Siddhant
commited on
Commit
•
b046f80
1
Parent(s):
c1d6237
Update model
Browse files- README.md +815 -0
- data/en_token_list/bpe_unigram500/bpe.model +3 -0
- exp/asr_train_asr2_hubert_lr0.002_raw_en_bpe500/RESULTS.md +38 -0
- exp/asr_train_asr2_hubert_lr0.002_raw_en_bpe500/config.yaml +709 -0
- exp/asr_train_asr2_hubert_lr0.002_raw_en_bpe500/images/acc.png +0 -0
- exp/asr_train_asr2_hubert_lr0.002_raw_en_bpe500/images/backward_time.png +0 -0
- exp/asr_train_asr2_hubert_lr0.002_raw_en_bpe500/images/cer.png +0 -0
- exp/asr_train_asr2_hubert_lr0.002_raw_en_bpe500/images/cer_ctc.png +0 -0
- exp/asr_train_asr2_hubert_lr0.002_raw_en_bpe500/images/forward_time.png +0 -0
- exp/asr_train_asr2_hubert_lr0.002_raw_en_bpe500/images/gpu_max_cached_mem_GB.png +0 -0
- exp/asr_train_asr2_hubert_lr0.002_raw_en_bpe500/images/iter_time.png +0 -0
- exp/asr_train_asr2_hubert_lr0.002_raw_en_bpe500/images/loss.png +0 -0
- exp/asr_train_asr2_hubert_lr0.002_raw_en_bpe500/images/loss_att.png +0 -0
- exp/asr_train_asr2_hubert_lr0.002_raw_en_bpe500/images/loss_ctc.png +0 -0
- exp/asr_train_asr2_hubert_lr0.002_raw_en_bpe500/images/optim0_lr0.png +0 -0
- exp/asr_train_asr2_hubert_lr0.002_raw_en_bpe500/images/optim_step_time.png +0 -0
- exp/asr_train_asr2_hubert_lr0.002_raw_en_bpe500/images/train_time.png +0 -0
- exp/asr_train_asr2_hubert_lr0.002_raw_en_bpe500/images/wer.png +0 -0
- exp/asr_train_asr2_hubert_lr0.002_raw_en_bpe500/valid.acc.ave_10best.pth +3 -0
- meta.yaml +8 -0
README.md
ADDED
@@ -0,0 +1,815 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- espnet
|
4 |
+
- audio
|
5 |
+
- automatic-speech-recognition
|
6 |
+
language: en
|
7 |
+
datasets:
|
8 |
+
- stop
|
9 |
+
license: cc-by-4.0
|
10 |
+
---
|
11 |
+
|
12 |
+
## ESPnet2 ASR model
|
13 |
+
|
14 |
+
### `espnet/stop_hubert_slu_raw_en_bpe500`
|
15 |
+
|
16 |
+
This model was trained by Siddhant using stop recipe in [espnet](https://github.com/espnet/espnet/).
|
17 |
+
|
18 |
+
### Demo: How to use in ESPnet2
|
19 |
+
|
20 |
+
```bash
|
21 |
+
cd espnet
|
22 |
+
git checkout 11890fdd9dd872edc50ce8eb7660d746c6ee160e
|
23 |
+
pip install -e .
|
24 |
+
cd egs2/stop/asr3
|
25 |
+
./run.sh --skip_data_prep false --skip_train true --download_model espnet/stop_hubert_slu_raw_en_bpe500
|
26 |
+
```
|
27 |
+
|
28 |
+
<!-- Generated by scripts/utils/show_asr_result.sh -->
|
29 |
+
# RESULTS
|
30 |
+
## Environments
|
31 |
+
- date: `Sun Dec 25 13:33:10 EST 2022`
|
32 |
+
- python version: `3.9.5 (default, Jun 4 2021, 12:28:51) [GCC 7.5.0]`
|
33 |
+
- espnet version: `espnet 202205`
|
34 |
+
- pytorch version: `pytorch 1.13.0+cu116`
|
35 |
+
- Git hash: `11890fdd9dd872edc50ce8eb7660d746c6ee160e`
|
36 |
+
- Commit date: `Sat Jun 18 17:05:39 2022 -0400`
|
37 |
+
|
38 |
+
## asr_train_asr2_hubert_lr0.002_raw_en_bpe500
|
39 |
+
### WER
|
40 |
+
|
41 |
+
|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
|
42 |
+
|---|---|---|---|---|---|---|---|---|
|
43 |
+
|decode_asr_asr_model_valid.acc.ave_10best/test|75636|728701|93.9|3.2|2.9|3.1|9.1|29.8|
|
44 |
+
|decode_asr_asr_model_valid.acc.ave_10best/valid|33384|322094|0.0|0.0|100.0|0.0|100.0|100.0|
|
45 |
+
|inference_asr_model_valid.acc.ave_10best/test|75636|728701|93.9|3.3|2.8|3.2|9.4|30.6|
|
46 |
+
|inference_asr_model_valid.acc.ave_10best/valid|33384|322094|0.0|0.0|100.0|0.0|100.0|100.0|
|
47 |
+
|
48 |
+
### CER
|
49 |
+
|
50 |
+
|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
|
51 |
+
|---|---|---|---|---|---|---|---|---|
|
52 |
+
|decode_asr_asr_model_valid.acc.ave_10best/test|75636|5745269|95.9|0.9|3.2|3.2|7.3|29.8|
|
53 |
+
|decode_asr_asr_model_valid.acc.ave_10best/valid|33384|2537594|0.0|0.0|100.0|0.0|100.0|100.0|
|
54 |
+
|inference_asr_model_valid.acc.ave_10best/test|75636|5745269|95.9|1.0|3.1|3.3|7.4|30.6|
|
55 |
+
|inference_asr_model_valid.acc.ave_10best/valid|33384|2537594|0.0|0.0|100.0|0.0|100.0|100.0|
|
56 |
+
|
57 |
+
### TER
|
58 |
+
|
59 |
+
|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
|
60 |
+
|---|---|---|---|---|---|---|---|---|
|
61 |
+
|decode_asr_asr_model_valid.acc.ave_10best/test|75636|2091389|95.1|1.5|3.4|3.1|8.0|29.8|
|
62 |
+
|decode_asr_asr_model_valid.acc.ave_10best/valid|33384|921077|0.0|0.0|100.0|0.0|100.0|100.0|
|
63 |
+
|inference_asr_model_valid.acc.ave_10best/test|75636|2091389|95.2|1.5|3.3|3.3|8.1|30.6|
|
64 |
+
|inference_asr_model_valid.acc.ave_10best/valid|33384|921077|0.0|0.0|100.0|0.0|100.0|100.0|
|
65 |
+
|
66 |
+
## ASR config
|
67 |
+
|
68 |
+
<details><summary>expand</summary>
|
69 |
+
|
70 |
+
```
|
71 |
+
config: conf/train_asr2_hubert_lr0.002.yaml
|
72 |
+
print_config: false
|
73 |
+
log_level: INFO
|
74 |
+
dry_run: false
|
75 |
+
iterator_type: sequence
|
76 |
+
output_dir: exp/asr_train_asr2_hubert_lr0.002_raw_en_bpe500
|
77 |
+
ngpu: 1
|
78 |
+
seed: 0
|
79 |
+
num_workers: 1
|
80 |
+
num_att_plot: 3
|
81 |
+
dist_backend: nccl
|
82 |
+
dist_init_method: env://
|
83 |
+
