|
--- |
|
tags: |
|
- espnet |
|
- audio |
|
- audio-to-audio |
|
language: noinfo |
|
datasets: |
|
- chime4 |
|
license: cc-by-4.0 |
|
--- |
|
|
|
## ESPnet2 ENH model |
|
|
|
### `lichenda/chime4_fasnet_dprnn_tac` |
|
|
|
This model was trained by LiChenda using chime4 recipe in [espnet](https://github.com/espnet/espnet/). |
|
|
|
### Demo: How to use in ESPnet2 |
|
|
|
```bash |
|
cd espnet |
|
git checkout 98f5fb2185b98f9c08fd56492b3d3234504561e7 |
|
pip install -e . |
|
cd egs2/chime4/enh1 |
|
./run.sh --skip_data_prep false --skip_train true --download_model lichenda/chime4_fasnet_dprnn_tac |
|
``` |
|
|
|
<!-- Generated by ./scripts/utils/show_enh_score.sh --> |
|
# RESULTS |
|
## Environments |
|
- date: `Sat Mar 19 07:17:45 CST 2022` |
|
- python version: `3.7.11 (default, Jul 27 2021, 14:32:16) [GCC 7.5.0]` |
|
- espnet version: `espnet 0.10.7a1` |
|
- pytorch version: `pytorch 1.8.1` |
|
- Git hash: `648b024d8fb262eb9923c06a698b9c6df5b16e51` |
|
- Commit date: `Wed Mar 16 18:47:21 2022 +0800` |
|
|
|
|
|
## .. |
|
|
|
config: conf/tuning/train_enh_dprnntac_fasnet.yaml |
|
|
|
|dataset|STOI|SAR|SDR|SIR| |
|
|---|---|---|---|---| |
|
|enhanced_dt05_simu_isolated_6ch_track|0.95|15.75|15.75|0.00| |
|
|enhanced_et05_simu_isolated_6ch_track|0.94|15.40|15.40|0.00| |
|
|
|
## ENH config |
|
|
|
<details><summary>expand</summary> |
|
|
|
``` |
|
config: conf/tuning/train_enh_dprnntac_fasnet.yaml |
|
print_config: false |
|
log_level: INFO |
|
dry_run: false |
|
iterator_type: chunk |
|
output_dir: exp/enh_train_enh_dprnntac_fasnet_raw |
|
ngpu: 1 |
|
seed: 0 |
|
num_workers: 4 |
|
num_att_plot: 3 |
|
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: false |
|
sharded_ddp: false |
|
cudnn_enabled: true |
|
cudnn_benchmark: false |
|
cudnn_deterministic: true |
|
collect_stats: false |
|
write_collected_feats: false |
|
max_epoch: 100 |
|
patience: 10 |
|
val_scheduler_criterion: |
|
- valid |
|
- loss |
|
early_stopping_criterion: |
|
- valid |
|
- loss |
|
- min |
|
best_model_criterion: |
|
- - valid |
|
- si_snr |
|
- max |
|
- - valid |
|
- loss |
|
- min |
|
keep_nbest_models: 1 |
|
nbest_averaging_interval: 0 |
|
grad_clip: 5.0 |
|
grad_clip_type: 2.0 |
|
grad_noise: false |
|
accum_grad: 1 |
|
no_forward_run: false |
|
resume: true |
|
train_dtype: float32 |
|
use_amp: false |
|
log_interval: null |
|
use_matplotlib: true |
|
use_tensorboard: true |
|
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: [] |
|
num_iters_per_epoch: null |
|
batch_size: 8 |
|
valid_batch_size: null |
|
batch_bins: 1000000 |
|
valid_batch_bins: null |
|
train_shape_file: |
|
- exp/enh_stats_16k/train/speech_mix_shape |
|
- exp/enh_stats_16k/train/speech_ref1_shape |
|
valid_shape_file: |
|
- exp/enh_stats_16k/valid/speech_mix_shape |
|
- exp/enh_stats_16k/valid/speech_ref1_shape |
|
batch_type: folded |
|
valid_batch_type: null |
|
fold_length: |
|
- 80000 |
|
- 80000 |
|
sort_in_batch: descending |
|
sort_batch: descending |
|
multiple_iterator: false |
|
chunk_length: 32000 |
|
chunk_shift_ratio: 0.5 |
|
num_cache_chunks: 1024 |
|
train_data_path_and_name_and_type: |
|
- - dump/raw/tr05_simu_isolated_6ch_track/wav.scp |
|
- speech_mix |
|
- sound |
|
- - dump/raw/tr05_simu_isolated_6ch_track/spk1.scp |
|
- speech_ref1 |
|
- sound |
|
valid_data_path_and_name_and_type: |
|
- - dump/raw/dt05_simu_isolated_6ch_track/wav.scp |
|
- speech_mix |
|
- sound |
|
- - dump/raw/dt05_simu_isolated_6ch_track/spk1.scp |
|
- speech_ref1 |
|
- sound |
|
allow_variable_data_keys: false |
|
max_cache_size: 0.0 |
|
max_cache_fd: 32 |
|
valid_max_cache_size: null |
|
optim: adam |
|
optim_conf: |
|
lr: 0.001 |
|
eps: 1.0e-08 |
|
weight_decay: 0 |
|
scheduler: steplr |
|
scheduler_conf: |
|
step_size: 2 |
|
gamma: 0.98 |
|
init: xavier_uniform |
|
model_conf: |
|
stft_consistency: false |
|
loss_type: mask_mse |
|
mask_type: null |
|
criterions: |
|
- name: si_snr |
|
conf: |
|
eps: 1.0e-07 |
|
wrapper: fixed_order |
|
wrapper_conf: |
|
weight: 1.0 |
|
use_preprocessor: false |
|
encoder: same |
|
encoder_conf: {} |
|
separator: fasnet |
|
separator_conf: |
|
enc_dim: 64 |
|
feature_dim: 64 |
|
hidden_dim: 128 |
|
layer: 6 |
|
segment_size: 24 |
|
num_spk: 1 |
|
win_len: 16 |
|
context_len: 16 |
|
sr: 16000 |
|
fasnet_type: fasnet |
|
dropout: 0.2 |
|
decoder: same |
|
decoder_conf: {} |
|
required: |
|
- output_dir |
|
version: 0.10.7a1 |
|
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} |
|
} |
|
|
|
|
|
@inproceedings{ESPnet-SE, |
|
author = {Chenda Li and Jing Shi and Wangyou Zhang and Aswin Shanmugam Subramanian and Xuankai Chang and |
|
Naoyuki Kamo and Moto Hira and Tomoki Hayashi and Christoph B{"{o}}ddeker and Zhuo Chen and Shinji Watanabe}, |
|
title = {ESPnet-SE: End-To-End Speech Enhancement and Separation Toolkit Designed for {ASR} Integration}, |
|
booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, |
|
pages = {785--792}, |
|
publisher = {{IEEE}}, |
|
year = {2021}, |
|
url = {https://doi.org/10.1109/SLT48900.2021.9383615}, |
|
doi = {10.1109/SLT48900.2021.9383615}, |
|
timestamp = {Mon, 12 Apr 2021 17:08:59 +0200}, |
|
biburl = {https://dblp.org/rec/conf/slt/Li0ZSCKHHBC021.bib}, |
|
bibsource = {dblp computer science bibliography, https://dblp.org} |
|
} |
|
|
|
|
|
``` |
|
|
|
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} |
|
} |
|
``` |
|
|
