
local_rank: 0
|
77 |
+
dist_master_addr: null
|
78 |
+
dist_master_port: null
|
79 |
+
dist_launcher: null
|
80 |
+
multiprocessing_distributed: false
|
81 |
+
unused_parameters: false
|
82 |
+
sharded_ddp: false
|
83 |
+
cudnn_enabled: true
|
84 |
+
cudnn_benchmark: false
|
85 |
+
cudnn_deterministic: true
|
86 |
+
collect_stats: false
|
87 |
+
write_collected_feats: false
|
88 |
+
max_epoch: 100
|
89 |
+
patience: 15
|
90 |
+
val_scheduler_criterion:
|
91 |
+
- valid
|
92 |
+
- loss
|
93 |
+
early_stopping_criterion:
|
94 |
+
- valid
|
95 |
+
- loss
|
96 |
+
- min
|
97 |
+
best_model_criterion:
|
98 |
+
- - valid
|
99 |
+
- acc
|
100 |
+
- max
|
101 |
+
keep_nbest_models: 10
|
102 |
+
grad_clip: 5
|
103 |
+
grad_clip_type: 2.0
|
104 |
+
grad_noise: false
|
105 |
+
accum_grad: 2
|
106 |
+
no_forward_run: false
|
107 |
+
resume: true
|
108 |
+
train_dtype: float32
|
109 |
+
use_amp: false
|
110 |
+
log_interval: null
|
111 |
+
use_tensorboard: true
|
112 |
+
use_wandb: false
|
113 |
+
wandb_project: null
|
114 |
+
wandb_id: null
|
115 |
+
wandb_entity: null
|
116 |
+
wandb_name: null
|
117 |
+
wandb_model_log_interval: -1
|
118 |
+
detect_anomaly: false
|
119 |
+
pretrain_path: null
|
120 |
+
init_param: []
|
121 |
+
ignore_init_mismatch: false
|
122 |
+
freeze_param: []
|
123 |
+
num_iters_per_epoch: null
|
124 |
+
batch_size: 32
|
125 |
+
valid_batch_size: null
|
126 |
+
batch_bins: 1000000
|
127 |
+
valid_batch_bins: null
|
128 |
+
train_shape_file:
|
129 |
+
- exp/asr_stats_raw_bpe500/train/speech_shape
|
130 |
+
- exp/asr_stats_raw_bpe500/train/text_shape.bpe
|
131 |
+
valid_shape_file:
|
132 |
+
- exp/asr_stats_raw_bpe500/valid/speech_shape
|
133 |
+
- exp/asr_stats_raw_bpe500/valid/text_shape.bpe
|
134 |
+
batch_type: folded
|
135 |
+
valid_batch_type: null
|
136 |
+
fold_length:
|
137 |
+
- 80000
|
138 |
+
- 150
|
139 |
+
sort_in_batch: descending
|
140 |
+
sort_batch: descending
|
141 |
+
multiple_iterator: false
|
142 |
+
chunk_length: 500
|
143 |
+
chunk_shift_ratio: 0.5
|
144 |
+
num_cache_chunks: 1024
|
145 |
+
train_data_path_and_name_and_type:
|
146 |
+
- - /tmp/st-jiatong-54826.tbQP9L0N/raw/train/wav.scp
|
147 |
+
- speech
|
148 |
+
- kaldi_ark
|
149 |
+
- - /tmp/st-jiatong-54826.tbQP9L0N/raw/train/text
|
150 |
+
- text
|
151 |
+
- text
|
152 |
+
valid_data_path_and_name_and_type:
|
153 |
+
- - /tmp/st-jiatong-54826.tbQP9L0N/raw/dev/wav.scp
|
154 |
+
- speech
|
155 |
+
- kaldi_ark
|
156 |
+
- - /tmp/st-jiatong-54826.tbQP9L0N/raw/dev/text
|
157 |
+
- text
|
158 |
+
- text
|
159 |
+
allow_variable_data_keys: false
|
160 |
+
max_cache_size: 0.0
|
161 |
+
max_cache_fd: 32
|
162 |
+
valid_max_cache_size: null
|
163 |
+
optim: adam
|
164 |
+
optim_conf:
|
165 |
+
lr: 1.0
|
166 |
+
scheduler: noamlr
|
167 |
+
scheduler_conf:
|
168 |
+
warmup_steps: 25000
|
169 |
+
token_list:
|
170 |
+
- <blank>
|
171 |
+
- <unk>
|
172 |
+
- '4'
|
173 |
+
- '3'
|
174 |
+
- '1'
|
175 |
+
- '2'
|
176 |
+
- A
|
177 |
+
- ▁NDI
|
178 |
+
- '''4'
|
179 |
+
- '''1'
|
180 |
+
- U
|
181 |
+
- ▁BA
|
182 |
+
- O
|
183 |
+
- ▁I
|
184 |
+
- E
|
185 |
+
- 4=
|
186 |
+
- ▁KU
|
187 |
+
- ▁TAN
|
188 |
+
- ▁KA
|
189 |
+
- '''3'
|
190 |
+
- NI
|
191 |
+
- ▁YA
|
192 |
+
- RA
|
193 |
+
- 3=
|
194 |
+
- 2=
|
195 |
+
- IN
|
196 |
+
- NA
|
197 |
+
- ▁TA
|
198 |
+
- AN
|
199 |
+
- ▁KAN
|
200 |
+
- ▁NI
|
201 |
+
- ▁NDA
|
202 |
+
- ▁NA
|
203 |
+
- ▁JI
|
204 |
+
- KAN
|
205 |
+
- CHI
|
206 |
+
- (3)=
|
207 |
+
- I
|
208 |
+
- UN
|
209 |
+
- 1-
|
210 |
+
- ▁SA
|
211 |
+
- (4)=
|
212 |
+
- ▁JA
|
213 |
+
- XI
|
214 |
+
- ▁KO
|
215 |
+
- ▁TI
|
216 |
+
- TA
|
217 |
+
- KU
|
218 |
+
- BI
|
219 |
+
- ▁YU
|
220 |
+
- ▁KWA
|
221 |
+
- KA
|
222 |
+
- XA
|
223 |
+
- 1=
|
224 |
+
- ▁YO
|
225 |
+
- RI
|
226 |
+
- NDO
|
227 |
+
- ▁XA
|
228 |
+
- TU
|
229 |
+
- ▁TU
|
230 |
+
- ▁ÑA
|
231 |
+
- ▁KI
|
232 |
+
- ▁XI
|
233 |
+
- YO
|
234 |
+
- NDU
|
235 |
+
- NDA
|
236 |
+
- ▁CHI