dist_world_size: 4
|
84 |
+
dist_rank: 0
|
85 |
+
local_rank: 0
|
86 |
+
dist_master_addr: localhost
|
87 |
+
dist_master_port: 57197
|
88 |
+
dist_launcher: null
|
89 |
+
multiprocessing_distributed: true
|
90 |
+
unused_parameters: false
|
91 |
+
sharded_ddp: false
|
92 |
+
cudnn_enabled: true
|
93 |
+
cudnn_benchmark: false
|
94 |
+
cudnn_deterministic: true
|
95 |
+
collect_stats: false
|
96 |
+
write_collected_feats: false
|
97 |
+
max_epoch: 50
|
98 |
+
patience: null
|
99 |
+
val_scheduler_criterion:
|
100 |
+
- valid
|
101 |
+
- loss
|
102 |
+
early_stopping_criterion:
|
103 |
+
- valid
|
104 |
+
- loss
|
105 |
+
- min
|
106 |
+
best_model_criterion:
|
107 |
+
- - valid
|
108 |
+
- acc
|
109 |
+
- max
|
110 |
+
keep_nbest_models: 10
|
111 |
+
nbest_averaging_interval: 0
|
112 |
+
grad_clip: 5.0
|
113 |
+
grad_clip_type: 2.0
|
114 |
+
grad_noise: false
|
115 |
+
accum_grad: 1
|
116 |
+
no_forward_run: false
|
117 |
+
resume: true
|
118 |
+
train_dtype: float32
|
119 |
+
use_amp: false
|
120 |
+
log_interval: null
|
121 |
+
use_matplotlib: true
|
122 |
+
use_tensorboard: true
|
123 |
+
use_wandb: false
|
124 |
+
wandb_project: null
|
125 |
+
wandb_id: null
|
126 |
+
wandb_entity: null
|
127 |
+
wandb_name: null
|
128 |
+
wandb_model_log_interval: -1
|
129 |
+
detect_anomaly: false
|
130 |
+
pretrain_path: null
|
131 |
+
init_param: []
|
132 |
+
ignore_init_mismatch: false
|
133 |
+
freeze_param:
|
134 |
+
- frontend.upstream
|
135 |
+
num_iters_per_epoch: null
|
136 |
+
batch_size: 128
|
137 |
+
valid_batch_size: null
|
138 |
+
batch_bins: 1000000
|
139 |
+
valid_batch_bins: null
|
140 |
+
train_shape_file:
|
141 |
+
- exp/asr_stats_raw_en_bpe500/train/speech_shape
|
142 |
+
- exp/asr_stats_raw_en_bpe500/train/text_shape.bpe
|
143 |
+
valid_shape_file:
|
144 |
+
- exp/asr_stats_raw_en_bpe500/valid/speech_shape
|
145 |
+
- exp/asr_stats_raw_en_bpe500/valid/text_shape.bpe
|
146 |
+
batch_type: folded
|
147 |
+
valid_batch_type: null
|
148 |
+
fold_length:
|
149 |
+
- 80000
|
150 |
+
- 150
|
151 |
+
sort_in_batch: descending
|
152 |
+
sort_batch: descending
|
153 |
+
multiple_iterator: false
|
154 |
+
chunk_length: 500
|
155 |
+
chunk_shift_ratio: 0.5
|
156 |
+
num_cache_chunks: 1024
|
157 |
+
train_data_path_and_name_and_type:
|
158 |
+
- - dump/raw/train/wav.scp
|
159 |
+
- speech
|
160 |
+
- sound
|
161 |
+
- - dump/raw/train/text
|
162 |
+
- text
|
163 |
+
- text
|
164 |
+
valid_data_path_and_name_and_type:
|
165 |
+
- - dump/raw/valid/wav.scp
|
166 |
+
- speech
|
167 |
+
- sound
|
168 |
+
- - dump/raw/valid/text
|
169 |
+
- text
|
170 |
+
- text
|
171 |
+
allow_variable_data_keys: false
|
172 |
+
max_cache_size: 0.0
|
173 |
+
max_cache_fd: 32
|
174 |
+
valid_max_cache_size: null
|
175 |
+
optim: adam
|
176 |
+
optim_conf:
|
177 |
+
lr: 0.0004
|
178 |
+
weight_decay: 1.0e-06
|
179 |
+
scheduler: warmuplr
|
180 |
+
scheduler_conf:
|
181 |
+
warmup_steps: 25000
|
182 |
+
token_list:
|
183 |
+
- <blank>
|
184 |
+
- <unk>
|
185 |
+
- ▁[
|
186 |
+
- ':'
|
187 |
+
- ▁]
|
188 |
+
- _
|
189 |
+
- SL
|
190 |
+
- IN
|
191 |
+
- GET
|
192 |
+
- S
|
193 |
+
- TIME
|
194 |
+
- DATE
|
195 |
+
- ▁THE
|
196 |
+
- ▁TO
|
197 |
+
- ▁FOR
|
198 |
+
- ▁
|
199 |
+
- E
|
200 |
+
- LOCATION
|
201 |
+
- A
|
202 |
+
- WEATHER
|
203 |
+
- O
|
204 |
+
- ▁ME
|
205 |
+
- MUSIC
|
206 |
+
- ▁MY
|
207 |
+
- CREATE
|
208 |
+
- ALARM
|
209 |
+
- Y
|
210 |
+
- D
|
211 |
+
- ▁I
|
212 |
+
- T
|
213 |
+
- ▁AT
|
214 |
+
- I
|
215 |
+
- ��A
|
216 |
+
- TIMER
|
217 |
+
- ▁IS
|
218 |
+
- U
|
219 |
+
- ▁IN
|
220 |
+
- ▁ON
|
221 |
+
- EVENT
|
222 |
+
- M
|
223 |
+
- ▁TIMER
|
224 |
+
- TODO
|
225 |
+
- REMINDER
|
226 |
+
- R
|
227 |
+
- ▁PM
|
228 |
+
- P
|
229 |
+
- ING
|
230 |
+
- ▁WHAT
|
231 |
+
- ▁THIS
|
232 |
+
- ▁TODAY
|
233 |
+
- ▁AM
|
234 |
+
- N
|
235 |
+
- ▁ALARM
|
236 |
+
- ▁SET
|
237 |
+
- NT
|
238 |
+
- METHOD
|
239 |
+
- ▁TOMORROW
|
240 |
+
- ER
|
241 |
+
- TYPE
|
242 |
+
- B
|
243 |
+
- ATTRIBUTE
|
244 |
+
- DESTINATION
|
245 |
+
- ▁MINUTES
|
246 |
+
- REMINDED
|
247 |
+
- PERSON
|
248 |
+
- L
|
249 |
+
- ▁HOW
|
250 |
+
- NAME
|
251 |
+
- K
|
252 |
+
- ▁FIVE
|
253 |
+
- ▁BE
|
254 |
+
- ▁'
|
255 |
+
- G
|
256 |
+
- ▁NEXT
|
257 |
+
- 'ON'
|
258 |
+
- ▁IT
|
259 |
+
- MESSAGE
|
260 |
+
- H
|
261 |
+
- ▁WILL
|
262 |
+
- ▁S
|
263 |
+
- ▁WEEK
|
264 |
+
- ST
|
265 |
+
- C
|
266 |
+
- INFO
|
267 |
+
- EN
|
268 |
+
- CATEGORY
|
269 |
+
- TRAFFIC
|
270 |
+
- ▁F
|
271 |
+
- LE
|
272 |
+
- ▁AND
|
273 |
+
- AR
|
274 |
+
- SEND
|
275 |
+
- RE
|
276 |
+
- ▁P
|
277 |
+
- ▁D
|
278 |
+
- ▁FROM
|
279 |
+
- RECIPIE
|
280 |
+
- PLAY
|
281 |
+
- ▁DO
|
282 |
+
- ▁TRAFFIC
|
283 |
+
- AN
|
284 |
+
- ▁AN
|
285 |
+
- AL
|
286 |
+
- ▁SIX
|
287 |
+
- ▁SONG
|
288 |
+
- ▁ALL
|
289 |
+
- ▁UP
|
290 |
+
- CONTENT
|
291 |
+
- ▁REMINDER
|
292 |
+
- ▁WEEKEND
|
293 |
+
- ▁REMIND
|
294 |
+
- ▁OF
|
295 |
+
- ▁T
|
296 |
+
- RA
|
297 |
+
- ▁WEATHER
|
298 |
+
- ▁SEVEN
|
299 |
+
- ▁PLEASE
|
300 |
+
- ▁RE
