|
--- |
|
tags: |
|
- espnet |
|
- audio |
|
- automatic-speech-recognition |
|
language: en |
|
datasets: |
|
- tedlium2 |
|
license: cc-by-4.0 |
|
--- |
|
|
|
## ESPnet2 ASR model |
|
|
|
### `pyf98/tedlium2_transducer_e_branchformer` |
|
|
|
This model was trained by Yifan Peng using tedlium2 recipe in [espnet](https://github.com/espnet/espnet/). |
|
|
|
References: |
|
- [E-Branchformer: Branchformer with Enhanced merging for speech recognition (SLT 2022)](https://arxiv.org/abs/2210.00077) |
|
- [Branchformer: Parallel MLP-Attention Architectures to Capture Local and Global Context for Speech Recognition and Understanding (ICML 2022)](https://proceedings.mlr.press/v162/peng22a.html) |
|
|
|
### 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 478ba004e114e7862b05fb01112de7f7e1da3996 |
|
pip install -e . |
|
cd egs2/tedlium2/asr1 |
|
./run.sh --skip_data_prep false --skip_train true --download_model pyf98/tedlium2_transducer_e_branchformer |
|
``` |
|
|
|
<!-- Generated by scripts/utils/show_asr_result.sh --> |
|
# RESULTS |
|
## Environments |
|
- date: `Thu Feb 9 01:29:33 CST 2023` |
|
- python version: `3.9.15 (main, Nov 24 2022, 14:31:59) [GCC 11.2.0]` |
|
- espnet version: `espnet 202301` |
|
- pytorch version: `pytorch 1.13.1` |
|
- Git hash: `478ba004e114e7862b05fb01112de7f7e1da3996` |
|
- Commit date: `Tue Feb 7 00:50:49 2023 +0000` |
|
|
|
## asr_train_asr_transducer_e_branchformer_e12_raw_en_bpe500_sp |
|
### WER |
|
|
|
|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err| |
|
|---|---|---|---|---|---|---|---|---| |
|
|decode_asr_transducer_asr_model_valid.loss.ave/dev|466|14671|93.4|4.3|2.3|1.0|7.6|71.7| |
|
|decode_asr_transducer_asr_model_valid.loss.ave/test|1155|27500|93.6|4.0|2.4|1.0|7.4|63.5| |
|
|
|
### CER |
|
|
|
|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err| |
|
|---|---|---|---|---|---|---|---|---| |
|
|decode_asr_transducer_asr_model_valid.loss.ave/dev|466|78259|97.1|0.9|2.0|0.9|3.8|71.7| |
|
|decode_asr_transducer_asr_model_valid.loss.ave/test|1155|145066|97.1|0.9|2.1|0.9|3.9|63.5| |
|
|
|
### TER |
|
|
|
|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err| |
|
|---|---|---|---|---|---|---|---|---| |
|
|decode_asr_transducer_asr_model_valid.loss.ave/dev|466|28296|94.7|3.1|2.3|0.8|6.2|71.7| |
|
|decode_asr_transducer_asr_model_valid.loss.ave/test|1155|52113|95.1|2.6|2.2|0.9|5.8|63.5| |
|
|
|
## ASR config |
|
|
|
<details><summary>expand</summary> |
|
|
|
``` |
|