|
237 |
+
- (2)=
|
238 |
+
- ▁BI
|
239 |
+
- ▁NU
|
240 |
+
- KI
|
241 |
+
- (1)=
|
242 |
+
- YU
|
243 |
+
- 3-
|
244 |
+
- ▁MI
|
245 |
+
- 'ON'
|
246 |
+
- ▁A
|
247 |
+
- BA
|
248 |
+
- 4-
|
249 |
+
- KO
|
250 |
+
- ▁NDU
|
251 |
+
- ▁ÑU
|
252 |
+
- ▁NDO
|
253 |
+
- NU
|
254 |
+
- ÑU
|
255 |
+
- '143'
|
256 |
+
- ▁SI
|
257 |
+
- ▁SO
|
258 |
+
- 13-
|
259 |
+
- NDI
|
260 |
+
- ▁AN
|
261 |
+
- ▁SU
|
262 |
+
- TIN
|
263 |
+
- SA
|
264 |
+
- ▁BE
|
265 |
+
- TO
|
266 |
+
- RUN
|
267 |
+
- KWA
|
268 |
+
- KWI
|
269 |
+
- ▁NDE
|
270 |
+
- ▁KWI
|
271 |
+
- XIN
|
272 |
+
- ▁U
|
273 |
+
- SI
|
274 |
+
- SO
|
275 |
+
- ▁TUN
|
276 |
+
- EN
|
277 |
+
- ▁KWE
|
278 |
+
- YA
|
279 |
+
- (4)=2
|
280 |
+
- NDE
|
281 |
+
- TI
|
282 |
+
- TUN
|
283 |
+
- ▁TIN
|
284 |
+
- MA
|
285 |
+
- ▁SE
|
286 |
+
- ▁XU
|
287 |
+
- SU
|
288 |
+
- ▁LU
|
289 |
+
- ▁KE
|
290 |
+
- ▁
|
291 |
+
- MI
|
292 |
+
- ▁RAN
|
293 |
+
- (3)=2
|
294 |
+
- 14-
|
295 |
+
- ▁MA
|
296 |
+
- KUN
|
297 |
+
- LU
|
298 |
+
- N
|
299 |
+
- ▁O
|
300 |
+
- KE
|
301 |
+
- NGA
|
302 |
+
- ▁IS
|
303 |
+
- ▁JU
|
304 |
+
- '='
|
305 |
+
- ▁LA
|
306 |
+
- ÑA
|
307 |
+
- JA
|
308 |
+
- CHUN
|
309 |
+
- R
|
310 |
+
- TAN
|
311 |
+
- PU
|
312 |
+
- ▁TIEM
|
313 |
+
- LI
|
314 |
+
- LA
|
315 |
+
- CHIU
|
316 |
+
- ▁PA
|
317 |
+
- M
|
318 |
+
- ▁REY
|
319 |
+
- ▁BAN
|
320 |
+
- JI
|
321 |
+
- L
|
322 |
+
- SUN
|
323 |
+
- ▁SEÑOR
|
324 |
+
- ▁JO
|
325 |
+
- ▁TIO
|
326 |
+
- KWE
|
327 |
+
- CHU
|
328 |
+
- S
|
329 |
+
- ▁YE
|
330 |
+
- KIN
|
331 |
+
- XU
|
332 |
+
- BE
|
333 |
+
- ▁CUENTA
|
334 |
+
- ▁SAN
|
335 |
+
- RRU
|
336 |
+
- ▁¿
|
337 |
+
- CHA
|
338 |
+
- ▁TO
|
339 |
+
- RRA
|
340 |
+
- LO
|
341 |
+
- TE
|
342 |
+
- ▁AMIGU
|
343 |
+
- PA
|
344 |
+
- XAN
|
345 |
+
- ▁C
|
346 |
+
- C
|
347 |
+
- ▁CHA
|
348 |
+
- ▁TE
|
349 |
+
- ▁HIJO
|
350 |
+
- ▁MB
|
351 |
+
- ▁PI
|
352 |
+
- G
|
353 |
+
- ▁ÁNIMA
|
354 |
+
- ▁CHE
|
355 |
+
- ▁P
|
356 |
+
- B
|
357 |
+
- NDIO
|
358 |
+
- SE
|
359 |
+
- ▁SANTU
|
360 |
+
- MU
|
361 |
+
- ▁PADRE
|
362 |
+
- D
|
363 |
+
- JU
|
364 |
+
- Z
|
365 |
+
- ▁TORO
|
366 |
+
- ▁PO
|
367 |
+
- LE
|
368 |
+
- ▁LI
|
369 |
+
- RO
|
370 |
+
- ▁LO
|
371 |
+
- ▁MESA
|
372 |
+
- CA
|
373 |
+
- ▁CHIU
|
374 |
+
- DO
|
375 |
+
- ▁BU
|
376 |
+
- ▁BUTA
|
377 |
+
- JO
|
378 |
+
- T
|
379 |
+
- TRU
|
380 |
+
- RU
|
381 |
+
- ▁MBO
|
382 |
+
- ▁JUAN
|
383 |
+
- ▁MM
|
384 |
+
- ▁CA
|
385 |
+
- ▁M
|
386 |
+
- ▁MAS
|
387 |
+
- ▁DE
|
388 |
+
- V
|
389 |
+
- ▁MAÑA
|
390 |
+
- ▁UTA
|
391 |
+
- DA
|
392 |
+
- ▁MULA
|
393 |
+
- ▁YOLOXÓCHITL
|
394 |
+
- ▁CONSEJU
|
395 |
+
- ▁Y
|
396 |
+
- ▁LE
|
397 |
+
- ÓN
|
398 |
+
- ▁MISA
|
399 |
+
- TIU
|
400 |
+
- ▁CANDELA
|
401 |
+
- ▁PATRÓN
|
402 |
+
- ▁PADRINU
|
403 |
+
- ▁MARCU
|
404 |
+
- ▁V
|
405 |
+
- ▁G
|
406 |
+
- Í
|
407 |
+
- ▁XE
|
408 |
+
- ▁MU
|
409 |
+
- ▁XO
|
410 |
+
- NGUI
|
411 |
+
- ▁CO
|
412 |
+
- ▁HOMBRE
|
413 |
+
- ▁PESU
|
414 |
+
- ▁PE
|
415 |
+
- ▁D
|
416 |
+
- ▁MACHITI
|
417 |
+
- CO
|
418 |
+
- REN
|
419 |
+
- ▁RANCHU
|
420 |
+
- ▁MIS
|
421 |
+
- ▁MACHU
|
422 |
+
- J
|
423 |
+
- ▁PAN
|
424 |
+
- CHO
|
425 |
+
- H
|
426 |
+
- ▁CHU
|
427 |
+
- Y
|
428 |
+
- ▁TON
|
429 |
+
- GA
|
430 |
+
- X
|
431 |
+
- ▁VI
|
432 |
+
- ▁FE
|
433 |
+
- ▁TARRAYA
|
434 |
+
- ▁SANTÍSIMA
|
435 |
+
- ▁N
|
436 |
+
- ▁MAYÓ
|
437 |
+
- ▁CARRU
|
438 |
+
- ▁F
|
439 |
+
- ▁PAPÁ
|
440 |
+
- ▁PALOMA
|
441 |
+
- ▁MARÍA
|
442 |
+
- ▁PEDRU
|
443 |
+
- ▁CAFÉ
|
444 |
+
- ▁COMISARIO
|
445 |
+
- ▁PANELA
|
446 |
+
- ▁PELÓN
|
447 |
+
- É
|
448 |
+
- ▁POZO
|
449 |
+
- ▁CABRÓN
|
450 |
+
- ▁GUACHU
|
451 |
+
- ▁S
|
452 |
+
- RES
|
453 |
+
- ▁COSTUMBRE
|
454 |
+
- ▁SEÑA
|
455 |
+
- QUI
|
456 |
+
- ▁ORO
|
457 |
+
- CH
|
458 |
+
- ▁MAR
|
459 |
+
- SIN
|
460 |
+
- SAN
|
461 |
+
- ▁COSTA
|
462 |
+
- ▁MAMÁ
|
463 |
+
- ▁CINCUENTA
|
464 |
+
- ▁CHO
|
465 |
+
- ▁PEDR
|
466 |
+
- ▁JUNTA
|
467 |
+
- MÚ
|
468 |
+
- ▁TIENDA
|
469 |
+
- ▁JOSÉ
|
470 |
+
- NC
|
471 |
+
- ▁ES
|
472 |
+
- ▁SUERTE
|