|
301 |
+
- ▁TONIGHT
|
302 |
+
- EXACT
|
303 |
+
- ▁EIGHT
|
304 |
+
- ▁W
|
305 |
+
- W
|
306 |
+
- ▁TEN
|
307 |
+
- F
|
308 |
+
- SOURCE
|
309 |
+
- ▁TIME
|
310 |
+
- ESTIMATED
|
311 |
+
- RECURRING
|
312 |
+
- TH
|
313 |
+
- DELETE
|
314 |
+
- VE
|
315 |
+
- ▁NEW
|
316 |
+
- LL
|
317 |
+
- ▁EVERY
|
318 |
+
- ▁PLAY
|
319 |
+
- ES
|
320 |
+
- ▁THIRTY
|
321 |
+
- ▁GET
|
322 |
+
- ▁RAIN
|
323 |
+
- CK
|
324 |
+
- ▁TWO
|
325 |
+
- ▁C
|
326 |
+
- ▁CO
|
327 |
+
- ▁ARE
|
328 |
+
- ▁MESSAGE
|
329 |
+
- RI
|
330 |
+
- ▁G
|
331 |
+
- ▁MORNING
|
332 |
+
- CONTACT
|
333 |
+
- ▁CAN
|
334 |
+
- ▁NOW
|
335 |
+
- ▁THREE
|
336 |
+
- ▁THERE
|
337 |
+
- ET
|
338 |
+
- ▁MUSIC
|
339 |
+
- TER
|
340 |
+
- ▁TAKE
|
341 |
+
- IC
|
342 |
+
- CH
|
343 |
+
- ▁J
|
344 |
+
- V
|
345 |
+
- ED
|
346 |
+
- ▁FOUR
|
347 |
+
- DURATION
|
348 |
+
- LY
|
349 |
+
- ▁E
|
350 |
+
- ▁FRIDAY
|
351 |
+
- UR
|
352 |
+
- ▁YOU
|
353 |
+
- ▁ANY
|
354 |
+
- ▁NINE
|
355 |
+
- ▁GO
|
356 |
+
- UNSUPPORTED
|
357 |
+
- OR
|
358 |
+
- ▁SHOW
|
359 |
+
- ▁O
|
360 |
+
- ▁BA
|
361 |
+
- ▁PA
|
362 |
+
- ▁LONG
|
363 |
+
- AT
|
364 |
+
- ▁ONE
|
365 |
+
- ND
|
366 |
+
- ▁MA
|
367 |
+
- ▁ST
|
368 |
+
- ▁GOING
|
369 |
+
- ▁LIKE
|
370 |
+
- ▁ALARMS
|
371 |
+
- ▁BY
|
372 |
+
- ▁THAT
|
373 |
+
- ▁TWENTY
|
374 |
+
- ▁DAY
|
375 |
+
- ▁CH
|
376 |
+
- ▁MONTH
|
377 |
+
- ▁K
|
378 |
+
- ▁SH
|
379 |
+
- UPDATE
|
380 |
+
- ▁MONDAY
|
381 |
+
- CE
|
382 |
+
- IT
|
383 |
+
- IL
|
384 |
+
- AMOUNT
|
385 |
+
- ▁SATURDAY
|
386 |
+
- ▁BR
|
387 |
+
- ▁NEED
|
388 |
+
- ▁WORK
|
389 |
+
- ID
|
390 |
+
- ▁DRIVE
|
391 |
+
- LA
|
392 |
+
- ▁MO
|
393 |
+
- ▁HAVE
|
394 |
+
- ▁TUESDAY
|
395 |
+
- ▁TELL
|
396 |
+
- IR
|
397 |
+
- HA
|
398 |
+
- ''''
|
399 |
+
- ▁IF
|
400 |
+
- HOME
|
401 |
+
- ▁HE
|
402 |
+
- ▁LO
|
403 |
+
- ▁LA
|
404 |
+
- ▁WHEN
|
405 |
+
- LO
|
406 |
+
- ▁TH
|
407 |
+
- ▁REMINDERS
|
408 |
+
- IE
|
409 |
+
- DISTANCE
|
410 |
+
- ▁WE
|
411 |
+
- ▁SA
|
412 |
+
- ▁HOUR
|
413 |
+
- OULD
|
414 |
+
- NE
|
415 |
+
- DEPARTURE
|
416 |
+
- ▁HI
|
417 |
+
- ▁LI
|
418 |
+
- ARTIST
|
419 |
+
- Z
|
420 |
+
- TRAVEL
|
421 |
+
- ▁OUT
|
422 |
+
- PAUSE
|
423 |
+
- EST
|
424 |
+
- ARRIVAL
|
425 |
+
- ▁CANCEL
|
426 |
+
- ▁MI
|
427 |
+
- ▁OFF
|
428 |
+
- ▁FIFTEEN
|
429 |
+
- POINT
|
430 |
+
- ▁SNOW
|
431 |
+
- NA
|
432 |
+
- EL
|
433 |
+
- ▁EVENTS
|
434 |
+
- ▁CA
|
435 |
+
- ▁SUNDAY
|
436 |
+
- ▁LEAVE
|
437 |
+
- TRACK
|
438 |
+
- ▁SEND
|
439 |
+
- ▁DELETE
|
440 |
+
- ▁APPOINTMENT
|
441 |
+
- ▁BO
|
442 |
+
- RDINAL
|
443 |
+
- ▁MAKE
|
444 |
+
- ▁NEAR
|
445 |
+
- ▁BEFORE
|
446 |
+
- GE
|
447 |
+
- ▁HOME
|
448 |
+
- RELATION
|
449 |
+
- ▁V
|
450 |
+
- FR
|
451 |
+
- ▁THURSDAY
|
452 |
+
- ▁LAST
|
453 |
+
- DIRECTIONS
|
454 |
+
- ▁WEDNESDAY
|
455 |
+
- ▁START
|
456 |
+
- ▁FORECAST
|
457 |
+
- ▁YORK
|
458 |
+
- ▁RIGHT
|
459 |
+
- UM
|
460 |
+
- ▁WITH
|
461 |
+
- USE
|
462 |
+
- ▁MEETING
|
463 |
+
- UT
|
464 |
+
- LI
|
465 |
+
- ▁CHANGE
|
466 |
+
- ▁CAR
|
467 |
+
- GENRE
|
468 |
+
- ATION
|
469 |
+
- X
|
470 |
+
- ▁PICK
|
471 |
+
- ▁WANT
|
472 |
+
- ▁NIGHT
|
473 |
+
- SKIP
|
474 |
+
- ▁DE
|
475 |
+
- ▁RO
|
476 |
+
- ▁ABOUT
|
477 |
+
- MAP
|
478 |
+
- CO
|
479 |
+
- MA
|
480 |
+
- ▁HOUSE
|
481 |
+
- ▁HOT
|
482 |
+
- ▁PARTY
|
483 |
+
- ▁WA
|
484 |
+
- UNIT
|
485 |
+
- ▁HERE
|
486 |
+
- ▁SU
|
487 |
+
- ▁AFTERNOON
|
488 |
+
- ▁MUCH
|
489 |
+
- ▁MOM
|
490 |
+
- ▁TEMPERATURE
|
491 |
+
- EQUENC
|
492 |
+
- ▁ADD
|
493 |
+
- ▁SAN
|
494 |
+
- ▁HER
|
495 |
+
- ▁CONCERTS
|
496 |
+
- ▁CHRISTMAS
|
497 |
+
- ▁DINNER
|
498 |
+
- ▁MAR
|
499 |
+
- LAND
|
500 |
+
- ▁HOURS
|
501 |
+
- ▁CURRENT
|
502 |
+
- ▁TRACK
|
503 |
+
- ▁SOME
|
504 |
+
- ▁CITY
|
505 |
+
- ▁FORTY
|
506 |
+
- ATE
|
507 |
+
- ▁ROUTE
|
508 |
+
- SNOOZE
|
509 |
+
- ▁TEXT
|
510 |
+
- WORK
|
511 |
+
- ▁COLD
|
512 |
+
- RELATED
|
513 |
+
- ▁OR
|
514 |
+
- ▁NO
|
515 |
+
- Q
|
516 |
+
- ▁WAY
|
517 |
+
- WAY
|
518 |
+
- ▁MANY
|
519 |
+
- ▁BIRTHDAY
|
520 |
+
- ▁MINUTE
|
521 |
+
- ▁PLAYLIST
|
522 |
+
- ▁NOON
|
523 |
+
- ▁ROAD
|
524 |
+
- TITLE
|
525 |
+
- PATH
|
526 |
+
- ▁ASK
|
527 |
+
- NAVIGATION
|
528 |
+
- ▁LEFT
|
529 |
+
- ▁ALBUM
|
530 |
+
- ▁TURN
|
531 |
+
- ▁LATE
|
532 |
+
- ▁ELEVEN
|
533 |
+
- NEW
|
534 |
+
- ▁CELSIUS
|
535 |
+
- ▁BUY
|
536 |
+
- AVOID
|
537 |
+
- LOW
|
538 |
+
- NCE
|
539 |
+
- SEARCH
|
540 |
+
- ▁GAME
|
541 |
+
- ▁STOP
|
542 |
+
- ▁JO
|
543 |
+
- ▁FIRST
|
544 |
+
- ▁SHE
|
545 |
+
- ▁DOCTOR
|
546 |
+
- ▁BU
|
547 |
+
- PERIOD
|
548 |
+
- ▁WAKE
|
549 |
+
- CONDITION
|
550 |
+
- ▁EVENING
|
551 |
+
- RADIUS
|
552 |
+
- MODIFIE
|
553 |
+
- ▁REPEAT
|
554 |
+
- ▁SECOND
|
555 |
+
- ▁CONCERT
|
556 |
+
- ▁ANGELES
|
557 |
+
- ▁DOWNTOWN
|
558 |
+
- ▁UMBRELLA
|
559 |
+
- TEMPERATURE
|
560 |
+
- ASH
|
561 |
+
- ▁YEAR
|
562 |
+
- GROUP
|
563 |
+
- ▁DRIVING
|
564 |
+
- ▁GIVE
|
565 |
+
- ▁HUNDRED
|
566 |
+
- ▁HO
|
567 |
+
- ▁MILES
|
568 |
+
- PLAYLIST
|
569 |
+
- ADD
|
570 |
+
- RETRIEV
|
571 |
+
- ▁TWELVE
|
572 |
+
- EAD
|
573 |
+
- ▁CLASS
|
574 |
+
- ▁FREE
|
575 |
+
- PORT
