|
--- |
|
tags: |
|
- espnet |
|
- audio |
|
- automatic-speech-recognition |
|
language: en |
|
datasets: |
|
- A |
|
license: cc-by-4.0 |
|
--- |
|
|
|
## ESPnet2 ASR model |
|
|
|
### `espnet/jiyang_tang_aphsiabank_english_asr_ebranchformer_small_wavlm_large1` |
|
|
|
This model was trained by Jiyang Tang using A recipe in [espnet](https://github.com/espnet/espnet/). |
|
|
|
### Demo: How to use in ESPnet2 |
|
|
|
Follow the [ESPnet installation instructions](https://espnet.github.io/espnet/installation.html) |
|
if you haven't done that already. |
|
|
|
```bash |
|
cd espnet |
|
git checkout 4ddda8634b6b03fbbdae97927e58722a13f1f7c8 |
|
pip install -e . |
|
cd jtang1/A/asr1 |
|
./run.sh --skip_data_prep false --skip_train true --download_model espnet/jiyang_tang_aphsiabank_english_asr_ebranchformer_small_wavlm_large1 |
|
``` |
|
|
|
<!-- Generated by scripts/utils/show_asr_result.sh --> |
|
# RESULTS |
|
## Environments |
|
- date: `Mon Mar 13 15:37:27 EDT 2023` |
|
- python version: `3.9.12 (main, Apr 5 2022, 06:56:58) [GCC 7.5.0]` |
|
- espnet version: `espnet 202301` |
|
- pytorch version: `pytorch 1.8.1` |
|
- Git hash: `b0b2a0aa9c335267046e83036b87e88af30698da` |
|
- Commit date: `Tue Feb 7 14:56:31 2023 -0500` |
|
|
|
## asr_ebranchformer_wavlm |
|
### WER |
|
|
|
|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err| |
|
|---|---|---|---|---|---|---|---|---| |
|
|decode_asr_model_valid.acc.ave/test|28424|240039|81.3|13.2|5.6|3.4|22.2|67.6| |
|
|
|
### CER |
|
|
|
|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err| |
|
|---|---|---|---|---|---|---|---|---| |
|
|decode_asr_model_valid.acc.ave/test|28424|1103375|89.9|4.1|6.0|3.7|13.8|67.6| |
|
|
|
### TER |
|
|
|
|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err| |
|
|---|---|---|---|---|---|---|---|---| |
|
|
|
## ASR config |
|
|
|
<details><summary>expand</summary> |
|
|
|
``` |
|
config: conf/tuning/train_asr_ebranchformer_small_wavlm_large1.yaml |
|
print_config: false |
|
log_level: INFO |
|
dry_run: false |
|
iterator_type: sequence |
|
output_dir: exp/asr_ebranchformer_wavlm |
|
ngpu: 1 |
|
seed: 2022 |
|
num_workers: 2 |
|
num_att_plot: 0 |
|
dist_backend: nccl |
|
dist_init_method: env:// |
|
dist_world_size: 2 |
|
dist_rank: 0 |
|
local_rank: 0 |
|
dist_master_addr: localhost |
|
dist_master_port: 47613 |
|
dist_launcher: null |
|
multiprocessing_distributed: true |
|
unused_parameters: true |
|
sharded_ddp: false |
|
cudnn_enabled: true |
|
cudnn_benchmark: false |
|
cudnn_deterministic: false |
|
collect_stats: false |
|
write_collected_feats: false |
|
max_epoch: 30 |
|
patience: null |
|
val_scheduler_criterion: |
|
- valid |
|
- loss |
|
early_stopping_criterion: |
|
- valid |
|
- loss |
|
- min |
|
best_model_criterion: |
|
- - valid |
