|
--- |
|
tags: |
|
- espnet |
|
- audio |
|
- automatic-speech-recognition |
|
language: tav |
|
datasets: |
|
- americasnlp22 |
|
license: cc-by-4.0 |
|
--- |
|
|
|
## ESPnet2 ASR model |
|
|
|
### `espnet/americasnlp22-asr-tav` |
|
|
|
This model was trained by Pavel Denisov using americasnlp22 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 66ca5df9f08b6084dbde4d9f312fa8ba0a47ecfc |
|
pip install -e . |
|
cd egs2/americasnlp22/asr1 |
|
./run.sh \ |
|
--skip_data_prep false \ |
|
--skip_train true \ |
|
--download_model espnet/americasnlp22-asr-tav \ |
|
--lang tav \ |
|
--local_data_opts "--lang tav" \ |
|
--train_set train_tav \ |
|
--valid_set dev_tav \ |
|
--test_sets dev_tav \ |
|
--gpu_inference false \ |
|
--inference_nj 8 \ |
|
--lm_train_text data/train_tav/text \ |
|
--bpe_train_text data/train_tav/text |
|
``` |
|
|
|
<!-- Generated by scripts/utils/show_asr_result.sh --> |
|
# RESULTS |
|
## Environments |
|
- date: `Sun Jun 5 02:36:59 CEST 2022` |
|
- python version: `3.9.13 (main, May 18 2022, 00:00:00) [GCC 11.3.1 20220421 (Red Hat 11.3.1-2)]` |
|
- espnet version: `espnet 202204` |
|
- pytorch version: `pytorch 1.11.0+cu115` |
|
- Git hash: `d55704daa36d3dd2ca24ae3162ac40d81957208c` |
|
- Commit date: `Wed Jun 1 02:33:09 2022 +0200` |
|
|
|
## asr_train_asr_transformer_raw_tav_bpe100_sp |
|
### WER |
|
|
|
|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err| |
|
|---|---|---|---|---|---|---|---|---| |
|
|decode_asr_asr_model_valid.cer_ctc.best/dev_tav|250|1201|3.0|83.1|13.9|17.0|114.0|99.6| |
|
|
|
### CER |
|
|
|
|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err| |
|
|---|---|---|---|---|---|---|---|---| |
|
|decode_asr_asr_model_valid.cer_ctc.best/dev_tav|250|8606|57.5|19.9|22.7|12.0|54.5|99.6| |
|
|
|
### TER |
|
|
|
|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err| |
|
|---|---|---|---|---|---|---|---|---| |
|
|decode_asr_asr_model_valid.cer_ctc.best/dev_tav|250|6741|49.2|28.5|22.3|12.6|63.4|99.6| |
|
|
|
## 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_tav_bpe100_sp |
|
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: 15 |
|
patience: null |
|
val_scheduler_criterion: |
|
- valid |
|
- loss |
|
early_stopping_criterion: |
|
- valid |
|
- loss |
|
- min |
|
best_model_criterion: |
|
- - valid |
|
- cer_ctc |
|
- 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: |
|
- frontend.upstream.model.feature_extractor |
|
- frontend.upstream.model.encoder.layers.0 |
|
- frontend.upstream.model.encoder.layers.1 |
|
- frontend.upstream.model.encoder.layers.2 |
|
- frontend.upstream.model.encoder.layers.3 |
|
- frontend.upstream.model.encoder.layers.4 |
|
- frontend.upstream.model.encoder.layers.5 |
|
- frontend.upstream.model.encoder.layers.6 |
|
- frontend.upstream.model.encoder.layers.7 |
|
- frontend.upstream.model.encoder.layers.8 |
|
- frontend.upstream.model.encoder.layers.9 |
|
- frontend.upstream.model.encoder.layers.10 |
|
- frontend.upstream.model.encoder.layers.11 |
|
- frontend.upstream.model.encoder.layers.12 |
|
- frontend.upstream.model.encoder.layers.13 |
|
- frontend.upstream.model.encoder.layers.14 |
|
- frontend.upstream.model.encoder.layers.15 |
|
- frontend.upstream.model.encoder.layers.16 |
|
- frontend.upstream.model.encoder.layers.17 |
|
- frontend.upstream.model.encoder.layers.18 |