|
576 |
+
- VILLE
|
577 |
+
- ▁BETWEEN
|
578 |
+
- ▁KNOW
|
579 |
+
- ▁AROUND
|
580 |
+
- ▁SCHOOL
|
581 |
+
- ▁NINETY
|
582 |
+
- PROVIDER
|
583 |
+
- SILENCE
|
584 |
+
- RESUME
|
585 |
+
- ▁LET
|
586 |
+
- TION
|
587 |
+
- ▁AUGUST
|
588 |
+
- ▁HAPPENING
|
589 |
+
- ▁AFTER
|
590 |
+
- ▁FAHRENHEIT
|
591 |
+
- ▁EX
|
592 |
+
- ▁VIDEO
|
593 |
+
- ROAD
|
594 |
+
- ▁PARK
|
595 |
+
- ▁CHICAGO
|
596 |
+
- ▁DAILY
|
597 |
+
- ▁CHECK
|
598 |
+
- ▁BEACH
|
599 |
+
- ▁WHERE
|
600 |
+
- ▁JUNE
|
601 |
+
- ▁STREET
|
602 |
+
- ▁FESTIVAL
|
603 |
+
- ▁FLORIDA
|
604 |
+
- ▁JOHN
|
605 |
+
- ▁HAS
|
606 |
+
- ▁SPOTIFY
|
607 |
+
- ▁BILL
|
608 |
+
- RESTART
|
609 |
+
- ▁HIGHWAY
|
610 |
+
- ▁SEATTLE
|
611 |
+
- J
|
612 |
+
- ▁LUNCH
|
613 |
+
- ▁LOOK
|
614 |
+
- ▁FRIEND
|
615 |
+
- ▁COMING
|
616 |
+
- ▁ALERT
|
617 |
+
- IGHT
|
618 |
+
- ▁PANDORA
|
619 |
+
- ▁HEAVY
|
620 |
+
- ▁KIDS
|
621 |
+
- ▁MOVIE
|
622 |
+
- ▁SOUTH
|
623 |
+
- REACT
|
624 |
+
- ▁CONSTRUCTION
|
625 |
+
- PREVIOUS
|
626 |
+
- ▁ORLANDO
|
627 |
+
- ▁OVER
|
628 |
+
- ▁MIAMI
|
629 |
+
- REACTION
|
630 |
+
- ▁ATLANTA
|
631 |
+
- ▁ACCIDENT
|
632 |
+
- ▁COUNTRY
|
633 |
+
- ▁NORTH
|
634 |
+
- ▁LIGHT
|
635 |
+
- RADIO
|
636 |
+
- ▁READ
|
637 |
+
- ▁FAMILY
|
638 |
+
- ▁AIRPORT
|
639 |
+
- ▁EXPECT
|
640 |
+
- ▁DEGREE
|
641 |
+
- ▁PRO
|
642 |
+
- ▁PARTIES
|
643 |
+
- ▁FIFTY
|
644 |
+
- ▁HIGH
|
645 |
+
- ▁PLAN
|
646 |
+
- ▁FOOD
|
647 |
+
- ▁WARM
|
648 |
+
- ▁SUNNY
|
649 |
+
- ▁VEGAS
|
650 |
+
- ▁HOLIDAY
|
651 |
+
- ▁SCHEDULE
|
652 |
+
- ▁STORM
|
653 |
+
- ▁FIFTH
|
654 |
+
- ▁BOSTON
|
655 |
+
- ▁FRANCISCO
|
656 |
+
- ▁LONDON
|
657 |
+
- ATTENDEE
|
658 |
+
- ▁JULY
|
659 |
+
- ▁WALK
|
660 |
+
- ▁COMMUTE
|
661 |
+
- ▁CLEAN
|
662 |
+
- ▁DENTIST
|
663 |
+
- TOWN
|
664 |
+
- ▁AGAIN
|
665 |
+
- ▁DALLAS
|
666 |
+
- ▁PORTLAND
|
667 |
+
- ▁SEPTEMBER
|
668 |
+
- ▁ARRIVE
|
669 |
+
- ▁SISTER
|
670 |
+
- ▁HOUSTON
|
671 |
+
- Ã
|
672 |
+
- É
|
673 |
+
- Í
|
674 |
+
- '*'
|
675 |
+
- Á
|
676 |
+
- Ç
|
677 |
+
- Ó
|
678 |
+
- ']'
|
679 |
+
- '['
|
680 |
+
- Ú
|
681 |
+
- Ü
|
682 |
+
- <sos/eos>
|
683 |
+
transcript_token_list: null
|
684 |
+
two_pass: false
|
685 |
+
pre_postencoder_norm: false
|
686 |
+
init: null
|
687 |
+
input_size: null
|
688 |
+
ctc_conf:
|
689 |
+
dropout_rate: 0.0
|
690 |
+
ctc_type: builtin
|
691 |
+
reduce: true
|
692 |
+
ignore_nan_grad: true
|
693 |
+
joint_net_conf: null
|
694 |
+
use_preprocessor: true
|
695 |
+
token_type: bpe
|
696 |
+
bpemodel: data/en_token_list/bpe_unigram500/bpe.model
|
697 |
+
non_linguistic_symbols: null
|
698 |
+
cleaner: null
|
699 |
+
g2p: null
|
700 |
+
speech_volume_normalize: null
|
701 |
+
rir_scp: null
|
702 |
+
rir_apply_prob: 1.0
|
703 |
+
noise_scp: null
|
704 |
+
noise_apply_prob: 1.0
|
705 |
+
noise_db_range: '13_15'
|
706 |
+
frontend: s3prl
|
707 |
+
frontend_conf:
|
708 |
+
frontend_conf:
|
709 |
+
upstream: hubert_large_ll60k
|
710 |
+
download_dir: ./hub
|
711 |
+
multilayer_feature: true
|
712 |
+
fs: 16k
|
713 |
+
specaug: specaug
|
714 |
+
specaug_conf:
|
715 |
+
apply_time_warp: true
|
716 |
+
time_warp_window: 5
|
717 |
+
time_warp_mode: bicubic
|
718 |
+
apply_freq_mask: true
|
719 |
+
freq_mask_width_range:
|
720 |
+
- 0
|
721 |
+
- 30
|
722 |
+
num_freq_mask: 2
|
723 |
+
apply_time_mask: true
|
724 |
+
time_mask_width_range:
|
725 |
+
- 0
|
726 |
+
- 40
|
727 |
+
num_time_mask: 2
|
728 |
+
normalize: utterance_mvn
|
729 |
+
normalize_conf: {}
|
730 |
+
model: espnet
|
731 |
+
model_conf:
|
732 |
+
ctc_weight: 0.3
|
733 |
+
lsm_weight: 0.1
|
734 |
+
length_normalized_loss: false
|
735 |
+
extract_feats_in_collect_stats: false
|
736 |
+
preencoder: linear
|
737 |
+
preencoder_conf:
|
738 |
+
input_size: 1024
|
739 |
+
output_size: 80
|
740 |
+
encoder: conformer
|
741 |
+
encoder_conf:
|
742 |
+
output_size: 512
|
743 |
+
attention_heads: 8
|
744 |
+
linear_units: 2048
|
745 |
+
num_blocks: 12
|
746 |
+
dropout_rate: 0.1
|
747 |
+
positional_dropout_rate: 0.1
|
748 |
+
attention_dropout_rate: 0.1
|
749 |
+
input_layer: conv2d2
|
750 |
+
normalize_before: true
|
751 |
+
macaron_style: true
|
752 |
+
rel_pos_type: latest
|
753 |
+
pos_enc_layer_type: rel_pos
|
754 |
+
selfattention_layer_type: rel_selfattn
|
755 |
+
activation_type: swish
|
756 |
+
use_cnn_module: true
|
757 |
+
cnn_module_kernel: 31
|
758 |
+
postencoder: null
|
759 |
+
postencoder_conf: {}
|
760 |
+
deliberationencoder: null
|
761 |
+
deliberationencoder_conf: {}
|
762 |
+
decoder: transformer
|
763 |
+
decoder_conf:
|
764 |
+
attention_heads: 8
|
765 |
+
linear_units: 2048
|
766 |
+
num_blocks: 6
|
767 |
+
dropout_rate: 0.1
|
768 |
+
positional_dropout_rate: 0.1
|
769 |
+
self_attention_dropout_rate: 0.1
|
770 |
+
src_attention_dropout_rate: 0.1
|
771 |
+
decoder2: null
|
772 |
+
decoder2_conf: {}
|
773 |
+
postdecoder: null
|
774 |
+
postdecoder_conf: {}
|
775 |
+
required:
|
776 |
+
- output_dir
|
777 |
+
- token_list
|
778 |
+
version: '202205'
|
779 |
+
distributed: true
