|
--- |
|
tags: |
|
- espnet |
|
- audio |
|
- automatic-speech-recognition |
|
language: en |
|
datasets: |
|
- myst_ogi_cmu_kids |
|
license: cc-by-4.0 |
|
--- |
|
|
|
## ESPnet2 ASR model |
|
|
|
### `espnet/myst_ogi_cmu_kids_ctc_nolm` |
|
|
|
This model was trained by eric102004 using myst_ogi_cmu_kids 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 6f722aee1f9593572d5eddfd8cac7075b07cf9ca |
|
pip install -e . |
|
cd egs2/myst_ogi_cmu_kids/asr1 |
|
./run.sh --skip_data_prep false --skip_train true --download_model espnet/myst_ogi_cmu_kids_ctc_nolm |
|
``` |
|
|
|
<!-- Generated by scripts/utils/show_asr_result.sh --> |
|
# RESULTS |
|
## Environments |
|
- date: `Tue Feb 18 10:19:00 CST 2025` |
|
- python version: `3.12.3 | packaged by Anaconda, Inc. | (main, May 6 2024, 19:46:43) [GCC 11.2.0]` |
|
- espnet version: `espnet 202412` |
|
- pytorch version: `pytorch 2.4.0` |
|
- Git hash: `6f722aee1f9593572d5eddfd8cac7075b07cf9ca` |
|
- Commit date: `Thu Feb 6 22:32:07 2025 -0600` |
|
|
|
## exp/asr_train_asr_ctc_e_branchformer_e12_mlp1024_linear1024_lr002_raw_en_char_dur05_filter/decode_ctc_bs1_jibo_asr_model_valid.cer_ctc.ave_10best |
|
### WER |
|
|
|
|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err| |
|
|---|---|---|---|---|---|---|---|---| |
|
|data_jibo/dev|853|853|11.0|88.2|0.8|0.8|89.8|89.7| |
|
|data_jibo/test|1044|1043|11.4|87.7|0.9|1.5|90.1|89.4| |
|
|
|
### CER |
|
|
|
|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err| |
|
|---|---|---|---|---|---|---|---|---| |
|
|data_jibo/dev|853|2014|21.4|23.1|55.4|2.5|81.0|89.7| |
|
|data_jibo/test|1044|2767|19.9|21.5|58.6|2.1|82.2|89.4| |
|
|
|
### TER |
|
|
|
|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err| |
|
|---|---|---|---|---|---|---|---|---| |
|
## exp/asr_train_asr_ctc_e_branchformer_e12_mlp1024_linear1024_lr002_raw_en_char_dur05_filter/decode_ctc_bs1_asr_model_valid.cer_ctc.ave_10best |
|
### WER |
|
|
|
|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err| |
|
|---|---|---|---|---|---|---|---|---| |
|
|data_cmu/dev|237|2170|83.4|14.3|2.3|3.9|20.5|56.5| |
|
|data_cmu/test|475|4287|81.9|15.1|3.0|3.7|21.8|59.2| |
|
|data_jibo/dev|853|853|29.3|70.3|0.4|227.2|297.9|88.9| |
|
|data_jibo/test|1044|1043|29.1|70.9|0.0|318.5|389.4|87.7| |
|
|data_myst/dev|9037|153273|87.6|10.6|1.8|3.4|15.8|74.1| |
|
|data_myst/test|10311|182712|87.5|10.6|1.9|3.5|16.0|72.0| |
|
|data_ogi_scripted/dev|5426|15375|97.4|2.2|0.4|0.4|3.1|5.1| |
|
|data_ogi_scripted/test|15945|45419|96.6|2.7|0.6|0.7|4.1|6.9| |
|
|data_ogi_spon/dev|349|13561|74.4|22.0|3.6|4.1|29.6|97.7| |
|
|data_ogi_spon/test|1095|38811|75.6|21.1|3.2|4.8|29.2|96.8| |
|
|high_age/test|11196|56799|1.4|34.9|63.7|63.8|162.4|99.9| |
|
|low_age/test|5147|24262|2.2|37.7|60.1|62.3|160.0|98.7| |
|
