|
--- |
|
tags: |
|
- espnet |
|
- audio |
|
- automatic-speech-recognition |
|
language: en |
|
datasets: |
|
- slue-voxceleb |
|
license: cc-by-4.0 |
|
--- |
|
|
|
## ESPnet2 ASR model |
|
|
|
### `espnet/sluevoxceleb_owsm_finetune_sa` |
|
|
|
This model was trained by “siddhu001” using slue-voxceleb 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 e23ef85f0b3116ad5c60d0833f186da0deec0734 |
|
pip install -e . |
|
cd egs2/slue-voxceleb/slu1_superb_correct |
|
./run.sh --skip_data_prep false --skip_train true --download_model espnet/sluevoxceleb_owsm_finetune_sa |
|
``` |
|
|
|
<!-- Generated by scripts/utils/show_asr_result.sh --> |
|
# RESULTS |
|
## Environments |
|
- date: `Wed Feb 7 23:48:24 CST 2024` |
|
- python version: `3.9.13 (main, Aug 25 2022, 23:26:10) [GCC 11.2.0]` |
|
- espnet version: `espnet 202310` |
|
- pytorch version: `pytorch 2.1.0+cu121` |
|
- Git hash: `21d2105784e4da98397bf487b2550d4c6e16d40d` |
|
- Commit date: `Wed Jan 31 13:40:37 2024 -0600` |
|
|
|
## exp/slu_train_asr_own3.1_weighted_finetune_0.000001_raw_en_word_sp |
|
### WER |
|
|
|
|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err| |
|
|---|---|---|---|---|---|---|---|---| |
|
|decode_asr_slu_model_valid.loss.ave/devel|1436|1436|79.5|20.5|0.0|0.0|20.5|20.5| |
|
|decode_asr_slu_model_valid.loss.ave/test|3426|3426|79.3|20.7|0.0|0.0|20.7|20.7| |
|
|
|
### CER |
|
|
|
|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err| |
|
|---|---|---|---|---|---|---|---|---| |
|
|decode_asr_slu_model_valid.loss.ave/devel|1436|10365|81.9|16.1|2.0|0.8|18.9|20.5| |
|
|decode_asr_slu_model_valid.loss.ave/test|3426|24887|82.1|15.8|2.2|0.6|18.6|20.7| |
|
|
|
### TER |
|
|
|
|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err| |
|
|---|---|---|---|---|---|---|---|---| |
|
## exp/slu_train_asr_own3.1_weighted_finetune_0.000001_raw_en_word_sp/decode_asr_slu_model_valid.loss.ave |
|
### WER |
|
|
|
|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err| |
|
|---|---|---|---|---|---|---|---|---| |
|
|org/devel|1437|1437|79.5|20.5|0.0|0.0|20.5|20.5| |
|
|
|
### CER |
|
|
|
|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err| |
|
|---|---|---|---|---|---|---|---|---| |
|
|org/devel|1437|10372|81.9|16.1|2.0|0.8|18.9|20.5| |
|
|
|
### TER |
|
|
|
|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err| |
|
|---|---|---|---|---|---|---|---|---| |
|
|
|
## ASR config |
|
|
|
<details><summary>expand</summary> |
|
|
|
``` |
|
config: conf/train_asr_own3.1_weighted_finetune_0.000001.yaml |
|
print_config: false |
|
log_level: INFO |
|
drop_last_iter: false |
|
dry_run: false |
|
iterator_type: sequence |
|
valid_iterator_type: null |
|
output_dir: exp/slu_train_asr_own3.1_weighted_finetune_0.000001_raw_en_word_sp |
|
ngpu: 1 |
|
seed: 0 |
|
num_workers: 1 |
|
num_att_plot: 3 |
|
dist_backend: nccl |
|
dist_init_method: env:// |
|
dist_world_size: 4 |
|
dist_rank: 0 |
|
local_rank: 0 |
|
dist_master_addr: localhost |
|
dist_master_port: 42653 |
|
dist_launcher: null |
|
multiprocessing_distributed: true |
|
unused_parameters: true |
|
sharded_ddp: false |
|
cudnn_enabled: true |
|
cudnn_benchmark: false |
|
cudnn_deterministic: true |
|
collect_stats: false |
|
write_collected_feats: false |
|
max_epoch: 50 |
|
patience: null |
|
val_scheduler_criterion: |
|
- valid |
|
- loss |
|
early_stopping_criterion: |
|
- valid |
|
- loss |
|
- min |
|
best_model_criterion: |
|
- - valid |
|
- loss |
|
- min |
|
- - train |
|
- loss |
|
- min |
|
keep_nbest_models: 10 |
|
nbest_averaging_interval: 0 |
|
grad_clip: 5.0 |
|
grad_clip_type: 2.0 |
|
grad_noise: false |
|
accum_grad: 2 |
|
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 |
|
use_lora: false |
|
save_lora_only: true |
|
lora_conf: {} |
|
pretrain_path: null |
|
init_param: |
|