|
780 |
+
```
|
781 |
+
|
782 |
+
</details>
|
783 |
+
|
784 |
+
|
785 |
+
|
786 |
+
### Citing ESPnet
|
787 |
+
|
788 |
+
```BibTex
|
789 |
+
@inproceedings{watanabe2018espnet,
|
790 |
+
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},
|
791 |
+
title={{ESPnet}: End-to-End Speech Processing Toolkit},
|
792 |
+
year={2018},
|
793 |
+
booktitle={Proceedings of Interspeech},
|
794 |
+
pages={2207--2211},
|
795 |
+
doi={10.21437/Interspeech.2018-1456},
|
796 |
+
url={http://dx.doi.org/10.21437/Interspeech.2018-1456}
|
797 |
+
}
|
798 |
+
|
799 |
+
|
800 |
+
|
801 |
+
|
802 |
+
```
|
803 |
+
|
804 |
+
or arXiv:
|
805 |
+
|
806 |
+
```bibtex
|
807 |
+
@misc{watanabe2018espnet,
|
808 |
+
title={ESPnet: End-to-End Speech Processing Toolkit},
|
809 |
+
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},
|
810 |
+
year={2018},
|
811 |
+
eprint={1804.00015},
|
812 |
+
archivePrefix={arXiv},
|
813 |
+
primaryClass={cs.CL}
|
814 |
+
}
|
815 |
+
```
|
data/en_token_list/bpe_unigram500/bpe.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:27d24b5d25713fdcb0697dfe5f78aaa56d67057bce490b8b0a8641ac63385496
|
3 |
+
size 245232
|
exp/asr_train_asr2_hubert_lr0.002_raw_en_bpe500/RESULTS.md
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
<!-- Generated by scripts/utils/show_asr_result.sh -->
|
2 |
+
# RESULTS
|
3 |
+
## Environments
|
4 |
+
- date: `Sun Dec 25 13:33:10 EST 2022`
|
5 |
+
- python version: `3.9.5 (default, Jun 4 2021, 12:28:51) [GCC 7.5.0]`
|
6 |
+
- espnet version: `espnet 202205`
|
7 |
+
- pytorch version: `pytorch 1.13.0+cu116`
|
8 |
+
- Git hash: `11890fdd9dd872edc50ce8eb7660d746c6ee160e`
|
9 |
+
- Commit date: `Sat Jun 18 17:05:39 2022 -0400`
|
10 |
+
|
11 |
+
## asr_train_asr2_hubert_lr0.002_raw_en_bpe500
|
12 |
+
### WER
|
13 |
+
|
14 |
+
|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
|
15 |
+
|---|---|---|---|---|---|---|---|---|
|
16 |
+
|decode_asr_asr_model_valid.acc.ave_10best/test|75636|728701|93.9|3.2|2.9|3.1|9.1|29.8|
|
17 |
+
|decode_asr_asr_model_valid.acc.ave_10best/valid|33384|322094|0.0|0.0|100.0|0.0|100.0|100.0|
|
18 |
+
|inference_asr_model_valid.acc.ave_10best/test|75636|728701|93.9|3.3|2.8|3.2|9.4|30.6|
|
19 |
+
|inference_asr_model_valid.acc.ave_10best/valid|33384|322094|0.0|0.0|100.0|0.0|100.0|100.0|
|
20 |
+
|
21 |
+
### CER
|
22 |
+
|
23 |
+
|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
|
24 |
+
|---|---|---|---|---|---|---|---|---|
|
25 |
+
|decode_asr_asr_model_valid.acc.ave_10best/test|75636|5745269|95.9|0.9|3.2|3.2|7.3|29.8|
|
26 |
+
|decode_asr_asr_model_valid.acc.ave_10best/valid|33384|2537594|0.0|0.0|100.0|0.0|100.0|100.0|
|
27 |
+
|inference_asr_model_valid.acc.ave_10best/test|75636|5745269|95.9|1.0|3.1|3.3|7.4|30.6|
|
28 |
+
|inference_asr_model_valid.acc.ave_10best/valid|33384|2537594|0.0|0.0|100.0|0.0|100.0|100.0|
|
29 |
+
|
30 |
+
### TER
|
31 |
+
|
32 |
+
|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
|
33 |
+
|---|---|---|---|---|---|---|---|---|
|
34 |
+
|decode_asr_asr_model_valid.acc.ave_10best/test|75636|2091389|95.1|1.5|3.4|3.1|8.0|29.8|
|
35 |
+
|decode_asr_asr_model_valid.acc.ave_10best/valid|33384|921077|0.0|0.0|100.0|0.0|100.0|100.0|
|
36 |
+
|inference_asr_model_valid.acc.ave_10best/test|75636|2091389|95.2|1.5|3.3|3.3|8.1|30.6|
|
37 |
+
|inference_asr_model_valid.acc.ave_10best/valid|33384|921077|0.0|0.0|100.0|0.0|100.0|100.0|
|
38 |
+
|
exp/asr_train_asr2_hubert_lr0.002_raw_en_bpe500/config.yaml
ADDED
@@ -0,0 +1,709 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
config: conf/train_asr2_hubert_lr0.002.yaml
|
2 |
+
print_config: false
|
3 |
+
log_level: INFO
|
4 |
+
dry_run: false
|
5 |
+
iterator_type: sequence
|
6 |
+
output_dir: exp/asr_train_asr2_hubert_lr0.002_raw_en_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: 4
|
14 |
+
dist_rank: 0
|
15 |
+
local_rank: 0
|
16 |
+
dist_master_addr: localhost
|
17 |
+
dist_master_port: 57197
|
18 |
+
dist_launcher: null
|
19 |
+
multiprocessing_distributed: true
|
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: 50
|
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 |
+
- - valid
|
38 |
+
- acc
|
39 |
+
- max
|
40 |
+
keep_nbest_models: 10
|
41 |
+
nbest_averaging_interval: 0
|
42 |
+
grad_clip: 5.0
|
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 |
+
use_matplotlib: true
|
52 |
+
use_tensorboard: true
|
53 |
+
use_wandb: false
|
54 |
+
wandb_project: null
|
55 |
+
wandb_id: null
|
56 |
+
wandb_entity: null
|
57 |
+
wandb_name: null
|
58 |
+
wandb_model_log_interval: -1
|
59 |
+
detect_anomaly: false
|
60 |
+
pretrain_path: null
|
61 |
+
init_param: []
|
62 |
+
ignore_init_mismatch: false
|
63 |
+
freeze_param:
|
64 |
+
- frontend.upstream
|
65 |
+
num_iters_per_epoch: null
|
66 |
+
batch_size: 128
|
67 |
+
valid_batch_size: null
|
68 |
+
batch_bins: 1000000
|
69 |
+
valid_batch_bins: null
|
70 |
+
train_shape_file:
|
71 |
+
- exp/asr_stats_raw_en_bpe500/train/speech_shape
