|
--- |
|
tags: |
|
- espnet |
|
- audio |
|
- speech-enhancement-recognition |
|
language: en |
|
datasets: |
|
- wsj0_2mix_spatialized |
|
license: cc-by-4.0 |
|
--- |
|
|
|
## ESPnet2 EnhS2T model |
|
|
|
### `espnet/yoshiki_wsj0_2mix_spatialized_enh_asr_tfgridnet_waspaa2023_raw_en_char` |
|
|
|
This model was trained by Yoshiki using wsj0_2mix_spatialized 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 |
|
|
|
pip install -e . |
|
cd egs2/wsj0_2mix_spatialized/enh_asr1 |
|
./run.sh --skip_data_prep false --skip_train true --download_model espnet/yoshiki_wsj0_2mix_spatialized_enh_asr_tfgridnet_waspaa2023_raw_en_char |
|
``` |
|
|
|
<!-- Generated by scripts/utils/show_asr_result.sh --> |
|
# RESULTS |
|
## Environments |
|
- date: `Sun Aug 13 19:05:53 UTC 2023` |
|
- python version: `3.7.4 (default, Aug 13 2019, 20:35:49) [GCC 7.3.0]` |
|
- espnet version: `espnet 202304` |
|
- pytorch version: `pytorch 1.10.1+cu111` |
|
- Git hash: `` |
|
- Commit date: `` |
|
|
|
## exp/enh_asr_train_enh_asr_tfgridnet_waspaa2023_raw_en_char |
|
### WER |
|
|
|
|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err| |
|
|---|---|---|---|---|---|---|---|---| |
|
|decode_asr_transformer_normalize_output_wavtrue_lm_lm_train_lm_transformer_en_char_valid.loss.ave_enh_asr_model_valid.acc.best/tt_spatialized_anechoic_multich_max_16k|6000|98613|98.7|1.2|0.1|0.5|1.7|16.5| |
|
|decode_asr_transformer_normalize_output_wavtrue_lm_lm_train_lm_transformer_en_char_valid.loss.ave_enh_asr_model_valid.acc.best/tt_spatialized_reverb_multich_max_16k|6000|98613|98.7|1.3|0.1|0.4|1.7|17.8| |
|
|
|
### CER |
|
|
|
|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err| |
|
|---|---|---|---|---|---|---|---|---| |
|
|decode_asr_transformer_normalize_output_wavtrue_lm_lm_train_lm_transformer_en_char_valid.loss.ave_enh_asr_model_valid.acc.best/tt_spatialized_anechoic_multich_max_16k|6000|598296|99.6|0.2|0.2|0.3|0.7|21.6| |
|
|decode_asr_transformer_normalize_output_wavtrue_lm_lm_train_lm_transformer_en_char_valid.loss.ave_enh_asr_model_valid.acc.best/tt_spatialized_reverb_multich_max_16k|6000|598296|99.6|0.2|0.3|0.3|0.7|23.0| |
|
|
|
### TER |
|
|
|
|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err| |
|
|---|---|---|---|---|---|---|---|---| |
|
|
|
## EnhS2T config |
|
|
|
<details><summary>expand</summary> |
|
|
|
``` |
|
config: conf/tuning/train_enh_asr_tfgridnet_waspaa.yaml |
|
print_config: false |
|
log_level: INFO |
|
dry_run: false |
|
iterator_type: sequence |
|
output_dir: exp/enh_asr_train_enh_asr_tfgridnet_waspaa_raw_en_char |
|
ngpu: 1 |
|
seed: 0 |
|
num_workers: 0 |
|
num_att_plot: 0 |
|
dist_backend: nccl |
|
dist_init_method: env:// |
|
dist_world_size: null |
|
dist_rank: null |
|
local_rank: 0 |
|
dist_master_addr: null |
|
dist_master_port: null |
|
dist_launcher: null |
|
multiprocessing_distributed: false |
|
unused_parameters: true |
|
sharded_ddp: false |
|
cudnn_enabled: true |
|
cudnn_benchmark: false |
|
cudnn_deterministic: true |
|
collect_stats: false |
|
write_collected_feats: false |
|
max_epoch: 11 |
|
patience: 10 |
|
val_scheduler_criterion: |
|
- valid |
|
- loss |
|
early_stopping_criterion: |
|
- valid |
|
- loss |
|
- min |
|
best_model_criterion: |
|
- - valid |
|
- acc |
|
- max |
|
- - train |
|
- loss |
|
- min |
|
keep_nbest_models: 10 |
|
nbest_averaging_interval: 0 |
|
grad_clip: 5 |
|
grad_clip_type: 2.0 |
|
grad_noise: false |
|
accum_grad: 4 |
|