config: conf/tuning/train_asr_transducer_e_branchformer_e12.yaml |
|
print_config: false |
|
log_level: INFO |
|
dry_run: false |
|
iterator_type: sequence |
|
output_dir: exp/asr_train_asr_transducer_e_branchformer_e12_raw_en_bpe500_sp |
|
ngpu: 1 |
|
seed: 2022 |
|
num_workers: 6 |
|
num_att_plot: 3 |
|
dist_backend: nccl |
|
dist_init_method: env:// |
|
dist_world_size: 2 |
|
dist_rank: 0 |
|
local_rank: 0 |
|
dist_master_addr: localhost |
|
dist_master_port: 45753 |
|
dist_launcher: null |
|
multiprocessing_distributed: true |
|
unused_parameters: false |
|
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 |
|
keep_nbest_models: 10 |
|
nbest_averaging_interval: 0 |
|
grad_clip: 5.0 |
|
grad_clip_type: 2.0 |
|
grad_noise: false |
|
accum_grad: 5 |
|
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: 20 |
|
valid_batch_size: null |
|
batch_bins: 10000000 |
|
valid_batch_bins: null |
|
train_shape_file: |
|
- exp/asr_stats_raw_en_bpe500_sp/train/speech_shape |
|
- exp/asr_stats_raw_en_bpe500_sp/train/text_shape.bpe |
|
valid_shape_file: |
|
- exp/asr_stats_raw_en_bpe500_sp/valid/speech_shape |
|
- exp/asr_stats_raw_en_bpe500_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_sp/wav.scp |
|
- speech |
|
- kaldi_ark |
|
- - dump/raw/train_sp/text |
|
- text |
|
- text |
|
valid_data_path_and_name_and_type: |
|
- - dump/raw/dev/wav.scp |
|
- speech |
|
- kaldi_ark |
|
- - 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: 0.002 |
|
weight_decay: 1.0e-06 |
|
scheduler: warmuplr |
|
scheduler_conf: |
|
warmup_steps: 15000 |
|
token_list: |
|
- <blank> |
|
- <unk> |
|
- s |
|
- ▁the |
|
- t |
|
- ▁a |
|
- ▁and |
|
- ▁to |
|
- d |
|
- e |
|
- ▁of |
|
- '''' |
|
- n |
|
- ing |
|
- ▁in |
|
- ▁i |
|
- ▁that |
|
- i |
|
- a |
|
- l |
|
- p |
|
- m |
|
- y |
|
- o |
|
- ▁it |
|
- ▁we |
|
- c |
|
- u |
|
- ▁you |
|
- ed |
|
- ▁ |
|
- r |
|
- ▁is |
|
- re |
|
- ▁this |
|
- ar |
|
- g |
|
- ▁so |
|
- al |
|
- b |
|
- ▁s |
|
- or |
|
- ▁f |
|
- ▁c |
|
- in |
|
- k |
|
- f |
|
- ▁for |
|
- ic |
|
- er |
|
- le |
|
- ▁be |
|
- ▁do |
|
- ▁re |
|
- ve |
|
- ▁e |
|
- ▁w |
|
- ▁was |
|
- es |
|
- ▁they |
|
- ly |
|
- h |
|
- ▁on |
|
- v |
|
- ▁are |
|
- ri |
|
- ▁have |
|
- an |
|
- ▁what |
|
- ▁with |
|
- ▁t |
|
- w |
|
- ur |
|
- it |
|
- ent |
|
- ▁can |
|
- ▁he |
|
- ▁but |
|
- ra |
|
- ce |
|
- ▁me |
|
- ▁b |
|
- ▁ma |
|
- ▁p |
|
- ll |
|
- ▁st |
|
- ▁one |
|
- 'on' |
|
- ▁about |
|
- th |
|
- ▁de |
|
- en |
|
- ▁all |
|
- ▁not |
|
- il |
|
- ▁g |
|
- ch |
|
- at |