|
72 |
+
- exp/asr_stats_raw_en_bpe500/train/text_shape.bpe
|
73 |
+
valid_shape_file:
|
74 |
+
- exp/asr_stats_raw_en_bpe500/valid/speech_shape
|
75 |
+
- exp/asr_stats_raw_en_bpe500/valid/text_shape.bpe
|
76 |
+
batch_type: folded
|
77 |
+
valid_batch_type: null
|
78 |
+
fold_length:
|
79 |
+
- 80000
|
80 |
+
- 150
|
81 |
+
sort_in_batch: descending
|
82 |
+
sort_batch: descending
|
83 |
+
multiple_iterator: false
|
84 |
+
chunk_length: 500
|
85 |
+
chunk_shift_ratio: 0.5
|
86 |
+
num_cache_chunks: 1024
|
87 |
+
train_data_path_and_name_and_type:
|
88 |
+
- - dump/raw/train/wav.scp
|
89 |
+
- speech
|
90 |
+
- sound
|
91 |
+
- - dump/raw/train/text
|
92 |
+
- text
|
93 |
+
- text
|
94 |
+
valid_data_path_and_name_and_type:
|
95 |
+
- - dump/raw/valid/wav.scp
|
96 |
+
- speech
|
97 |
+
- sound
|
98 |
+
- - dump/raw/valid/text
|
99 |
+
- text
|
100 |
+
- text
|
101 |
+
allow_variable_data_keys: false
|
102 |
+
max_cache_size: 0.0
|
103 |
+
max_cache_fd: 32
|
104 |
+
valid_max_cache_size: null
|
105 |
+
optim: adam
|
106 |
+
optim_conf:
|
107 |
+
lr: 0.0004
|
108 |
+
weight_decay: 1.0e-06
|
109 |
+
scheduler: warmuplr
|
110 |
+
scheduler_conf:
|
111 |
+
warmup_steps: 25000
|
112 |
+
token_list:
|
113 |
+
- <blank>
|
114 |
+
- <unk>
|
115 |
+
- ▁[
|
116 |
+
- ':'
|
117 |
+
- ▁]
|
118 |
+
- _
|
119 |
+
- SL
|
120 |
+
- IN
|
121 |
+
- GET
|
122 |
+
- S
|
123 |
+
- TIME
|
124 |
+
- DATE
|
125 |
+
- ▁THE
|
126 |
+
- ▁TO
|
127 |
+
- ▁FOR
|
128 |
+
- ▁
|
129 |
+
- E
|
130 |
+
- LOCATION
|
131 |
+
- A
|
132 |
+
- WEATHER
|
133 |
+
- O
|
134 |
+
- ▁ME
|
135 |
+
- MUSIC
|
136 |
+
- ▁MY
|
137 |
+
- CREATE
|
138 |
+
- ALARM
|
139 |
+
- Y
|
140 |
+
- D
|
141 |
+
- ▁I
|
142 |
+
- T
|
143 |
+
- ▁AT
|
144 |
+
- I
|
145 |
+
- ▁A
|
146 |
+
- TIMER
|
147 |
+
- ▁IS
|
148 |
+
- U
|
149 |
+
- ▁IN
|
150 |
+
- ▁ON
|
151 |
+
- EVENT
|
152 |
+
- M
|
153 |
+
- ▁TIMER
|
154 |
+
- TODO
|
155 |
+
- REMINDER
|
156 |
+
- R
|
157 |
+
- ▁PM
|
158 |
+
- P
|
159 |
+
- ING
|
160 |
+
- ▁WHAT
|
161 |
+
- ▁THIS
|
162 |
+
- ▁TODAY
|
163 |
+
- ▁AM
|
164 |
+
- N
|
165 |
+
- ▁ALARM
|
166 |
+
- ▁SET
|
167 |
+
- NT
|
168 |
+
- METHOD
|
169 |
+
- ▁TOMORROW
|
170 |
+
- ER
|
171 |
+
- TYPE
|
172 |
+
- B
|
173 |
+
- ATTRIBUTE
|
174 |
+
- DESTINATION
|
175 |
+
- ▁MINUTES
|
176 |
+
- REMINDED
|
177 |
+
- PERSON
|
178 |
+
- L
|
179 |
+
- ▁HOW
|
180 |
+
- NAME
|
181 |
+
- K
|
182 |
+
- ▁FIVE
|
183 |
+
- ▁BE
|
184 |
+
- ▁'
|
185 |
+
- G
|
186 |
+
- ▁NEXT
|
187 |
+
- 'ON'
|
188 |
+
- ▁IT
|
189 |
+
- MESSAGE
|
190 |
+
- H
|
191 |
+
- ▁WILL
|
192 |
+
- ▁S
|
193 |
+
- ▁WEEK
|
194 |
+
- ST
|
195 |
+
- C
|
196 |
+
- INFO
|
197 |
+
- EN
|
198 |
+
- CATEGORY
|
199 |
+
- TRAFFIC
|
200 |
+
- ▁F
|
201 |
+
- LE
|
202 |
+
- ▁AND
|
203 |
+
- AR
|
204 |
+
- SEND
|
205 |
+
- RE
|
206 |
+
- ▁P
|
207 |
+
- ▁D
|
208 |
+
- ▁FROM
|
209 |
+
- RECIPIE
|
210 |
+
- PLAY
|
211 |
+
- ▁DO
|
212 |
+
- ▁TRAFFIC
|
213 |
+
- AN
|
214 |
+
- ▁AN
|
215 |
+
- AL
|
216 |
+
- ▁SIX
|
217 |
+
- ▁SONG
|
218 |
+
- ▁ALL
|
219 |
+
- ▁UP
|
220 |
+
- CONTENT
|
221 |
+
- ▁REMINDER
|
222 |
+
- ▁WEEKEND
|
223 |
+
- ▁REMIND
|
224 |
+
- ▁OF
|
225 |
+
- ▁T
|
226 |
+
- RA
|
227 |
+
- ▁WEATHER
|
228 |
+
- ▁SEVEN
|
229 |
+
- ▁PLEASE
|
230 |
+
- ▁RE
|
231 |
+
- ▁TONIGHT
|
232 |
+
- EXACT
|
233 |
+
- ▁EIGHT
|
234 |
+
- ▁W
|
235 |
+
- W
|
236 |
+
- ▁TEN
|
237 |
+
- F
|
238 |
+
- SOURCE
|
239 |
+
- ▁TIME
|
240 |
+
- ESTIMATED
|
241 |
+
- RECURRING
|
242 |
+
- TH
|
243 |
+
- DELETE
|
244 |
+
- VE
|
245 |
+
- ▁NEW
|
246 |
+
- LL
|
247 |
+
- ▁EVERY
|
248 |
+
- ▁PLAY
|
249 |
+
- ES
|
250 |
+
- ▁THIRTY
|
251 |
+
- ▁GET
|
252 |
+
- ▁RAIN
|
253 |
+
- CK
|
254 |
+
- ▁TWO
|
255 |
+
- ▁C
|
256 |
+
- ▁CO
|
257 |
+
- ▁ARE
|
258 |
+
- ▁MESSAGE
|
259 |
+
- RI
|
260 |
+
- ▁G
|
261 |
+
- ▁MORNING
|
262 |
+
- CONTACT
|
263 |
+
- ▁CAN
|
264 |
+
- ▁NOW
|
265 |
+
- ▁THREE
|
266 |
+
- ▁THERE
|
267 |
+
- ET
|
268 |
+
- ▁MUSIC
|
269 |
+
- TER
|
270 |
+
- ▁TAKE
|
271 |
+
- IC
|
272 |
+
- CH
|
273 |
+
- ▁J
|
274 |
+
- V
|
275 |
+
- ED
|
276 |
+
- ▁FOUR
|
277 |
+
- DURATION
|
278 |
+
- LY
|
279 |
+
- ▁E
|
280 |
+
- ▁FRIDAY
|
281 |
+
- UR
|
282 |
+
- ▁YOU
|
283 |
+
- ▁ANY
|
284 |
+
- ▁NINE
|
285 |
+
- ▁GO
|
286 |
+
- UNSUPPORTED
|
287 |
+
- OR
|
288 |
+
- ▁SHOW
|
289 |
+
- ▁O
|
290 |
+
- ▁BA
|
291 |
+
- ▁PA
|
292 |
+
- ▁LONG
|
293 |
+
- AT
|
294 |
+
- ▁ONE
|
295 |
+
- ND
|
296 |
+
- ▁MA
|
297 |
+
- ▁ST
|
298 |
+
- ▁GOING
|
299 |
+
- ▁LIKE
|
300 |
+
- ▁ALARMS
|
301 |
+
- ▁BY
|
302 |
+
- ▁THAT
|
303 |
+
- ▁TWENTY
|
304 |
+
- ▁DAY
|
305 |
+
- ▁CH
|
306 |
+
- ▁MONTH
|
307 |
+
- ▁K
|
308 |
+
- ▁SH
|
309 |
+
- UPDATE
|
310 |
+
- ▁MONDAY
|
311 |
+
- CE
|
312 |
+
- IT
|
313 |
+
- IL
|
314 |
+
- AMOUNT
|
315 |
+
- ▁SATURDAY
|
316 |
+
- ▁BR
|
317 |
+
- ▁NEED
|
318 |
+
- ▁WORK
|
319 |
+
- ID
|
320 |
+
- ▁DRIVE
|
321 |
+
- LA
|
322 |
+
- ▁MO
|
323 |
+
- ▁HAVE
|
324 |
+
- ▁TUESDAY
|
325 |
+
- ▁TELL
|
326 |
+
- IR
|
327 |
+
- HA
|
328 |
+
- ''''
|
329 |
+
- ▁IF
|