|
- acc |
|
- max |
|
keep_nbest_models: 10 |
|
nbest_averaging_interval: 0 |
|
grad_clip: 5 |
|
grad_clip_type: 2.0 |
|
grad_noise: false |
|
accum_grad: 8 |
|
no_forward_run: false |
|
resume: true |
|
train_dtype: float32 |
|
use_amp: true |
|
log_interval: 200 |
|
use_matplotlib: true |
|
use_tensorboard: true |
|
create_graph_in_tensorboard: false |
|
use_wandb: false |
|
wandb_project: null |
|
wandb_id: null |
|
wandb_entity: null |
|
wandb_name: null |
|
wandb_model_log_interval: -1 |
|
detect_anomaly: false |
|
pretrain_path: null |
|
init_param: [] |
|
ignore_init_mismatch: false |
|
freeze_param: |
|
- frontend.upstream |
|
num_iters_per_epoch: null |
|
batch_size: 20 |
|
valid_batch_size: null |
|
batch_bins: 6000000 |
|
valid_batch_bins: null |
|
train_shape_file: |
|
- exp/asr_stats_raw_en_char_sp/train/speech_shape |
|
- exp/asr_stats_raw_en_char_sp/train/text_shape.char |
|
valid_shape_file: |
|
- exp/asr_stats_raw_en_char_sp/valid/speech_shape |
|
- exp/asr_stats_raw_en_char_sp/valid/text_shape.char |
|
batch_type: numel |
|
valid_batch_type: null |
|
fold_length: |
|
- 80000 |
|
- 150 |
|
sort_in_batch: descending |
|
sort_batch: descending |
|
multiple_iterator: false |
|
chunk_length: 500 |
|
chunk_shift_ratio: 0.5 |
|
num_cache_chunks: 1024 |
|
train_data_path_and_name_and_type: |
|
- - dump/raw/train_sp/wav.scp |
|
- speech |
|
- sound |
|
- - dump/raw/train_sp/text |
|
- text |
|
- text |
|
valid_data_path_and_name_and_type: |
|
- - dump/raw/val/wav.scp |
|
- speech |
|
- sound |
|
- - dump/raw/val/text |
|
- text |
|
- text |
|
allow_variable_data_keys: false |
|
max_cache_size: 0.0 |
|
max_cache_fd: 32 |
|
valid_max_cache_size: null |
|
exclude_weight_decay: false |
|
exclude_weight_decay_conf: {} |
|
optim: adam |
|
optim_conf: |
|
lr: 0.001 |
|
weight_decay: 1.0e-06 |
|
scheduler: warmuplr |
|
scheduler_conf: |
|
warmup_steps: 2500 |
|
token_list: |
|
- <blank> |
|
- <unk> |
|
- '[APH]' |
|
- '[NONAPH]' |
|
- <space> |
|
- e |
|
- t |
|
- a |
|
- h |
|
- o |
|
- n |
|
- i |
|
- s |
|
- d |
|
- r |
|
- u |
|
- l |
|
- m |
|
- w |
|
- y |
|
- g |
|
- c |
|
- b |
|
- f |
|
- p |
|
- k |
|
- '''' |
|
- v |
|
- j |
|
- < |
|
- L |
|
- A |
|
- U |
|
- '>' |
|
- ɪ |
|
- x |
|
- ə |
|
- z |
|
- ɛ |
|
- ɑ |
|
- q |
|
- ɹ |
|
- æ |
|
- ˞ |
|
- ʌ |
|
- ʃ |
|
- ʊ |
|
- ɔ |
|
- ŋ |
|
- ɚ |
|
- ɾ |
|
- ʒ |
|
- ð |
|
- θ |
|
- ɜ |
|
- ɝ |
|
- ɡ |
|
- '0' |
|
- ː |
|
- ʔ |
|
- ɒ |
|
- é |
|
- ɸ |
|
- ̩ |
|
- ʤ |
|
- ʧ |
|
- <sos/eos> |
|
init: null |
|
input_size: null |
|
ctc_conf: |
|
dropout_rate: 0.0 |
|
ctc_type: builtin |
|
reduce: true |
|
ignore_nan_grad: null |
|
zero_infinity: true |
|
joint_net_conf: null |
|
use_preprocessor: true |
|
token_type: char |
|
bpemodel: null |
|
non_linguistic_symbols: local/nlsyms.txt |