|mid_age/test|26532|374547|11.2|45.6|43.2|44.7|133.6|98.8| |
|
|
|
### CER |
|
|
|
|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err| |
|
|---|---|---|---|---|---|---|---|---| |
|
|data_cmu/dev|237|11449|93.8|3.1|3.1|3.8|10.0|56.5| |
|
|data_cmu/test|475|22664|93.1|3.0|3.9|3.3|10.3|59.2| |
|
|data_jibo/dev|853|2014|69.2|28.0|2.8|472.7|503.5|88.9| |
|
|data_jibo/test|1044|2767|73.9|24.1|2.0|574.8|600.9|87.7| |
|
|data_myst/dev|9037|763728|95.9|2.1|2.1|3.3|7.4|74.1| |
|
|data_myst/test|10311|911898|95.8|2.0|2.1|3.4|7.6|72.0| |
|
|data_ogi_scripted/dev|5426|83141|98.5|0.6|0.9|0.5|2.0|5.1| |
|
|data_ogi_scripted/test|15945|244467|98.2|0.7|1.1|0.8|2.5|6.9| |
|
|data_ogi_spon/dev|349|58255|89.0|5.8|5.2|4.8|15.8|97.7| |
|
|data_ogi_spon/test|1095|165977|89.6|5.6|4.8|5.4|15.8|96.8| |
|
|high_age/test|11196|278522|18.8|20.2|61.1|60.5|141.8|99.9| |
|
|low_age/test|5147|117778|20.8|22.1|57.1|58.0|137.2|98.7| |
|
|mid_age/test|26532|1865279|34.6|20.1|45.3|46.4|111.8|98.8| |
|
|
|
### TER |
|
|
|
|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err| |
|
|---|---|---|---|---|---|---|---|---| |
|
|
|
## ASR config |
|
|
|
<details><summary>expand</summary> |
|
|
|
``` |
|
config: conf/tuning/train_asr_ctc_e_branchformer_e12_mlp1024_linear1024_lr002.yaml |
|
print_config: false |
|
log_level: INFO |
|
drop_last_iter: false |
|
dry_run: false |
|
iterator_type: sequence |
|
valid_iterator_type: null |
|
output_dir: exp/asr_train_asr_ctc_e_branchformer_e12_mlp1024_linear1024_lr002_raw_en_char_dur05_filter |
|
ngpu: 1 |
|
seed: 2022 |
|
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 |
|
use_deepspeed: false |
|
deepspeed_config: null |
|
static_graph: false |
|
gradient_as_bucket_view: false |
|
broadcast_buffers: true |
|
bucket_cap_mb: 25 |
|
compress_gradients: false |
|
cudnn_enabled: true |
|
cudnn_benchmark: false |
|
cudnn_deterministic: true |
|
use_tf32: false |
|
collect_stats: false |
|
write_collected_feats: false |
|
max_epoch: 70 |
|
patience: null |
|
val_scheduler_criterion: |
|
- valid |
|
- loss |
|
early_stopping_criterion: |
|
- valid |
|
- loss |
|
- min |
|
best_model_criterion: |
|
- - valid |
|
- cer_ctc |
|
- min |
|
keep_nbest_models: 10 |
|
nbest_averaging_interval: 0 |
|
grad_clip: 5.0 |
|
grad_clip_type: 2.0 |
|
grad_noise: false |
|
accum_grad: 4 |
|
no_forward_run: false |
|
resume: true |
|
train_dtype: float32 |
|
use_amp: true |
|
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_adapter: false |
|
adapter: lora |
|
save_strategy: all |
|
adapter_conf: {} |
|
pretrain_path: null |
|
init_param: [] |
|
ignore_init_mismatch: false |
|
freeze_param: [] |
|
num_iters_per_epoch: null |
|
batch_size: 20 |
|
valid_batch_size: null |
|
batch_bins: 16000000 |
|
valid_batch_bins: null |
|
category_sample_size: 10 |
|