- /scratch/bbjs/arora1/new_download_espnet_egs2/harpervalley/slu1_superb_onlyda/owsm_v3.1_ebf/exp/s2t_train_s2t_ebf_conv2d_size1024_e18_d18_piecewise_lr2e-4_warmup60k_flashattn_raw_bpe50000/valid.total_count.ave_5best.till45epoch.pth:encoder:encoder |
|
ignore_init_mismatch: false |
|
freeze_param: [] |
|
num_iters_per_epoch: null |
|
batch_size: 64 |
|
valid_batch_size: null |
|
batch_bins: 1000000 |
|
valid_batch_bins: null |
|
train_shape_file: |
|
- exp/slu_stats_raw_en_word_sp/train/speech_shape |
|
- exp/slu_stats_raw_en_word_sp/train/text_shape.word |
|
valid_shape_file: |
|
- exp/slu_stats_raw_en_word_sp/valid/speech_shape |
|
- exp/slu_stats_raw_en_word_sp/valid/text_shape.word |
|
batch_type: folded |
|
valid_batch_type: null |
|
fold_length: |
|
- 80000 |
|
- 150 |
|
sort_in_batch: descending |
|
shuffle_within_batch: false |
|
sort_batch: descending |
|
multiple_iterator: false |
|
chunk_length: 500 |
|
chunk_shift_ratio: 0.5 |
|
num_cache_chunks: 1024 |
|
chunk_excluded_key_prefixes: [] |
|
chunk_default_fs: null |
|
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/devel/wav.scp |
|
- speech |
|
- sound |
|
- - dump/raw/devel/text |
|
- text |
|
- text |
|
allow_variable_data_keys: false |
|
max_cache_size: 0.0 |
|
max_cache_fd: 32 |
|
allow_multi_rates: false |
|
valid_max_cache_size: null |
|
exclude_weight_decay: false |
|
exclude_weight_decay_conf: {} |
|
optim: adam |
|
optim_conf: |
|
lr: 1.0e-06 |
|
scheduler: warmuplr |
|
scheduler_conf: |
|
warmup_steps: 1000 |
|
token_list: |
|
- <blank> |
|
- <unk> |
|
- Neutral |
|
- Positive |
|
- Negative |
|
- <sos/eos> |
|
transcript_token_list: null |
|
two_pass: false |
|
pre_postencoder_norm: false |
|
init: null |
|
input_size: null |
|
ctc_conf: |
|
dropout_rate: 0.0 |
|
ctc_type: builtin |
|
reduce: true |
|
ignore_nan_grad: null |
|
zero_infinity: true |
|
brctc_risk_strategy: exp |
|
brctc_group_strategy: end |
|
brctc_risk_factor: 0.0 |
|
joint_net_conf: null |
|
use_preprocessor: true |
|
token_type: word |
|
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 |
|
frontend: default |
|
frontend_conf: |
|
n_fft: 512 |
|
win_length: 400 |
|
hop_length: 160 |
|
fs: 16k |
|
specaug: specaug |
|
specaug_conf: |
|
apply_time_warp: false |
|
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: 10 |
|
normalize: global_mvn |
|
normalize_conf: |
|
stats_file: /scratch/bbjs/arora1/new_download_espnet_egs2/harpervalley/slu1_superb_onlyda/owsm_v3.1_ebf/exp/s2t_stats_raw_bpe50000/train/feats_stats.npz |
|
model: espnet |
|
model_conf: |
|
ctc_weight: 0.0 |
|
lsm_weight: 0.1 |
|
length_normalized_loss: false |
|
superb_setup_encoder: true |
|
num_class: 3 |
|
ssl_input_size: 1024 |
|
weighted_sum: true |
|
extract_feats_in_collect_stats: false |
|
preencoder: null |
|
preencoder_conf: {} |
|
encoder: e_branchformer |
|
encoder_conf: |
|
output_size: 1024 |
|
attention_heads: 16 |
|
attention_layer_type: selfattn |
|
pos_enc_layer_type: abs_pos |
|
rel_pos_type: latest |
|
cgmlp_linear_units: 4096 |
|
cgmlp_conv_kernel: 31 |
|
use_linear_after_conv: false |
|
gate_activation: identity |
|
num_blocks: 18 |
|
dropout_rate: 0.1 |
|
positional_dropout_rate: 0.1 |
|
attention_dropout_rate: 0.1 |
|
input_layer: conv2d |
|
layer_drop_rate: 0.0 |
|
linear_units: 4096 |
|
positionwise_layer_type: linear |
|
use_ffn: true |
|
macaron_ffn: true |
|
merge_conv_kernel: 31 |
|
prepostencoder: null |
|
prepostencoder_conf: {} |
|
postencoder: null |
|
postencoder_conf: {} |
|
deliberationencoder: null |
|
deliberationencoder_conf: {} |
|
decoder: rnn |
|
decoder_conf: {} |
|
postdecoder: null |
|
postdecoder_conf: {} |
|
required: |
|
- output_dir |
|
- token_list |
|
version: '202310' |
|
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} |
|
} |
|
``` |
|
|