330 |
+
- HOME
|
331 |
+
- ▁HE
|
332 |
+
- ▁LO
|
333 |
+
- ▁LA
|
334 |
+
- ▁WHEN
|
335 |
+
- LO
|
336 |
+
- ▁TH
|
337 |
+
- ▁REMINDERS
|
338 |
+
- IE
|
339 |
+
- DISTANCE
|
340 |
+
- ▁WE
|
341 |
+
- ▁SA
|
342 |
+
- ▁HOUR
|
343 |
+
- OULD
|
344 |
+
- NE
|
345 |
+
- DEPARTURE
|
346 |
+
- ▁HI
|
347 |
+
- ▁LI
|
348 |
+
- ARTIST
|
349 |
+
- Z
|
350 |
+
- TRAVEL
|
351 |
+
- ▁OUT
|
352 |
+
- PAUSE
|
353 |
+
- EST
|
354 |
+
- ARRIVAL
|
355 |
+
- ▁CANCEL
|
356 |
+
- ▁MI
|
357 |
+
- ▁OFF
|
358 |
+
- ▁FIFTEEN
|
359 |
+
- POINT
|
360 |
+
- ▁SNOW
|
361 |
+
- NA
|
362 |
+
- EL
|
363 |
+
- ▁EVENTS
|
364 |
+
- ▁CA
|
365 |
+
- ▁SUNDAY
|
366 |
+
- ▁LEAVE
|
367 |
+
- TRACK
|
368 |
+
- ▁SEND
|
369 |
+
- ▁DELETE
|
370 |
+
- ▁APPOINTMENT
|
371 |
+
- ▁BO
|
372 |
+
- RDINAL
|
373 |
+
- ▁MAKE
|
374 |
+
- ▁NEAR
|
375 |
+
- ▁BEFORE
|
376 |
+
- GE
|
377 |
+
- ▁HOME
|
378 |
+
- RELATION
|
379 |
+
- ▁V
|
380 |
+
- FR
|
381 |
+
- ▁THURSDAY
|
382 |
+
- ▁LAST
|
383 |
+
- DIRECTIONS
|
384 |
+
- ▁WEDNESDAY
|
385 |
+
- ▁START
|
386 |
+
- ▁FORECAST
|
387 |
+
- ▁YORK
|
388 |
+
- ▁RIGHT
|
389 |
+
- UM
|
390 |
+
- ▁WITH
|
391 |
+
- USE
|
392 |
+
- ▁MEETING
|
393 |
+
- UT
|
394 |
+
- LI
|
395 |
+
- ▁CHANGE
|
396 |
+
- ▁CAR
|
397 |
+
- GENRE
|
398 |
+
- ATION
|
399 |
+
- X
|
400 |
+
- ▁PICK
|
401 |
+
- ▁WANT
|
402 |
+
- ▁NIGHT
|
403 |
+
- SKIP
|
404 |
+
- ▁DE
|
405 |
+
- ▁RO
|
406 |
+
- ▁ABOUT
|
407 |
+
- MAP
|
408 |
+
- CO
|
409 |
+
- MA
|
410 |
+
- ▁HOUSE
|
411 |
+
- ▁HOT
|
412 |
+
- ▁PARTY
|
413 |
+
- ▁WA
|
414 |
+
- UNIT
|
415 |
+
- ▁HERE
|
416 |
+
- ▁SU
|
417 |
+
- ▁AFTERNOON
|
418 |
+
- ▁MUCH
|
419 |
+
- ▁MOM
|
420 |
+
- ▁TEMPERATURE
|
421 |
+
- EQUENC
|
422 |
+
- ▁ADD
|
423 |
+
- ▁SAN
|
424 |
+
- ▁HER
|
425 |
+
- ▁CONCERTS
|
426 |
+
- ▁CHRISTMAS
|
427 |
+
- ▁DINNER
|
428 |
+
- ▁MAR
|
429 |
+
- LAND
|
430 |
+
- ▁HOURS
|
431 |
+
- ▁CURRENT
|
432 |
+
- ▁TRACK
|
433 |
+
- ▁SOME
|
434 |
+
- ▁CITY
|
435 |
+
- ▁FORTY
|
436 |
+
- ATE
|
437 |
+
- ▁ROUTE
|
438 |
+
- SNOOZE
|
439 |
+
- ▁TEXT
|
440 |
+
- WORK
|
441 |
+
- ▁COLD
|
442 |
+
- RELATED
|
443 |
+
- ▁OR
|
444 |
+
- ▁NO
|
445 |
+
- Q
|
446 |
+
- ▁WAY
|
447 |
+
- WAY
|
448 |
+
- ▁MANY
|
449 |
+
- ▁BIRTHDAY
|
450 |
+
- ▁MINUTE
|
451 |
+
- ▁PLAYLIST
|
452 |
+
- ▁NOON
|
453 |
+
- ▁ROAD
|
454 |
+
- TITLE
|
455 |
+
- PATH
|
456 |
+
- ▁ASK
|
457 |
+
- NAVIGATION
|
458 |
+
- ▁LEFT
|
459 |
+
- ▁ALBUM
|
460 |
+
- ▁TURN
|
461 |
+
- ▁LATE
|
462 |
+
- ▁ELEVEN
|
463 |
+
- NEW
|
464 |
+
- ▁CELSIUS
|
465 |
+
- ▁BUY
|
466 |
+
- AVOID
|
467 |
+
- LOW
|
468 |
+
- NCE
|
469 |
+
- SEARCH
|
470 |
+
- ▁GAME
|
471 |
+
- ▁STOP
|
472 |
+
- ▁JO
|
473 |
+
- ▁FIRST
|
474 |
+
- ▁SHE
|
475 |
+
- ▁DOCTOR
|
476 |
+
- ▁BU
|
477 |
+
- PERIOD
|
478 |
+
- ▁WAKE
|
479 |
+
- CONDITION
|
480 |
+
- ▁EVENING
|
481 |
+
- RADIUS
|
482 |
+
- MODIFIE
|
483 |
+
- ▁REPEAT
|
484 |
+
- ▁SECOND
|
485 |
+
- ▁CONCERT
|
486 |
+
- ▁ANGELES
|
487 |
+
- ▁DOWNTOWN
|
488 |
+
- ▁UMBRELLA
|
489 |
+
- TEMPERATURE
|
490 |
+
- ASH
|
491 |
+
- ▁YEAR
|
492 |
+
- GROUP
|
493 |
+
- ▁DRIVING
|
494 |
+
- ▁GIVE
|
495 |
+
- ▁HUNDRED
|
496 |
+
- ▁HO
|
497 |
+
- ▁MILES
|
498 |
+
- PLAYLIST
|
499 |
+
- ADD
|
500 |
+
- RETRIEV
|
501 |
+
- ▁TWELVE
|
502 |
+
- EAD
|
503 |
+
- ▁CLASS
|
504 |
+
- ▁FREE
|
505 |
+
- PORT
|
506 |
+
- VILLE
|
507 |
+
- ▁BETWEEN
|
508 |
+
- ▁KNOW
|
509 |
+
- ▁AROUND
|
510 |
+
- ▁SCHOOL
|
511 |
+
- ▁NINETY
|
512 |
+
- PROVIDER
|
513 |
+
- SILENCE
|
514 |
+
- RESUME
|
515 |
+
- ▁LET
|
516 |
+
- TION
|
517 |
+
- ▁AUGUST
|
518 |
+
- ▁HAPPENING
|
519 |
+
- ▁AFTER
|
520 |
+
- ▁FAHRENHEIT
|
521 |
+
- ▁EX
|
522 |
+
- ▁VIDEO
|
523 |
+
- ROAD
|
524 |
+
- ▁PARK
|
525 |
+
- ▁CHICAGO
|
526 |
+
- ▁DAILY
|
527 |
+
- ▁CHECK
|
528 |
+
- ▁BEACH
|
529 |
+
- ▁WHERE
|
530 |
+
- ▁JUNE
|
531 |
+
- ▁STREET
|
532 |
+
- ▁FESTIVAL
|
533 |
+
- ▁FLORIDA
|
534 |
+
- ▁JOHN
|
535 |
+
- ▁HAS
|
536 |
+
- ▁SPOTIFY
|
537 |
+
- ▁BILL
|
538 |
+
- RESTART
|
539 |
+
- ▁HIGHWAY
|
540 |
+
- ▁SEATTLE
|
541 |
+
- J
|
542 |
+
- ▁LUNCH
|
543 |
+
- ▁LOOK
|
544 |
+
- ▁FRIEND
|
545 |
+
- ▁COMING
|
546 |
+
- ▁ALERT
|
547 |
+
- IGHT
|
548 |
+
- ▁PANDORA
|
549 |
+
- ▁HEAVY
|
550 |
+
- ▁KIDS
|
551 |
+
- ▁MOVIE
|
552 |
+
- ▁SOUTH
|
553 |
+
- REACT
|
554 |
+
- ▁CONSTRUCTION
|
555 |
+
- PREVIOUS
|
556 |
+
- ▁ORLANDO
|
557 |
+
- ▁OVER
|
558 |
+
- ▁MIAMI
|
559 |
+
- REACTION
|
560 |
+
- ▁ATLANTA
|
561 |
+
- ▁ACCIDENT
|
562 |
+
- ▁COUNTRY
|
563 |
+
- ▁NORTH
|
564 |
+
- ▁LIGHT
|
565 |
+
- RADIO
|
566 |
+
- ▁READ
|
567 |
+
- ▁FAMILY
|
568 |
+
- ▁AIRPORT
|
569 |
+
- ▁EXPECT
|
570 |
+
- ▁DEGREE
|
571 |
+
- ▁PRO
|
572 |
+
- ▁PARTIES
|
573 |
+
- ▁FIFTY
|
574 |
+
- ▁HIGH
|
575 |
+
- ▁PLAN
|
576 |
+
- ▁FOOD
|
577 |
+
- ▁WARM
|
578 |
+
- ▁SUNNY
|
579 |
+
- ▁VEGAS
|
580 |
+
- ▁HOLIDAY
|
581 |
+
- ▁SCHEDULE
|
582 |
+
- ▁STORM
|
583 |
+
- ▁FIFTH
|
584 |
+
- ▁BOSTON
|
585 |
+
- ▁FRANCISCO
|
586 |
+
- ▁LONDON
|
587 |
+
- ATTENDEE
|
588 |
+
- ▁JULY
|
589 |
+
- ▁WALK
|
590 |
+
- ▁COMMUTE
|
591 |
+
- ▁CLEAN
|
592 |
+
- ▁DENTIST
|
593 |
+