train_shape_file: |
|
- exp/asr_stats_raw_en_char/train/speech_shape |
|
- exp/asr_stats_raw_en_char/train/text_shape.char |
|
valid_shape_file: |
|
- exp/asr_stats_raw_en_char/valid/speech_shape |
|
- exp/asr_stats_raw_en_char/valid/text_shape.char |
|
batch_type: numel |
|
valid_batch_type: null |
|
fold_length: |
|
- 80000 |
|
- 150 |
|
sort_in_batch: descending |
|
shuffle_within_batch: false |
|
sort_batch: descending |
|
multiple_iterator: false |
|
validate_each_iter_factory: true |
|
chunk_length: 500 |
|
chunk_shift_ratio: 0.5 |
|
num_cache_chunks: 1024 |
|
chunk_excluded_key_prefixes: [] |
|
chunk_default_fs: null |
|
chunk_max_abs_length: null |
|
chunk_discard_short_samples: true |
|
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 |
|
multi_task_dataset: false |
|
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: 0.002 |
|
weight_decay: 1.0e-06 |
|
scheduler: warmuplr |
|
scheduler_conf: |
|
warmup_steps: 15000 |
|
token_list: |
|
- <blank> |
|
- <unk> |
|
- <space> |
|
- E |
|
- T |
|
- A |
|
- O |
|
- I |
|
- N |
|
- H |
|
- S |
|
- R |
|
- L |
|
- D |
|
- U |
|
- W |
|
- M |
|
- C |
|
- G |
|
- Y |
|
- B |
|
- P |
|
- F |
|
- K |
|
- '''' |
|
- V |
|
- X |
|
- J |
|
- Z |
|
- Q |
|
- ',' |
|
- '-' |
|
- <sos/eos> |
|
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 |
|
use_lang_prompt: false |
|
use_nlp_prompt: false |
|
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: |
|
n_fft: 512 |
|
win_length: 400 |
|
hop_length: 160 |
|
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 |
|
- 27 |
|
num_freq_mask: 2 |
|
apply_time_mask: true |
|
time_mask_width_ratio_range: |
|
- 0.0 |
|
- 0.05 |
|
num_time_mask: 5 |
|
normalize: utterance_mvn |
|
normalize_conf: {} |
|
model: espnet |
|
model_conf: |
|
ctc_weight: 1.0 |
|
lsm_weight: 0.1 |
|
length_normalized_loss: false |
|
preencoder: null |
|
preencoder_conf: {} |
|
encoder: e_branchformer |
|
encoder_conf: |
|
output_size: 256 |
|
attention_heads: 4 |
|
attention_layer_type: rel_selfattn |
|
pos_enc_layer_type: rel_pos |
|
rel_pos_type: latest |
|
cgmlp_linear_units: 1024 |
|
cgmlp_conv_kernel: 31 |
|
use_linear_after_conv: false |
|
gate_activation: identity |
|
num_blocks: 12 |
|
dropout_rate: 0.1 |
|
positional_dropout_rate: 0.1 |
|
attention_dropout_rate: 0.1 |
|
input_layer: conv2d |
|
layer_drop_rate: 0.0 |
|
linear_units: 1024 |
|
positionwise_layer_type: linear |
|
use_ffn: true |
|
macaron_ffn: true |
|
merge_conv_kernel: 31 |
|
postencoder: null |
|
postencoder_conf: {} |
|
decoder: null |
|
decoder_conf: {} |
|
preprocessor: default |
|
preprocessor_conf: {} |
|
masker: null |
|
masker_conf: {} |
|
required: |
|
- output_dir |
|
- token_list |
|
version: '202412' |
|
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} |
|
} |
|
``` |
|
|