no_forward_run: false |
|
resume: true |
|
train_dtype: float32 |
|
use_amp: false |
|
log_interval: null |
|
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: |
|
- ../enh1/exp/enh_train_enh_tfgridnet_waspaa2023_raw/valid.loss.best.pth:separator:enh_model.separator |
|
- ../../wsj/asr1/exp/asr_train_asr_conformer_s3prlfrontend_wavlm_raw_en_char/valid.acc.best.pth:frontend:s2t_model.frontend |
|
- ../../wsj/asr1/exp/asr_train_asr_conformer_s3prlfrontend_wavlm_raw_en_char/valid.acc.best.pth:preencoder:s2t_model.preencoder |
|
- ../../wsj/asr1/exp/asr_train_asr_conformer_s3prlfrontend_wavlm_raw_en_char/valid.acc.best.pth:encoder:s2t_model.encoder |
|
- ../../wsj/asr1/exp/asr_train_asr_conformer_s3prlfrontend_wavlm_raw_en_char/valid.acc.best.pth:ctc:s2t_model.ctc |
|
- ../../wsj/asr1/exp/asr_train_asr_conformer_s3prlfrontend_wavlm_raw_en_char/valid.acc.best.pth:decoder:s2t_model.decoder |
|
ignore_init_mismatch: false |
|
freeze_param: |
|
- s2t_model.frontend.upstream |
|
num_iters_per_epoch: 20000 |
|
batch_size: 2 |
|
valid_batch_size: null |
|
batch_bins: 1000000 |
|
valid_batch_bins: null |
|
train_shape_file: |
|
- exp/enh_asr_stats_raw_en_char/train/speech_shape |
|
- exp/enh_asr_stats_raw_en_char/train/speech_ref1_shape |
|
- exp/enh_asr_stats_raw_en_char/train/text_spk1_shape.char |
|
- exp/enh_asr_stats_raw_en_char/train/speech_ref2_shape |
|
- exp/enh_asr_stats_raw_en_char/train/text_spk2_shape.char |
|
valid_shape_file: |
|
- exp/enh_asr_stats_raw_en_char/valid/speech_shape |
|
- exp/enh_asr_stats_raw_en_char/valid/speech_ref1_shape |
|
- exp/enh_asr_stats_raw_en_char/valid/text_spk1_shape.char |
|
- exp/enh_asr_stats_raw_en_char/valid/speech_ref2_shape |
|
- exp/enh_asr_stats_raw_en_char/valid/text_spk2_shape.char |
|
batch_type: folded |
|
valid_batch_type: null |
|
fold_length: |
|
- 80000 |
|
- 80000 |
|
- 150 |
|
- 80000 |
|
- 150 |
|
sort_in_batch: descending |
|
sort_batch: descending |
|
multiple_iterator: false |
|
chunk_length: 500 |
|
chunk_shift_ratio: 0.5 |
|
num_cache_chunks: 1024 |
|
chunk_excluded_key_prefixes: [] |
|
train_data_path_and_name_and_type: |
|
- - dump/raw/tr_spatialized_multi_multich_max_16k/wav.scp |
|
- speech |
|
- sound |
|
- - dump/raw/tr_spatialized_multi_multich_max_16k/spk1.scp |
|
- speech_ref1 |
|
- sound |
|
- - dump/raw/tr_spatialized_multi_multich_max_16k/text_spk1 |
|
- text_spk1 |
|
- text |
|
- - dump/raw/tr_spatialized_multi_multich_max_16k/spk2.scp |
|
- speech_ref2 |
|
- sound |
|
- - dump/raw/tr_spatialized_multi_multich_max_16k/text_spk2 |
|
- text_spk2 |
|
- text |
|
valid_data_path_and_name_and_type: |
|
- - dump/raw/cv_spatialized_multi_multich_max_16k/wav.scp |
|
- speech |
|
- sound |
|
- - dump/raw/cv_spatialized_multi_multich_max_16k/spk1.scp |
|
- speech_ref1 |
|
- sound |
|
- - dump/raw/cv_spatialized_multi_multich_max_16k/text_spk1 |
|
- text_spk1 |
|
- text |
|
- - dump/raw/cv_spatialized_multi_multich_max_16k/spk2.scp |
|
- speech_ref2 |
|
- sound |
|
- - dump/raw/cv_spatialized_multi_multich_max_16k/text_spk2 |
|
- text_spk2 |
|
- 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: sgd |
|
optim_conf: |
|
lr: 0.001 |
|
momentum: 0.9 |
|
scheduler: null |
|
scheduler_conf: {} |
|
token_list: data/en_token_list/char/tokens.txt |
|
src_token_list: null |
|
init: xavier_uniform |
|
input_size: null |
|
ctc_conf: |
|
dropout_rate: 0.0 |
|
ctc_type: builtin |
|
reduce: true |
|
ignore_nan_grad: null |
