|
--- |
|
tags: |
|
- espnet |
|
- audio |
|
- automatic-speech-recognition |
|
language: can |
|
datasets: |
|
- mini_an4 |
|
license: cc-by-4.0 |
|
--- |
|
|
|
## ESPnet2 ASR model |
|
|
|
### `siuze/Cantonese-MDCC` |
|
|
|
This model was trained by siuze using mini_an4 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 52160d6ed337e9dec74dd59695fec1548042e0b2 |
|
pip install -e . |
|
cd egs2/mini_an4/asr1 |
|
./run.sh --skip_data_prep false --skip_train true --download_model siuze/Cantonese-MDCC |
|
``` |
|
|
|
<!-- Generated by scripts/utils/show_asr_result.sh --> |
|
# RESULTS |
|
## Environments |
|
- date: `Fri Mar 17 23:08:24 CST 2023` |
|
- python version: `3.8.16 | packaged by conda-forge | (default, Feb 1 2023, 16:01:55) [GCC 11.3.0]` |
|
- espnet version: `espnet 202301` |
|
- pytorch version: `pytorch 1.10.0` |
|
- Git hash: `52160d6ed337e9dec74dd59695fec1548042e0b2` |
|
- Commit date: `Thu Mar 16 21:37:39 2023 +0000` |
|
|
|
## exp/asr_train_asr_transformer_raw_can_char |
|
### WER |
|
|
|
|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err| |
|
|---|---|---|---|---|---|---|---|---| |
|
|inference_asr_model_valid.acc.ave/test|9077|108147|0.0|0.0|100.0|0.0|100.0|100.0| |
|
|
|
### CER |
|
|
|
|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err| |
|
|---|---|---|---|---|---|---|---|---| |
|
|inference_asr_model_valid.acc.ave/test|9077|666586|0.0|0.0|100.0|0.0|100.0|100.0| |
|
|
|
### TER |
|
|
|
|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err| |
|
|---|---|---|---|---|---|---|---|---| |
|
|
|
## ASR config |
|
|
|
<details><summary>expand</summary> |
|
|
|
``` |
|
config: conf/train_asr_transformer.yaml |
|
print_config: false |
|
log_level: INFO |
|
dry_run: false |
|
iterator_type: sequence |
|
output_dir: exp/asr_train_asr_transformer_raw_can_char |
|
ngpu: 1 |
|
seed: 0 |
|
num_workers: 1 |
|
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: 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: 5.0 |
|
grad_clip_type: 2.0 |
|
grad_noise: false |
|
accum_grad: 8 |
|
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: [] |
|
ignore_init_mismatch: false |
|
freeze_param: [] |
|
num_iters_per_epoch: null |
|
batch_size: 16 |
|
valid_batch_size: null |
|
batch_bins: 1000000 |
|
valid_batch_bins: null |
|
train_shape_file: |
|
- exp/asr_stats_raw_can_char/train/speech_shape |
|
- exp/asr_stats_raw_can_char/train/text_shape.char |
|
valid_shape_file: |
|
- exp/asr_stats_raw_can_char/valid/speech_shape |
|
- exp/asr_stats_raw_can_char/valid/text_shape.char |
|
batch_type: folded |
|
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 |
|
chunk_excluded_key_prefixes: [] |
|
train_data_path_and_name_and_type: |
|
- - dump/raw/train/wav.scp |
|
- speech |
|
- sound |
|
- - dump/raw/train/text |
|
- text |
|
- text |
|
valid_data_path_and_name_and_type: |
|
- - dump/raw/dev/wav.scp |
|
- speech |
|
- sound |
|
- - dump/raw/dev/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: 0.005 |
|
scheduler: warmuplr |
|
scheduler_conf: |
|
warmup_steps: 30000 |
|
token_list: |
|
- <blank> |
|
- <unk> |
|
- <space> |
|
- '3' |
|
- '2' |
|
- '5' |
|
- g |
|
- o |
|
- a |
|
- n |
|
- i |
|
- '4' |
|
- u |
|
- e |
|
- k |
|
- '1' |
|
- j |
|
- y |
|
- z |
|
- s |
|
- h |
|
- d |
|
- m |
|
- l |
|
- c |
|
- b |
|
- f |
|
- t |
|
- w |
|
- p |
|
- r |
|
- x |
|
- v |
|
- q |
|
- <sos/eos> |
|
init: xavier_uniform |
|
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: null |
|
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: default |
|
frontend_conf: |
|
fs: 16k |
|
specaug: null |
|
specaug_conf: {} |
|
normalize: global_mvn |
|
normalize_conf: |
|
stats_file: exp/asr_stats_raw_can_char/train/feats_stats.npz |
|
model: espnet |
|
model_conf: |
|
ctc_weight: 0.3 |
|
lsm_weight: 0.1 |
|
length_normalized_loss: false |
|
preencoder: null |
|
preencoder_conf: {} |
|
encoder: transformer |
|
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: conv2d |
|
normalize_before: true |
|
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: 0.0 |
|
src_attention_dropout_rate: 0.0 |
|
preprocessor: default |
|
preprocessor_conf: {} |
|
required: |
|
- output_dir |
|
- token_list |
|
version: '202301' |
|
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} |
|
} |
|
``` |
|
|