473 |
+
- ▁FAMILIA
|
474 |
+
- ▁ZAPATU
|
475 |
+
- NTE
|
476 |
+
- ▁PASTO
|
477 |
+
- ▁CON
|
478 |
+
- Ñ
|
479 |
+
- ▁BOTE
|
480 |
+
- CIÓN
|
481 |
+
- ▁RE
|
482 |
+
- ▁BOLSA
|
483 |
+
- ▁MANGO
|
484 |
+
- ▁JWE
|
485 |
+
- ▁GASTU
|
486 |
+
- ▁T
|
487 |
+
- ▁B
|
488 |
+
- ▁KW
|
489 |
+
- ÍN
|
490 |
+
- ▁HIJA
|
491 |
+
- ▁CUARENT
|
492 |
+
- ▁VAQUERU
|
493 |
+
- ▁NECHITO
|
494 |
+
- ▁NOVIA
|
495 |
+
- ▁NOVIO
|
496 |
+
- JWE
|
497 |
+
- ▁PUENTE
|
498 |
+
- ▁SANDÍA
|
499 |
+
- ▁MALA
|
500 |
+
- Ó
|
501 |
+
- ▁ABONO
|
502 |
+
- ▁JESÚS
|
503 |
+
- ▁CUARTO
|
504 |
+
- ▁EFE
|
505 |
+
- ▁REINA
|
506 |
+
- ▁COMANDANTE
|
507 |
+
- ▁ESCUELA
|
508 |
+
- ▁MANZANA
|
509 |
+
- ▁MÁQUINA
|
510 |
+
- LLA
|
511 |
+
- ▁COR
|
512 |
+
- ▁JERÓNIMO
|
513 |
+
- ▁PISTOLA
|
514 |
+
- NGI
|
515 |
+
- CIO
|
516 |
+
- ▁FRANCISCU
|
517 |
+
- ▁TEODORO
|
518 |
+
- CER
|
519 |
+
- ▁SALUBI
|
520 |
+
- ▁MEZA
|
521 |
+
- ▁MÚSIC
|
522 |
+
- ▁RU
|
523 |
+
- ▁CONSTANTINO
|
524 |
+
- ▁GARCÍA
|
525 |
+
- ▁FRENU
|
526 |
+
- ▁ROSA
|
527 |
+
- ▁CERVEZA
|
528 |
+
- ▁CIGARRU
|
529 |
+
- ▁COMISIÓN
|
530 |
+
- ▁CUNIJO
|
531 |
+
- ▁FRANCISCO
|
532 |
+
- ▁HÍJOLE
|
533 |
+
- ▁NUEVE
|
534 |
+
- ▁MUL
|
535 |
+
- ▁PANTALÓN
|
536 |
+
- ▁CAMISA
|
537 |
+
- ▁CHINGADA
|
538 |
+
- ▁SEMANA
|
539 |
+
- ▁COM
|
540 |
+
- GAR
|
541 |
+
- ▁MARTÍN
|
542 |
+
- ▁SÁBADO
|
543 |
+
- ▁TRABAJO
|
544 |
+
- ▁CINCO
|
545 |
+
- ▁DIE
|
546 |
+
- ▁EST
|
547 |
+
- NDWA
|
548 |
+
- ▁LECHIN
|
549 |
+
- ▁COCO
|
550 |
+
- ILLU
|
551 |
+
- ▁CORRE
|
552 |
+
- ▁MADR
|
553 |
+
- ▁REC
|
554 |
+
- ▁BAUTISTA
|
555 |
+
- ▁VENTANA
|
556 |
+
- ▁CUÑAD
|
557 |
+
- ▁ANTONIU
|
558 |
+
- ▁COPALA
|
559 |
+
- LÍN
|
560 |
+
- ▁SECUND
|
561 |
+
- ▁COHETE
|
562 |
+
- ▁HISTORIA
|
563 |
+
- ▁POLICÍA
|
564 |
+
- ENCIA
|
565 |
+
- ▁CAD
|
566 |
+
- ▁LUIS
|
567 |
+
- ▁DOCTOR
|
568 |
+
- ▁GONZÁLEZ
|
569 |
+
- ▁JUEVE
|
570 |
+
- ▁LIBRU
|
571 |
+
- ▁QUESU
|
572 |
+
- ▁VIAJE
|
573 |
+
- ▁CART
|
574 |
+
- ▁LOCO
|
575 |
+
- ▁BOL
|
576 |
+
- ▁COMPADRE
|
577 |
+
- ▁JWI
|
578 |
+
- ▁METRU
|
579 |
+
- ▁BUENO
|
580 |
+
- ▁TRE
|
581 |
+
- ▁CASTILLO
|
582 |
+
- ▁COMITÉ
|
583 |
+
- ▁ETERNO
|
584 |
+
- ▁LÍQUIDO
|
585 |
+
- ▁MOLE
|
586 |
+
- ▁CAPULCU
|
587 |
+
- ▁DOMING
|
588 |
+
- ▁ROMA
|
589 |
+
- ▁CARAJU
|
590 |
+
- ▁RIATA
|
591 |
+
- ▁TRATU
|
592 |
+
- ▁SEIS
|
593 |
+
- ▁ADÁN
|
594 |
+
- ▁JUANCITO
|
595 |
+
- ▁HOR
|
596 |
+
- ''''
|
597 |
+
- ▁ARRÓ
|
598 |
+
- ▁COCINA
|
599 |
+
- ▁PALACIO
|
600 |
+
- ▁RÓMULO
|
601 |
+
- K
|
602 |
+
- ▁ALFONSO
|
603 |
+
- ▁BARTOLO
|
604 |
+
- ▁FELIPE
|
605 |
+
- ▁HERRER
|
606 |
+
- ▁PAULINO
|
607 |
+
- ▁YEGUA
|
608 |
+
- ▁LISTA
|
609 |
+
- Ú
|
610 |
+
- ▁ABRIL
|
611 |
+
- ▁CUATRO
|
612 |
+
- ▁DICIEMBRE
|
613 |
+
- ▁MARGARITO
|
614 |
+
- ▁MOJONERA
|
615 |
+
- ▁SOLEDAD
|
616 |
+
- ▁VESTIDO
|
617 |
+
- ▁PELOTA
|
618 |
+
- RRET
|
619 |
+
- ▁CAPITÁN
|
620 |
+
- ▁COMUNIÓN
|
621 |
+
- ▁CUCHARA
|
622 |
+
- ▁FERNANDO
|
623 |
+
- ▁GUADALUPE
|
624 |
+
- ▁MIGUEL
|
625 |
+
- ▁PELÚN
|
626 |
+
- ▁SECRETARIU
|
627 |
+
- ▁LENCHU
|
628 |
+
- ▁EVA
|
629 |
+
- ▁SEGUND
|
630 |
+
- ▁CANTOR
|
631 |
+
- ▁CHILPANCINGO
|
632 |
+
- ▁GABRIEL
|
633 |
+
- ▁QUINIENTO
|
634 |
+
- ▁RAÚL
|
635 |
+
- ▁SEVERIAN
|
636 |
+
- ▁TUMBADA
|
637 |
+
- ▁MALINCHI
|
638 |
+
- ▁PRIMU
|
639 |
+
- ▁MORAL
|
640 |
+
- ▁AGOSTO
|
641 |
+
- ▁CENTÍMETRO
|
642 |
+
- ▁FIRMA
|
643 |
+
- ▁HUEHUETÁN
|
644 |
+
- ▁MANGUERA
|
645 |
+
- ▁MEDI
|
646 |
+
- ▁MUERT
|
647 |
+
- ▁SALAZAR
|
648 |
+
- ▁VIERNI
|
649 |
+
- LILL
|
650 |
+
- ▁LL
|
651 |
+
- '-'
|
652 |
+
- ▁CAMPESINO
|
653 |
+
- ▁CIVIL
|
654 |
+
- ▁COMISARIADO
|
655 |
+
- )
|
656 |
+
- (
|
657 |
+
- Ã
|
658 |
+
- ‘
|
659 |
+
- ¿
|
660 |
+
- Ü
|
661 |
+
- ¡
|
662 |
+
- Q
|
663 |
+
- F
|
664 |
+
- Á
|
665 |
+
- P
|
666 |
+
- Ÿ
|
667 |
+
- W
|
668 |
+
- Ý
|
669 |
+
- <sos/eos>
|
670 |
+
init: xavier_uniform
|
671 |
+
input_size: null
|
672 |
+
ctc_conf:
|
673 |
+
dropout_rate: 0.0
|
674 |
+
ctc_type: builtin
|
675 |
+
reduce: true