- TOWN
|
594 |
+
- ▁AGAIN
|
595 |
+
- ▁DALLAS
|
596 |
+
- ▁PORTLAND
|
597 |
+
- ▁SEPTEMBER
|
598 |
+
- ▁ARRIVE
|
599 |
+
- ▁SISTER
|
600 |
+
- ▁HOUSTON
|
601 |
+
- Ã
|
602 |
+
- É
|
603 |
+
- Í
|
604 |
+
- '*'
|
605 |
+
- Á
|
606 |
+
- Ç
|
607 |
+
- Ó
|
608 |
+
- ']'
|
609 |
+
- '['
|
610 |
+
- Ú
|
611 |
+
- Ü
|
612 |
+
- <sos/eos>
|
613 |
+
transcript_token_list: null
|
614 |
+
two_pass: false
|
615 |
+
pre_postencoder_norm: false
|
616 |
+
init: null
|
617 |
+
input_size: null
|
618 |
+
ctc_conf:
|
619 |
+
dropout_rate: 0.0
|
620 |
+
ctc_type: builtin
|
621 |
+
reduce: true
|
622 |
+
ignore_nan_grad: true
|
623 |
+
joint_net_conf: null
|
624 |
+
use_preprocessor: true
|
625 |
+
token_type: bpe
|
626 |
+
bpemodel: data/en_token_list/bpe_unigram500/bpe.model
|
627 |
+
non_linguistic_symbols: null
|
628 |
+
cleaner: null
|
629 |
+
g2p: null
|
630 |
+
speech_volume_normalize: null
|
631 |
+
rir_scp: null
|
632 |
+
rir_apply_prob: 1.0
|
633 |
+
noise_scp: null
|
634 |
+
noise_apply_prob: 1.0
|
635 |
+
noise_db_range: '13_15'
|
636 |
+
frontend: s3prl
|
637 |
+
frontend_conf:
|
638 |
+
frontend_conf:
|
639 |
+
upstream: hubert_large_ll60k
|
640 |
+
download_dir: ./hub
|
641 |
+
multilayer_feature: true
|
642 |
+
fs: 16k
|
643 |
+
specaug: specaug
|
644 |
+
specaug_conf:
|
645 |
+
apply_time_warp: true
|
646 |
+
time_warp_window: 5
|
647 |
+
time_warp_mode: bicubic
|
648 |
+
apply_freq_mask: true
|
649 |
+
freq_mask_width_range:
|
650 |
+
- 0
|
651 |
+
- 30
|
652 |
+
num_freq_mask: 2
|
653 |
+
apply_time_mask: true
|
654 |
+
time_mask_width_range:
|
655 |
+
- 0
|
656 |
+
- 40
|
657 |
+
num_time_mask: 2
|
658 |
+
normalize: utterance_mvn
|
659 |
+
normalize_conf: {}
|
660 |
+
model: espnet
|
661 |
+
model_conf:
|
662 |
+
ctc_weight: 0.3
|
663 |
+
lsm_weight: 0.1
|
664 |
+
length_normalized_loss: false
|
665 |
+
extract_feats_in_collect_stats: false
|
666 |
+
preencoder: linear
|
667 |
+
preencoder_conf:
|
668 |
+
input_size: 1024
|
669 |
+
output_size: 80
|
670 |
+
encoder: conformer
|
671 |
+
encoder_conf:
|
672 |
+
output_size: 512
|
673 |
+
attention_heads: 8
|
674 |
+
linear_units: 2048
|
675 |
+
num_blocks: 12
|
676 |
+
dropout_rate: 0.1
|
677 |
+
positional_dropout_rate: 0.1
|
678 |
+
attention_dropout_rate: 0.1
|
679 |
+
input_layer: conv2d2
|
680 |
+
normalize_before: true
|
681 |
+
macaron_style: true
|
682 |
+
rel_pos_type: latest
|
683 |
+
pos_enc_layer_type: rel_pos
|
684 |
+
selfattention_layer_type: rel_selfattn
|
685 |
+
activation_type: swish
|
686 |
+
use_cnn_module: true
|
687 |
+
cnn_module_kernel: 31
|
688 |
+
postencoder: null
|
689 |
+
postencoder_conf: {}
|
690 |
+
deliberationencoder: null
|
691 |
+
deliberationencoder_conf: {}
|
692 |
+
decoder: transformer
|
693 |
+
decoder_conf:
|
694 |
+
attention_heads: 8
|
695 |
+
linear_units: 2048
|
696 |
+
num_blocks: 6
|
697 |
+
dropout_rate: 0.1
|
698 |
+
positional_dropout_rate: 0.1
|
699 |
+
self_attention_dropout_rate: 0.1
|
700 |
+
src_attention_dropout_rate: 0.1
|
701 |
+
decoder2: null
|
702 |
+
decoder2_conf: {}
|
703 |
+
postdecoder: null
|
704 |
+
postdecoder_conf: {}
|
705 |
+
required:
|
706 |
+
- output_dir
|
707 |
+
- token_list
|
708 |
+
version: '202205'
|
709 |
+
distributed: true
|
exp/asr_train_asr2_hubert_lr0.002_raw_en_bpe500/images/acc.png
ADDED
exp/asr_train_asr2_hubert_lr0.002_raw_en_bpe500/images/backward_time.png
ADDED
exp/asr_train_asr2_hubert_lr0.002_raw_en_bpe500/images/cer.png
ADDED
exp/asr_train_asr2_hubert_lr0.002_raw_en_bpe500/images/cer_ctc.png
ADDED
exp/asr_train_asr2_hubert_lr0.002_raw_en_bpe500/images/forward_time.png
ADDED
exp/asr_train_asr2_hubert_lr0.002_raw_en_bpe500/images/gpu_max_cached_mem_GB.png
ADDED
exp/asr_train_asr2_hubert_lr0.002_raw_en_bpe500/images/iter_time.png
ADDED
exp/asr_train_asr2_hubert_lr0.002_raw_en_bpe500/images/loss.png
ADDED
exp/asr_train_asr2_hubert_lr0.002_raw_en_bpe500/images/loss_att.png
ADDED
exp/asr_train_asr2_hubert_lr0.002_raw_en_bpe500/images/loss_ctc.png
ADDED
exp/asr_train_asr2_hubert_lr0.002_raw_en_bpe500/images/optim0_lr0.png
ADDED
exp/asr_train_asr2_hubert_lr0.002_raw_en_bpe500/images/optim_step_time.png
ADDED
exp/asr_train_asr2_hubert_lr0.002_raw_en_bpe500/images/train_time.png
ADDED
exp/asr_train_asr2_hubert_lr0.002_raw_en_bpe500/images/wer.png
ADDED
exp/asr_train_asr2_hubert_lr0.002_raw_en_bpe500/valid.acc.ave_10best.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:033429e1cae3fe196282f17888ec71b9cae5b7b0fe2fac84ab6c717d4ff2f1b3
|
3 |
+
size 1723018419
|
meta.yaml
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
espnet: '202205'
|
2 |
+
files:
|
3 |
+
asr_model_file: exp/asr_train_asr2_hubert_lr0.002_raw_en_bpe500/valid.acc.ave_10best.pth
|
4 |
+
python: "3.9.5 (default, Jun 4 2021, 12:28:51) \n[GCC 7.5.0]"
|
5 |
+
timestamp: 1672045757.354614
|
6 |
+
torch: 1.13.0+cu116
|
7 |
+
yaml_files:
|
8 |
+
asr_train_config: exp/asr_train_asr2_hubert_lr0.002_raw_en_bpe500/config.yaml
|