|
zero_infinity: true |
|
enh_criterions: |
|
- name: mr_l1_tfd |
|
conf: |
|
window_sz: |
|
- 512 |
|
time_domain_weight: 1.0 |
|
wrapper: pit |
|
wrapper_conf: |
|
weight: 1.0 |
|
diar_num_spk: null |
|
diar_input_size: null |
|
enh_model_conf: |
|
stft_consistency: false |
|
loss_type: mask_mse |
|
mask_type: null |
|
asr_model_conf: |
|
ctc_weight: 0.3 |
|
lsm_weight: 0.1 |
|
length_normalized_loss: false |
|
extract_feats_in_collect_stats: false |
|
st_model_conf: |
|
stft_consistency: false |
|
loss_type: mask_mse |
|
mask_type: null |
|
diar_model_conf: |
|
diar_weight: 1.0 |
|
attractor_weight: 1.0 |
|
subtask_series: |
|
- enh |
|
- asr |
|
model_conf: |
|
bypass_enh_prob: 0.0 |
|
calc_enh_loss: false |
|
use_preprocessor: true |
|
token_type: char |
|
bpemodel: null |
|
src_token_type: bpe |
|
src_bpemodel: null |
|
non_linguistic_symbols: data/nlsyms.txt |
|
cleaner: null |
|
g2p: null |
|
text_name: |
|
- text_spk1 |
|
- text_spk2 |
|
enh_encoder: same |
|
enh_encoder_conf: {} |
|
enh_separator: tfgridnet |
|
enh_separator_conf: |
|
n_srcs: 2 |
|
n_fft: 512 |
|
stride: 256 |
|
window: hann |
|
n_imics: 8 |
|
n_layers: 6 |
|
lstm_hidden_units: 192 |
|
attn_n_head: 4 |
|
attn_approx_qk_dim: 512 |
|
emb_dim: 48 |
|
emb_ks: 4 |
|
emb_hs: 2 |
|
activation: gelu |
|
eps: 1.0e-05 |
|
ref_channel: 0 |
|
enh_decoder: same |
|
enh_decoder_conf: {} |
|
enh_mask_module: multi_mask |
|
enh_mask_module_conf: {} |
|
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 |
|
- 100 |
|
num_freq_mask: 4 |
|
apply_time_mask: true |
|
time_mask_width_range: |
|
- 0 |
|
- 40 |
|
num_time_mask: 2 |
|
normalize: utterance_mvn |
|
normalize_conf: {} |
|
asr_preencoder: linear |
|
asr_preencoder_conf: |
|
input_size: 1024 |
|
output_size: 80 |
|
asr_encoder: conformer |
|
asr_encoder_conf: |
|
output_size: 256 |
|
attention_heads: 4 |
|
linear_units: 2048 |
|
num_blocks: 12 |
|
dropout_rate: 0.1 |
|
positional_dropout_rate: 0.1 |
|
attention_dropout_rate: 0.0 |
|
input_layer: conv2d2 |
|
normalize_before: true |
|
macaron_style: true |
|
rel_pos_type: latest |
|
pos_enc_layer_type: rel_pos |
|
selfattention_layer_type: rel_selfattn |
|
activation_type: swish |
|
use_cnn_module: true |
|
cnn_module_kernel: 15 |
|
asr_postencoder: null |
|
asr_postencoder_conf: {} |
|
asr_decoder: transformer |
|
asr_decoder_conf: |
|
input_layer: embed |
|
attention_heads: 4 |
|
linear_units: 2048 |
|
num_blocks: 6 |
|
dropout_rate: 0.1 |
|
positional_dropout_rate: 0.1 |
|
self_attention_dropout_rate: 0.0 |
|
src_attention_dropout_rate: 0.0 |
|
st_preencoder: null |
|
st_preencoder_conf: {} |
|
st_encoder: rnn |
|
st_encoder_conf: {} |
|
st_postencoder: null |
|
st_postencoder_conf: {} |
|
st_decoder: rnn |
|
st_decoder_conf: {} |
|
st_extra_asr_decoder: rnn |
|
st_extra_asr_decoder_conf: {} |
|
st_extra_mt_decoder: rnn |
|
st_extra_mt_decoder_conf: {} |
|
diar_frontend: default |
|
diar_frontend_conf: {} |
|
diar_specaug: null |
|
diar_specaug_conf: {} |
|
diar_normalize: utterance_mvn |
|
diar_normalize_conf: {} |
|
diar_encoder: transformer |
|
diar_encoder_conf: {} |
|
diar_decoder: linear |
|
diar_decoder_conf: {} |
|
label_aggregator: label_aggregator |
|
label_aggregator_conf: {} |
|
diar_attractor: null |
|
diar_attractor_conf: {} |
|
required: |
|
- output_dir |
|
version: '202304' |
|
distributed: false |
|
``` |
|
|
|
</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} |
|
} |
|
``` |
|
|