|
676 |
+
ignore_nan_grad: true
|
677 |
+
model_conf:
|
678 |
+
ctc_weight: 0.3
|
679 |
+
lsm_weight: 0.1
|
680 |
+
length_normalized_loss: false
|
681 |
+
use_preprocessor: true
|
682 |
+
token_type: bpe
|
683 |
+
bpemodel: data/token_list/bpe_unigram500/bpe.model
|
684 |
+
non_linguistic_symbols: null
|
685 |
+
cleaner: null
|
686 |
+
g2p: null
|
687 |
+
speech_volume_normalize: null
|
688 |
+
rir_scp: null
|
689 |
+
rir_apply_prob: 1.0
|
690 |
+
noise_scp: null
|
691 |
+
noise_apply_prob: 1.0
|
692 |
+
noise_db_range: '13_15'
|
693 |
+
frontend: default
|
694 |
+
frontend_conf:
|
695 |
+
fs: 16k
|
696 |
+
specaug: specaug
|
697 |
+
specaug_conf:
|
698 |
+
apply_time_warp: true
|
699 |
+
time_warp_window: 5
|
700 |
+
time_warp_mode: bicubic
|
701 |
+
apply_freq_mask: true
|
702 |
+
freq_mask_width_range:
|
703 |
+
- 0
|
704 |
+
- 30
|
705 |
+
num_freq_mask: 2
|
706 |
+
apply_time_mask: true
|
707 |
+
time_mask_width_range:
|
708 |
+
- 0
|
709 |
+
- 40
|
710 |
+
num_time_mask: 2
|
711 |
+
normalize: global_mvn
|
712 |
+
normalize_conf:
|
713 |
+
stats_file: exp/asr_stats_raw_bpe500/train/feats_stats.npz
|
714 |
+
preencoder: null
|
715 |
+
preencoder_conf: {}
|
716 |
+
encoder: transformer
|
717 |
+
encoder_conf:
|
718 |
+
input_layer: conv2d
|
719 |
+
num_blocks: 12
|
720 |
+
linear_units: 2048
|
721 |
+
dropout_rate: 0.1
|
722 |
+
output_size: 512
|
723 |
+
attention_heads: 4
|
724 |
+
attention_dropout_rate: 0.0
|
725 |
+
postencoder: null
|
726 |
+
postencoder_conf: {}
|
727 |
+
decoder: transformer
|
728 |
+
decoder_conf:
|
729 |
+
input_layer: embed
|
730 |
+
num_blocks: 6
|
731 |
+
linear_units: 2048
|
732 |
+
dropout_rate: 0.1
|
733 |
+
required:
|
734 |
+
- output_dir
|
735 |
+
- token_list
|
736 |
+
version: 0.10.4a1
|
737 |
+
distributed: false
|
738 |
+
```
|
739 |
+
|
740 |
+
</details>
|
741 |
+
|
742 |
+
|
743 |
+
|
744 |
+
### Citing ESPnet
|
745 |
+
|
746 |
+
```BibTex
|
747 |
+
@inproceedings{watanabe2018espnet,
|
748 |
+
author={Shinji Watanabe and Takaaki Hori and Shigeki Karita and Tomoki Hayashi and Jiro Nishitoba and Yuya Unno and Nelson Yalta and Jahn Heymann and Matthew Wiesner and Nanxin Chen and Adithya Renduchintala and Tsubasa Ochiai},
|
749 |
+
title={{ESPnet}: End-to-End Speech Processing Toolkit},
|
750 |
+
year={2018},
|
751 |
+
booktitle={Proceedings of Interspeech},
|
752 |
+
pages={2207--2211},
|
753 |
+
doi={10.21437/Interspeech.2018-1456},
|
754 |
+
url={http://dx.doi.org/10.21437/Interspeech.2018-1456}
|
755 |
+
}
|
756 |
+
|
757 |
+
|
758 |
+
|
759 |
+
|
760 |
+
```
|
761 |
+
|
762 |
+
or arXiv:
|
763 |
+
|
764 |
+
```bibtex
|
765 |
+
@misc{watanabe2018espnet,
|
766 |
+
title={ESPnet: End-to-End Speech Processing Toolkit},
|
767 |
+
author={Shinji Watanabe and Takaaki Hori and Shigeki Karita and Tomoki Hayashi and Jiro Nishitoba and Yuya Unno and Nelson Yalta and Jahn Heymann and Matthew Wiesner and Nanxin Chen and Adithya Renduchintala and Tsubasa Ochiai},
|
768 |
+
year={2018},
|
769 |
+
eprint={1804.00015},
|
770 |
+
archivePrefix={arXiv},
|
771 |
+
primaryClass={cs.CL}
|
772 |
+
}
|
773 |
+
```
|
data/token_list/bpe_unigram500/bpe.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:92b5c5a4f2da619fc71f8938c06e011f79a8fd1824ea835a78c65c88941c7004
|
3 |
+
size 244672
|
exp/asr_stats_raw_bpe500/train/feats_stats.npz
ADDED
Binary file (1.4 kB). View file
|
|
exp/asr_train_asr_transformer_specaug_raw_bpe500/56epoch.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0d825491b8c9d8ddf38476dd110957d6c6e5d7fad2bad317d0e38da2786caa66
|
3 |
+
size 284901797
|
exp/asr_train_asr_transformer_specaug_raw_bpe500/RESULTS.md
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
<!-- Generated by scripts/utils/show_asr_result.sh -->
|
2 |
+
# RESULTS
|
3 |
+
## Environments
|
4 |
+
- date: `Wed Nov 10 02:59:39 EST 2021`
|
5 |
+
- python version: `3.9.7 (default, Sep 16 2021, 13:09:58) [GCC 7.5.0]`