|
cleaner: null |
|
g2p: null |
|
speech_volume_normalize: null |
|
rir_scp: null |
|
rir_apply_prob: 1.0 |
|
noise_scp: null |
|
noise_apply_prob: 1.0 |
|
noise_db_range: '13_15' |
|
short_noise_thres: 0.5 |
|
aux_ctc_tasks: [] |
|
frontend: s3prl |
|
frontend_conf: |
|
frontend_conf: |
|
upstream: wavlm_large |
|
download_dir: ./hub |
|
multilayer_feature: true |
|
fs: 16k |
|
specaug: specaug |
|
specaug_conf: |
|
apply_time_warp: true |
|
time_warp_window: 5 |
|
time_warp_mode: bicubic |
|
apply_freq_mask: true |
|
freq_mask_width_range: |
|
- 0 |
|
- 27 |
|
num_freq_mask: 2 |
|
apply_time_mask: true |
|
time_mask_width_ratio_range: |
|
- 0.0 |
|
- 0.05 |
|
num_time_mask: 5 |
|
normalize: utterance_mvn |
|
normalize_conf: {} |
|
model: espnet |
|
model_conf: |
|
ctc_weight: 0.3 |
|
lsm_weight: 0.1 |
|
length_normalized_loss: false |
|
extract_feats_in_collect_stats: false |
|
preencoder: linear |
|
preencoder_conf: |
|
input_size: 1024 |
|
output_size: 80 |
|
encoder: e_branchformer |
|
encoder_conf: |
|
output_size: 256 |
|
attention_heads: 4 |
|
linear_units: 1024 |
|
num_blocks: 12 |
|
dropout_rate: 0.1 |
|
positional_dropout_rate: 0.1 |
|
attention_dropout_rate: 0.1 |
|
layer_drop_rate: 0.1 |
|
input_layer: conv2d1 |
|
macaron_ffn: true |
|
pos_enc_layer_type: rel_pos |
|
attention_layer_type: rel_selfattn |
|
rel_pos_type: latest |
|
cgmlp_linear_units: 3072 |
|
cgmlp_conv_kernel: 31 |
|
use_linear_after_conv: false |
|
gate_activation: identity |
|
positionwise_layer_type: linear |
|
use_ffn: true |
|
merge_conv_kernel: 31 |
|
postencoder: null |
|
postencoder_conf: {} |
|
decoder: transformer |
|
decoder_conf: |
|
attention_heads: 4 |
|
linear_units: 2048 |
|
num_blocks: 6 |
|
dropout_rate: 0.1 |
|
positional_dropout_rate: 0.1 |
|
self_attention_dropout_rate: 0.1 |
|
src_attention_dropout_rate: 0.1 |
|
layer_drop_rate: 0.2 |
|
preprocessor: default |
|
preprocessor_conf: {} |
|
required: |
|
- output_dir |
|
- token_list |
|
version: '202301' |
|
distributed: true |
|
``` |
|
|
|
</details> |
|
|
|
|
|
|
|
### Citing ESPnet |
|
|
|
```BibTex |
|
@inproceedings{watanabe2018espnet, |
|
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}, |
|
title={{ESPnet}: End-to-End Speech Processing Toolkit}, |
|
year={2018}, |
|
booktitle={Proceedings of Interspeech}, |
|
pages={2207--2211}, |
|
doi={10.21437/Interspeech.2018-1456}, |
|
url={http://dx.doi.org/10.21437/Interspeech.2018-1456} |
|
} |
|
|
|
|
|
|
|
|
|
``` |
|
|
|
or arXiv: |
|
|
|
```bibtex |
|
@misc{watanabe2018espnet, |
|
title={ESPnet: End-to-End Speech Processing Toolkit}, |
|
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}, |
|
year={2018}, |
|
eprint={1804.00015}, |
|
archivePrefix={arXiv}, |
|
primaryClass={cs.CL} |
|
} |
|
``` |
|
|