|
- frontend.upstream.model.encoder.layers.19 |
|
- frontend.upstream.model.encoder.layers.20 |
|
- frontend.upstream.model.encoder.layers.21 |
|
num_iters_per_epoch: null |
|
batch_size: 20 |
|
valid_batch_size: null |
|
batch_bins: 200000 |
|
valid_batch_bins: null |
|
train_shape_file: |
|
- exp/asr_stats_raw_tav_bpe100_sp/train/speech_shape |
|
- exp/asr_stats_raw_tav_bpe100_sp/train/text_shape.bpe |
|
valid_shape_file: |
|
- exp/asr_stats_raw_tav_bpe100_sp/valid/speech_shape |
|
- exp/asr_stats_raw_tav_bpe100_sp/valid/text_shape.bpe |
|
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_tav_sp/wav.scp |
|
- speech |
|
- sound |
|
- - dump/raw/train_tav_sp/text |
|
- text |
|
- text |
|
valid_data_path_and_name_and_type: |
|
- - dump/raw/dev_tav/wav.scp |
|
- speech |
|
- sound |
|
- - dump/raw/dev_tav/text |
|
- text |
|
- text |
|
allow_variable_data_keys: false |
|
max_cache_size: 0.0 |
|
max_cache_fd: 32 |
|
valid_max_cache_size: null |
|
optim: adamw |
|
optim_conf: |
|
lr: 0.0001 |
|
scheduler: warmuplr |
|
scheduler_conf: |
|
warmup_steps: 300 |
|
token_list: |
|
- <blank> |
|
- <unk> |
|
- ▁ |
|
- a |
|
- '''' |
|
- i |
|
- h |
|
- o |
|
- e |
|
- u |
|
- U |
|
- do |
|
- ':' |
|
- li |
|
- na |
|
- sa |
|
- ▁ti |
|
- n |
|
- k |
|
- ',' |
|
- '~' |
|
- p |
|
- ye |
|
- le |
|
- ka |
|
- ta |
|
- pe |
|
- ▁ni |
|
- ti |
|
- ▁ihi |
|
- ▁ma |
|
- ▁~ |
|
- 'no' |
|
- ya |
|
- s |
|
- ▁wa |
|
- aye |
|
- t |
|
- . |
|
- y |
|
- m |
|
- g |
|
- d |
|
- r |
|
- ã |
|
- '"' |
|
- õ |
|
- ( |
|
- ) |
|
- l |
|
- '!' |
|
- c |
|
- '0' |
|
- I |
|
- '[' |
|
- ']' |
|
- '2' |
|
- '-' |
|
- ç |
|
- M |
|
- '6' |
|
- f |
|
- A |
|
- D |
|
- '?' |
|
- J |
|
- j |
|
- Y |
|
- z |
|
- Õ |
|
- K |
|
- '`' |
|
- Ã |
|
- O |
|
- N |
|
- F |
|
- C |
|
- '1' |
|
- S |
|
- P |
|
- L |
|
- T |
|
- G |
|
- v |
|
- ñ |
|
- b |
|
- H |
|
- E |
|
- '3' |
|
- '4' |
|
- '5' |
|
- '7' |
|
- B |
|
- W |
|
- é |
|
- ó |
|
- ́ |
|
- w |
|
- í |
|
- <sos/eos> |
|
init: null |
|
input_size: null |
|
ctc_conf: |
|
dropout_rate: 0.0 |
|
ctc_type: builtin |
|
reduce: true |
|
ignore_nan_grad: true |
|
joint_net_conf: null |
|
use_preprocessor: true |
|
token_type: bpe |
|
bpemodel: data/tav_token_list/bpe_unigram100/bpe.model |
|
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' |
|
frontend: s3prl |
|
frontend_conf: |
|
frontend_conf: |
|
upstream: wav2vec2_url |
|
upstream_ckpt: https://dl.fbaipublicfiles.com/fairseq/wav2vec/xlsr2_300m.pt |
|
download_dir: ./hub |
|
multilayer_feature: true |
|
fs: 16k |
|
specaug: null |
|
specaug_conf: {} |
|
normalize: utterance_mvn |
|
normalize_conf: {} |
|
model: espnet |
|
model_conf: |
|
ctc_weight: 1.0 |
|
lsm_weight: 0.0 |
|
length_normalized_loss: false |
|
extract_feats_in_collect_stats: false |
|
preencoder: linear |
|
preencoder_conf: |
|
input_size: 1024 |
|
output_size: 80 |
|
encoder: transformer |
|
encoder_conf: |
|
input_layer: conv2d2 |
|
num_blocks: 1 |
|
linear_units: 2048 |
|
dropout_rate: 0.2 |
|
output_size: 256 |
|
attention_heads: 8 |
|
attention_dropout_rate: 0.2 |
|
postencoder: null |
|
postencoder_conf: {} |
|
decoder: rnn |
|
decoder_conf: {} |
|
required: |
|
- output_dir |
|
- token_list |
|
version: '202204' |
|
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} |
|
} |
|
``` |
|
|