|
6 |
+
- espnet version: `espnet 0.10.4a1`
|
7 |
+
- pytorch version: `pytorch 1.9.0`
|
8 |
+
- Git hash: ``
|
9 |
+
- Commit date: ``
|
10 |
+
|
11 |
+
## asr_train_asr_transformer_specaug_raw_bpe500
|
12 |
+
### WER
|
13 |
+
|
14 |
+
|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
|
15 |
+
|---|---|---|---|---|---|---|---|---|
|
16 |
+
|decode_asr_lm_lm_train_bpe500_valid.loss.ave_asr_model_valid.acc.best/test|4985|81348|84.1|11.8|4.1|2.5|18.3|82.5|
|
17 |
+
|
18 |
+
### CER
|
19 |
+
|
20 |
+
|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
|
21 |
+
|---|---|---|---|---|---|---|---|---|
|
22 |
+
|decode_asr_lm_lm_train_bpe500_valid.loss.ave_asr_model_valid.acc.best/test|4985|626187|93.4|2.2|4.4|2.4|9.0|82.5|
|
23 |
+
|
24 |
+
### TER
|
25 |
+
|
26 |
+
|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
|
27 |
+
|---|---|---|---|---|---|---|---|---|
|
28 |
+
|decode_asr_lm_lm_train_bpe500_valid.loss.ave_asr_model_valid.acc.best/test|4985|325684|90.7|5.2|4.1|2.2|11.5|82.5|
|
29 |
+
|
exp/asr_train_asr_transformer_specaug_raw_bpe500/config.yaml
ADDED
@@ -0,0 +1,676 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
config: conf/tuning/train_asr_transformer_specaug.yaml
|
2 |
+
print_config: false
|
3 |
+
log_level: INFO
|
4 |
+
dry_run: false
|
5 |
+
iterator_type: sequence
|
6 |
+
output_dir: exp/asr_train_asr_transformer_specaug_raw_bpe500
|
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 |
+
unused_parameters: false
|
21 |
+
sharded_ddp: false
|
22 |
+
cudnn_enabled: true
|
23 |
+
cudnn_benchmark: false
|
24 |
+
cudnn_deterministic: true
|
25 |
+
collect_stats: false
|
26 |
+
write_collected_feats: false
|
27 |
+
max_epoch: 100
|
28 |
+
patience: 15
|
29 |
+
val_scheduler_criterion:
|
30 |
+
- valid
|
31 |
+
- loss
|
32 |
+
early_stopping_criterion:
|
33 |
+
- valid
|
34 |
+
- loss
|
35 |
+
- min
|
36 |
+
best_model_criterion:
|
37 |
+
- - valid
|
38 |
+
- acc
|
39 |
+
- max
|
40 |
+
keep_nbest_models: 10
|
41 |
+
grad_clip: 5
|
42 |
+
grad_clip_type: 2.0
|
43 |
+
grad_noise: false
|
44 |
+
accum_grad: 2
|
45 |
+
no_forward_run: false
|
46 |
+
resume: true
|
47 |
+
train_dtype: float32
|
48 |
+
use_amp: false
|
49 |
+
log_interval: null
|
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: null
|
63 |
+
batch_size: 32
|
64 |
+
valid_batch_size: null
|
65 |
+
batch_bins: 1000000
|
66 |
+
valid_batch_bins: null
|
67 |
+
train_shape_file:
|
68 |
+
- exp/asr_stats_raw_bpe500/train/speech_shape
|
69 |
+
- exp/asr_stats_raw_bpe500/train/text_shape.bpe
|
70 |
+
valid_shape_file:
|
71 |
+
- exp/asr_stats_raw_bpe500/valid/speech_shape
|
72 |
+
- exp/asr_stats_raw_bpe500/valid/text_shape.bpe
|
73 |
+
batch_type: folded
|
74 |
+
valid_batch_type: null
|
75 |
+
fold_length:
|
76 |
+
- 80000
|
77 |
+
- 150
|
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 |
+
- - /tmp/st-jiatong-54826.tbQP9L0N/raw/train/wav.scp
|
86 |
+
- speech
|
87 |
+
- kaldi_ark
|
88 |
+
- - /tmp/st-jiatong-54826.tbQP9L0N/raw/train/text
|
89 |
+
- text
|
90 |
+
- text
|
91 |
+
valid_data_path_and_name_and_type:
|
92 |
+
- - /tmp/st-jiatong-54826.tbQP9L0N/raw/dev/wav.scp
|
93 |
+
- speech
|
94 |
+
- kaldi_ark
|
95 |
+
- - /tmp/st-jiatong-54826.tbQP9L0N/raw/dev/text
|
96 |
+
- text
|
97 |
+
- text
|
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: adam
|
103 |
+
optim_conf:
|
104 |
+
lr: 1.0
|
105 |
+
scheduler: noamlr
|
106 |
+
scheduler_conf:
|
107 |
+
warmup_steps: 25000
|
108 |
+
token_list:
|
109 |
+
- <blank>
|
110 |
+
- <unk>
|
111 |
+
- '4'
|
112 |
+
- '3'
|
113 |
+
- '1'
|
114 |
+
- '2'
|
115 |
+
- A
|
116 |
+
- ▁NDI
|
117 |
+
- '''4'
|
118 |
+
- '''1'
|
119 |
+
- U
|
120 |
+
- ▁BA
|
121 |
+
- O
|
122 |
+
- ▁I
|
123 |
+
- E
|
124 |
+
- 4=
|
125 |
+
- ▁KU
|
126 |
+
- ▁TAN
|
127 |
+
- ▁KA
|
128 |
+
- '''3'
|
129 |
+
- NI
|
130 |
+
- ▁YA
|
131 |
+
- RA
|
132 |
+
- 3=
|
133 |
+
- 2=
|
134 |
+
- IN
|
135 |
+
- NA
|
136 |
+
- ▁TA
|
137 |
+
- AN
|
138 |
+
- ▁KAN
|
139 |
+
- ▁NI
|
140 |
+
- ▁NDA
|
141 |
+
- ▁NA
|
142 |
+
- ▁JI
|
143 |
+
- KAN
|
144 |
+
- CHI
|
145 |
+
- (3)=
|
146 |
+
- I
|
147 |
+
- UN
|
148 |
+
- 1-
|
149 |
+
- ▁SA
|
150 |
+
- (4)=
|
151 |
+
- ▁JA
|
152 |
+
- XI
|
153 |
+
- ▁KO
|
154 |
+
- ▁TI
|
155 |
+
- TA
|
156 |
+
- KU
|
157 |
+
- BI
|
158 |
+
- ▁YU
|
159 |
+
- ▁KWA
|
160 |
+
- KA
|
161 |
+
- XA
|
162 |
+
- 1=
|
163 |
+
- ▁YO
|
164 |
+
- RI
|
165 |
+
- NDO
|
166 |
+
- ▁XA
|
167 |
+
- TU
|
168 |
+
- ▁TU
|
169 |
+
- ▁ÑA
|
170 |
+
- ▁KI
|
171 |
+
- ▁XI
|
172 |
+
- YO
|
173 |
+
- NDU
|
174 |
+
- NDA
|
175 |
+
- ▁CHI
|
176 |
+
- (2)=
|
177 |
+
- ▁BI
|
178 |
+
- ▁NU
|
179 |
+
- KI
|
180 |
+
- (1)=
|
181 |
+
- YU
|
182 |
+
- 3-
|
183 |
+
- ▁MI
|
184 |
+
- 'ON'
|
185 |
+
- ▁A
|
186 |
+
- BA
|
187 |
+
- 4-
|
188 |
+
- KO
|
189 |
+
- ▁NDU
|
190 |
+
- ▁ÑU
|
191 |
+
- ▁NDO
|
192 |
+
- NU
|
193 |
+
- ÑU
|
194 |
+
- '143'
|
195 |
+
- ▁SI
|
196 |
+
- ▁SO
|
197 |
+
- 13-
|
198 |
+
- NDI
|
199 |
+
- ▁AN
|
200 |
+
- ▁SU
|
201 |
+
- TIN
|
202 |
+
- SA
|
203 |
+
- ▁BE
|
204 |
+
- TO
|
205 |
+
- RUN
|
206 |
+
- KWA
|
207 |
+
- KWI
|
208 |
+
- ▁NDE
|
209 |
+
- ▁KWI
|
210 |
+
- XIN
|
211 |
+
- ▁U
|
212 |
+
- SI
|
213 |
+
- SO
|
214 |
+
- ▁TUN
|
215 |
+
- EN
|
216 |
+
- ▁KWE
|
217 |
+
- YA
|
218 |
+
- (4)=2
|
219 |
+
- NDE
|
220 |
+
- TI
|
221 |
+
- TUN
|
222 |
+
- ▁TIN
|
223 |
+
- MA
|
224 |
+
- ▁SE
|
225 |
+
- ▁XU
|
226 |
+
- SU
|
227 |
+
- ▁LU
|
228 |
+
- ▁KE
|
229 |
+
- ▁
|
230 |
+
- MI
|
231 |
+
- ▁RAN
|
232 |
+
- (3)=2
|
233 |
+
- 14-
|
234 |
+
- ▁MA
|
235 |
+
- KUN
|
236 |
+
- LU
|
237 |
+
- N
|
238 |
+
- ▁O
|
239 |
+
- KE
|
240 |
+
- NGA
|
241 |
+
- ▁IS
|
242 |
+
- ▁JU
|
243 |
+
- '='
|
244 |
+
- ▁LA
|
245 |
+
- ÑA
|
246 |
+
- JA
|
247 |
+
- CHUN
|
248 |
+
- R
|
249 |
+
- TAN
|
250 |
+
- PU
|
251 |
+
- ▁TIEM
|
252 |
+
- LI
|
253 |
+
- LA
|
254 |
+
- CHIU
|
255 |
+
- ▁PA
|
256 |
+
- M
|
257 |
+
- ▁REY
|
258 |
+
- ▁BAN
|
259 |
+
- JI
|
260 |
+
- L
|
261 |
+
- SUN
|
262 |
+
- ▁SEÑOR
|
263 |
+
- ▁JO
|
264 |
+
- ▁TIO
|
265 |
+
- KWE
|
266 |
+
- CHU
|
267 |
+
- S
|
268 |
+
- ▁YE
|
269 |
+
- KIN
|
270 |
+
- XU
|
271 |
+
- BE
|
272 |
+
- ▁CUENTA
|
273 |
+
- ▁SAN
|
274 |
+
- RRU
|
275 |
+
- ▁¿
|
276 |
+
- CHA
|
277 |
+
- ▁TO
|
278 |
+
- RRA
|
279 |
+
- LO
|
280 |
+
- TE
|
281 |
+
- ▁AMIGU
|
282 |
+
- PA
|
283 |
+
- XAN
|
284 |
+
- ▁C
|
285 |
+
- C
|
286 |
+
- ▁CHA
|
287 |
+
- ▁TE
|
288 |
+
- ▁HIJO
|
289 |
+
- ▁MB
|
290 |
+
- ▁PI
|
291 |
+
- G
|
292 |
+
- ▁ÁNIMA
|
293 |
+
- ▁CHE
|
294 |
+
- ▁P
|
295 |
+
- B
|
296 |
+
- NDIO
|
297 |
+
- SE
|
298 |
+
- ▁SANTU
|
299 |
+
- MU
|
300 |
+
- ▁PADRE
|
301 |
+
- D
|
302 |
+
- JU
|
303 |
+
- Z
|
304 |
+
- ▁TORO
|
305 |
+
- ▁PO
|
306 |
+
- LE
|
307 |
+
- ▁LI
|
308 |
+
- RO
|
309 |
+
- ▁LO
|
310 |
+
- ▁MESA
|
311 |
+
- CA
|
312 |
+
- ▁CHIU
|
313 |
+
- DO
|
314 |
+
- ▁BU
|
315 |
+
- ▁BUTA
|
316 |
+
- JO
|
317 |
+
- T
|
318 |
+
- TRU
|
319 |
+
- RU
|
320 |
+
- ▁MBO
|
321 |
+
- ▁JUAN
|
322 |
+
- ▁MM
|
323 |
+
- ▁CA
|
324 |
+
- ▁M
|
325 |
+
- ▁MAS
|
326 |
+
- ▁DE
|
327 |
+
- V
|
328 |
+
- ▁MAÑA
|
329 |
+
- ▁UTA
|
330 |
+
- DA
|
331 |
+
- ▁MULA
|
332 |
+
- ▁YOLOXÓCHITL
|
333 |
+
- ▁CONSEJU
|
334 |
+
- ▁Y
|
335 |
+
- ▁LE
|
336 |
+
- ÓN
|
337 |
+
- ▁MISA
|
338 |
+
- TIU
|
339 |
+
- ▁CANDELA
|
340 |
+
- ▁PATRÓN
|
341 |
+
- ▁PADRINU
|
342 |
+
- ▁MARCU
|
343 |
+
- ▁V
|
344 |
+
- ▁G
|
345 |
+
- Í
|
346 |
+
- ▁XE
|
347 |
+
- ▁MU
|
348 |
+
- ▁XO
|
349 |
+
- NGUI
|
350 |
+
- ▁CO
|
351 |
+
- ▁HOMBRE
|
352 |
+
- ▁PESU
|
353 |
+
- ▁PE
|
354 |
+
- ▁D
|
355 |
+
- ▁MACHITI
|
356 |
+
- CO
|
357 |
+
- REN
|
358 |
+
- ▁RANCHU
|
359 |
+
- ▁MIS
|
360 |
+
- ▁MACHU
|
361 |
+
- J
|
362 |
+
- ▁PAN
|
363 |
+
- CHO
|
364 |
+
- H
|
365 |
+
- ▁CHU
|
366 |
+
- Y
|
367 |
+
- ▁TON
|
368 |
+
- GA
|
369 |
+
- X
|
370 |
+
- ▁VI
|
371 |
+
- ▁FE
|
372 |
+
- ▁TARRAYA
|
373 |
+
- ▁SANTÍSIMA
|
374 |
+
- ▁N
|
375 |
+
- ▁MAYÓ
|
376 |
+
- ▁CARRU
|
377 |
+
- ▁F
|
378 |
+
- ▁PAPÁ
|
379 |
+
- ▁PALOMA
|
380 |
+
- ▁MARÍA
|
381 |
+
- ▁PEDRU
|
382 |
+
- ▁CAFÉ
|
383 |
+
- ▁COMISARIO
|
384 |
+
- ▁PANELA
|
385 |
+
- ▁PELÓN
|
386 |
+
- É
|
387 |
+
- ▁POZO
|
388 |
+
- ▁CABRÓN
|
389 |
+
- ▁GUACHU
|
390 |
+
- ▁S
|
391 |
+
- RES
|
392 |
+
- ▁COSTUMBRE
|
393 |
+
- ▁SEÑA
|
394 |
+
- QUI
|
395 |
+
- ▁ORO
|
396 |
+
- CH
|
397 |
+
- ▁MAR
|
398 |
+
- SIN
|
399 |
+
- SAN
|
400 |
+
- ▁COSTA
|
401 |
+
- ▁MAMÁ
|
402 |
+
- ▁CINCUENTA
|
403 |
+
- ▁CHO
|
404 |
+
- ▁PEDR
|
405 |
+
- ▁JUNTA
|
406 |
+
- MÚ
|
407 |
+
- ▁TIENDA
|
408 |
+
- ▁JOSÉ
|
409 |
+
- NC
|
410 |
+
- ▁ES
|
411 |
+
- ▁SUERTE
|
412 |
+
- ▁FAMILIA
|
413 |
+
- ▁ZAPATU
|
414 |
+
- NTE
|
415 |
+
- ▁PASTO
|
416 |
+
- ▁CON
|
417 |
+
- Ñ
|
418 |
+
- ▁BOTE
|
419 |
+
- CIÓN
|
420 |
+
- ▁RE
|
421 |
+
- ▁BOLSA
|
422 |
+
- ▁MANGO
|
423 |
+
- ▁JWE
|
424 |
+
- ▁GASTU
|
425 |
+
- ▁T
|
426 |
+
- ▁B
|
427 |
+
- ▁KW
|
428 |
+
- ÍN
|
429 |
+
- ▁HIJA
|
430 |
+
- ▁CUARENT
|
431 |
+
- ▁VAQUERU
|
432 |
+
- ▁NECHITO
|
433 |
+
- ▁NOVIA
|
434 |
+
- ▁NOVIO
|
435 |
+
- JWE
|
436 |
+
- ▁PUENTE
|
437 |
+
- ▁SANDÍA
|
438 |
+
- ▁MALA
|
439 |
+
- Ó
|
440 |
+
- ▁ABONO
|
441 |
+
- ▁JESÚS
|
442 |
+
- ▁CUARTO
|
443 |
+
- ▁EFE
|
444 |
+
- ▁REINA
|
445 |
+
- ▁COMANDANTE
|
446 |
+
- ▁ESCUELA
|
447 |
+
- ▁MANZANA
|
448 |
+
- ▁MÁQUINA
|
449 |
+
- LLA
|
450 |
+
- ▁COR
|
451 |
+
- ▁JERÓNIMO
|
452 |
+
- ▁PISTOLA
|
453 |
+
- NGI
|
454 |
+
- CIO
|
455 |
+
- ▁FRANCISCU
|
456 |
+
- ▁TEODORO
|
457 |
+
- CER
|
458 |
+
- ▁SALUBI
|
459 |
+
- ▁MEZA
|
460 |
+
- ▁MÚSIC
|
461 |
+
- ▁RU
|
462 |
+
- ▁CONSTANTINO
|
463 |
+
- ▁GARCÍA
|
464 |
+
- ▁FRENU
|
465 |
+
- ▁ROSA
|
466 |
+
- ▁CERVEZA
|
467 |
+
- ▁CIGARRU
|
468 |
+
- ▁COMISIÓN
|
469 |
+
- ▁CUNIJO
|
470 |
+
- ▁FRANCISCO
|
471 |
+
- ▁HÍJOLE
|
472 |
+
- ▁NUEVE
|
473 |
+
- ▁MUL
|
474 |
+
- ▁PANTALÓN
|
475 |
+
- ▁CAMISA
|
476 |
+
- ▁CHINGADA
|
477 |
+
- ▁SEMANA
|
478 |
+
- ▁COM
|
479 |
+
- GAR
|
480 |
+
- ▁MARTÍN
|
481 |
+
- ▁SÁBADO
|
482 |
+
- ▁TRABAJO
|
483 |
+
- ▁CINCO
|
484 |
+
- ▁DIE
|
485 |
+
- ▁EST
|
486 |
+
- NDWA
|
487 |
+
- ▁LECHIN
|
488 |
+
- ▁COCO
|
489 |
+
- ILLU
|
490 |
+
- ▁CORRE
|
491 |
+
- ▁MADR
|
492 |
+
- ▁REC
|
493 |
+
- ▁BAUTISTA
|
494 |
+
- ▁VENTANA
|
495 |
+
- ▁CUÑAD
|
496 |
+
- ▁ANTONIU
|
497 |
+
- ▁COPALA
|
498 |
+
- LÍN
|
499 |
+
- ▁SECUND
|
500 |
+
- ▁COHETE
|
501 |
+
- ▁HISTORIA
|
502 |
+
- ▁POLICÍA
|
503 |
+
- ENCIA
|
504 |
+
- ▁CAD
|
505 |
+
- ▁LUIS
|
506 |
+
- ▁DOCTOR
|
507 |
+
- ▁GONZÁLEZ
|
508 |
+
- ▁JUEVE
|
509 |
+
- ▁LIBRU
|
510 |
+
- ▁QUESU
|
511 |
+
- ▁VIAJE
|
512 |
+
- ▁CART
|
513 |
+
- ▁LOCO
|
514 |
+
- ▁BOL
|
515 |
+
- ▁COMPADRE
|
516 |
+
- ▁JWI
|
517 |
+
- ▁METRU
|
518 |
+
- ▁BUENO
|
519 |
+
- ▁TRE
|
520 |
+
- ▁CASTILLO
|
521 |
+
- ▁COMITÉ
|
522 |
+
- ▁ETERNO
|
523 |
+
- ▁LÍQUIDO
|
524 |
+
- ▁MOLE
|
525 |
+
- ▁CAPULCU
|
526 |
+
- ▁DOMING
|
527 |
+
- ▁ROMA
|
528 |
+
- ▁CARAJU
|
529 |
+
- ▁RIATA
|
530 |
+
- ▁TRATU
|
531 |
+
- ▁SEIS
|
532 |
+
- ▁ADÁN
|
533 |
+
- ▁JUANCITO
|
534 |
+
- ▁HOR
|
535 |
+
- ''''
|
536 |
+
- ▁ARRÓ
|
537 |
+
- ▁COCINA
|
538 |
+
- ▁PALACIO
|
539 |
+
- ▁RÓMULO
|
540 |
+
- K
|
541 |
+
- ▁ALFONSO
|
542 |
+
- ▁BARTOLO
|
543 |
+
- ▁FELIPE
|
544 |
+
- ▁HERRER
|
545 |
+
- ▁PAULINO
|
546 |
+
- ▁YEGUA
|
547 |
+
- ▁LISTA
|
548 |
+
- Ú
|
549 |
+
- ▁ABRIL
|
550 |
+
- ▁CUATRO
|
551 |
+
- ▁DICIEMBRE
|
552 |
+
- ▁MARGARITO
|
553 |
+
- ▁MOJONERA
|
554 |
+
- ▁SOLEDAD
|
555 |
+
- ▁VESTIDO
|
556 |
+
- ▁PELOTA
|
557 |
+
- RRET
|
558 |
+
- ▁CAPITÁN
|
559 |
+
- ▁COMUNIÓN
|
560 |
+
- ▁CUCHARA
|
561 |
+
- ▁FERNANDO
|
562 |
+
- ▁GUADALUPE
|
563 |
+
- ▁MIGUEL
|
564 |
+
- ▁PELÚN
|
565 |
+
- ▁SECRETARIU
|
566 |
+
- ▁LENCHU
|
567 |
+
- ▁EVA
|
568 |
+
- ▁SEGUND
|
569 |
+
- ▁CANTOR
|
570 |
+
- ▁CHILPANCINGO
|
571 |
+
- ▁GABRIEL
|
572 |
+
- ▁QUINIENTO
|
573 |
+
- ▁RAÚL
|
574 |
+
- ▁SEVERIAN
|
575 |
+
- ▁TUMBADA
|
576 |
+
- ▁MALINCHI
|
577 |
+
- ▁PRIMU
|
578 |
+
- ▁MORAL
|
579 |
+
- ▁AGOSTO
|
580 |
+
- ▁CENTÍMETRO
|
581 |
+
- ▁FIRMA
|
582 |
+
- ▁HUEHUETÁN
|
583 |
+
- ▁MANGUERA
|
584 |
+
- ▁MEDI
|
585 |
+
- ▁MUERT
|
586 |
+
- ▁SALAZAR
|
587 |
+
- ▁VIERNI
|
588 |
+
- LILL
|
589 |
+
- ▁LL
|
590 |
+
- '-'
|
591 |
+
- ▁CAMPESINO
|
592 |
+
- ▁CIVIL
|
593 |
+
- ▁COMISARIADO
|
594 |
+
- )
|
595 |
+
- (
|
596 |
+
- Ã
|
597 |
+
- ‘
|
598 |
+
- ¿
|
599 |
+
- Ü
|
600 |
+
- ¡
|
601 |
+
- Q
|
602 |
+
- F
|
603 |
+
- Á
|
604 |
+
- P
|
605 |
+
- Ÿ
|
606 |
+
- W
|
607 |
+
- Ý
|
608 |
+
- <sos/eos>
|
609 |
+
init: xavier_uniform
|
610 |
+
input_size: null
|
611 |
+
ctc_conf:
|
612 |
+
dropout_rate: 0.0
|
613 |
+
ctc_type: builtin
|
614 |
+
reduce: true
|
615 |
+
ignore_nan_grad: true
|
616 |
+
model_conf:
|
617 |
+
ctc_weight: 0.3
|
618 |
+
lsm_weight: 0.1
|
619 |
+
length_normalized_loss: false
|
620 |
+
use_preprocessor: true
|
621 |
+
token_type: bpe
|
622 |
+
bpemodel: data/token_list/bpe_unigram500/bpe.model
|
623 |
+
non_linguistic_symbols: null
|
624 |
+
cleaner: null
|
625 |
+
g2p: null
|
626 |
+
speech_volume_normalize: null
|
627 |
+
rir_scp: null
|
628 |
+
rir_apply_prob: 1.0
|
629 |
+
noise_scp: null
|
630 |
+
noise_apply_prob: 1.0
|
631 |
+
noise_db_range: '13_15'
|
632 |
+
frontend: default
|
633 |
+
frontend_conf:
|
634 |
+
fs: 16k
|
635 |
+
specaug: specaug
|
636 |
+
specaug_conf:
|
637 |
+
apply_time_warp: true
|
638 |
+
time_warp_window: 5
|
639 |
+
time_warp_mode: bicubic
|
640 |
+
apply_freq_mask: true
|
641 |
+
freq_mask_width_range:
|
642 |
+
- 0
|
643 |
+
- 30
|
644 |
+
num_freq_mask: 2
|
645 |
+
apply_time_mask: true
|
646 |
+
time_mask_width_range:
|
647 |
+
- 0
|
648 |
+
- 40
|
649 |
+
num_time_mask: 2
|
650 |
+
normalize: global_mvn
|
651 |
+
normalize_conf:
|
652 |
+
stats_file: exp/asr_stats_raw_bpe500/train/feats_stats.npz
|
653 |
+
preencoder: null
|
654 |
+
preencoder_conf: {}
|
655 |
+
encoder: transformer
|
656 |
+
encoder_conf:
|
657 |
+
input_layer: conv2d
|
658 |
+
num_blocks: 12
|
659 |
+
linear_units: 2048
|
660 |
+
dropout_rate: 0.1
|
661 |
+
output_size: 512
|
662 |
+
attention_heads: 4
|
663 |
+
attention_dropout_rate: 0.0
|
664 |
+
postencoder: null
|
665 |
+
postencoder_conf: {}
|
666 |
+
decoder: transformer
|
667 |
+
decoder_conf:
|
668 |
+
input_layer: embed
|
669 |
+
num_blocks: 6
|
670 |
+
linear_units: 2048
|
671 |
+
dropout_rate: 0.1
|
672 |
+
required:
|
673 |
+
- output_dir
|
674 |
+
- token_list
|
675 |
+
version: 0.10.4a1
|
676 |
+
distributed: false
|
exp/asr_train_asr_transformer_specaug_raw_bpe500/images/acc.png
ADDED
exp/asr_train_asr_transformer_specaug_raw_bpe500/images/backward_time.png
ADDED
exp/asr_train_asr_transformer_specaug_raw_bpe500/images/cer.png
ADDED
exp/asr_train_asr_transformer_specaug_raw_bpe500/images/cer_ctc.png
ADDED
exp/asr_train_asr_transformer_specaug_raw_bpe500/images/forward_time.png
ADDED
exp/asr_train_asr_transformer_specaug_raw_bpe500/images/gpu_max_cached_mem_GB.png
ADDED
exp/asr_train_asr_transformer_specaug_raw_bpe500/images/iter_time.png
ADDED
exp/asr_train_asr_transformer_specaug_raw_bpe500/images/loss.png
ADDED
exp/asr_train_asr_transformer_specaug_raw_bpe500/images/loss_att.png
ADDED
exp/asr_train_asr_transformer_specaug_raw_bpe500/images/loss_ctc.png
ADDED
exp/asr_train_asr_transformer_specaug_raw_bpe500/images/optim0_lr0.png
ADDED
exp/asr_train_asr_transformer_specaug_raw_bpe500/images/optim_step_time.png
ADDED
exp/asr_train_asr_transformer_specaug_raw_bpe500/images/train_time.png
ADDED
exp/asr_train_asr_transformer_specaug_raw_bpe500/images/wer.png
ADDED
meta.yaml
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
espnet: 0.10.5a1
|
2 |
+
files:
|
3 |
+
asr_model_file: exp/asr_train_asr_transformer_specaug_raw_bpe500/56epoch.pth
|
4 |
+
python: "3.9.7 (default, Sep 16 2021, 13:09:58) \n[GCC 7.5.0]"
|
5 |
+
timestamp: 1640102337.378326
|
6 |
+
torch: 1.9.0
|
7 |
+
yaml_files:
|
8 |
+
asr_train_config: exp/asr_train_asr_transformer_specaug_raw_bpe500/config.yaml
|