|
- ▁there |
|
- ▁mo |
|
- ter |
|
- ation |
|
- tion |
|
- ▁at |
|
- ▁my |
|
- ro |
|
- ▁as |
|
- te |
|
- ▁le |
|
- ▁con |
|
- ▁like |
|
- ▁people |
|
- ▁or |
|
- ▁an |
|
- el |
|
- ▁if |
|
- ▁from |
|
- ver |
|
- ▁su |
|
- ▁co |
|
- ate |
|
- ▁these |
|
- ol |
|
- ci |
|
- ▁now |
|
- ▁see |
|
- ▁out |
|
- ▁our |
|
- ion |
|
- ▁know |
|
- ect |
|
- ▁just |
|
- as |
|
- ▁ex |
|
- ▁ch |
|
- ▁d |
|
- ▁when |
|
- ▁very |
|
- ▁think |
|
- ▁who |
|
- ▁because |
|
- ▁go |
|
- ▁up |
|
- ▁us |
|
- ▁pa |
|
- ▁no |
|
- ies |
|
- ▁di |
|
- ▁ho |
|
- om |
|
- ive |
|
- ▁get |
|
- id |
|
- ▁o |
|
- ▁hi |
|
- un |
|
- ▁how |
|
- ▁by |
|
- ir |
|
- et |
|
- ck |
|
- ity |
|
- ▁po |
|
- ul |
|
- ▁which |
|
- ▁mi |
|
- ▁some |
|
- z |
|
- ▁sp |
|
- ▁un |
|
- ▁going |
|
- ▁pro |
|
- ist |
|
- ▁se |
|
- ▁look |
|
- ▁time |
|
- ment |
|
- de |
|
- ▁more |
|
- ▁had |
|
- ng |
|
- ▁would |
|
- ge |
|
- la |
|
- ▁here |
|
- ▁really |
|
- x |
|
- ▁your |
|
- ▁them |
|
- us |
|
- me |
|
- ▁en |
|
- ▁two |
|
- ▁k |
|
- ▁li |
|
- ▁world |
|
- ne |
|
- ow |
|
- ▁way |
|
- ▁want |
|
- ▁work |
|
- ▁don |
|
- ▁lo |
|
- ▁fa |
|
- ▁were |
|
- ▁their |
|
- age |
|
- vi |
|
- ▁ha |
|
- ac |
|
- der |
|
- est |
|
- ▁bo |
|
- am |
|
- ▁other |
|
- able |
|
- ▁actually |
|
- ▁sh |
|
- ▁make |
|
- ▁ba |
|
- ▁la |
|
- ine |
|
- ▁into |
|
- ▁where |
|
- ▁could |
|
- ▁comp |
|
- ting |
|
- ▁has |
|
- ▁will |
|
- ▁ne |
|
- j |
|
- ical |
|
- ally |
|
- ▁vi |
|
- ▁things |
|
- ▁te |
|
- igh |
|
- ▁say |
|
- ▁years |
|
- ers |
|
- ▁ra |
|
- ther |
|
- ▁than |
|
- ru |
|
- ▁ro |
|
- op |
|
- ▁did |
|
- ▁any |
|
- ▁new |
|
- ound |
|
- ig |
|
- ▁well |
|
- mo |
|
- ▁she |
|
- ▁na |
|
- ▁been |
|
- he |
|
- ▁thousand |
|
- ▁car |
|
- ▁take |
|
- ▁right |
|
- ▁then |
|
- ▁need |
|
- ▁start |
|
- ▁hundred |
|
- ▁something |
|
- ▁over |
|
- ▁com |
|
- ia |
|
- ▁kind |
|
- um |
|
- if |
|
- ▁those |
|
- ▁first |
|
- ▁pre |
|
- ta |
|
- ▁said |
|
- ize |
|
- end |
|
- ▁even |
|
- ▁thing |
|
- one |
|
- ▁back |
|
- ite |
|
- ▁every |
|
- ▁little |
|
- ry |
|
- ▁life |
|
- ▁much |
|
- ke |
|
- ▁also |
|
- ▁most |
|
- ant |
|
- per |
|
- ▁three |
|
- ▁come |
|
- ▁lot |
|
- ance |
|
- ▁got |
|
- ▁talk |
|
- ▁per |
|
- ▁inter |
|
- ▁sa |
|
- ▁use |
|
- ▁mu |
|
- ▁part |
|
- ish |
|
- ence |
|
- ▁happen |
|
- ▁bi |
|
- ▁mean |
|
- ough |
|
- ▁qu |
|
- ▁bu |
|
- ▁day |
|
- ▁ga |
|
- ▁only |
|
- ▁many |
|
- ▁different |
|
- ▁dr |
|
- ▁th |
|
- ▁show |
|
- ful |
|
- ▁down |
|
- ated |
|
- ▁good |
|
- ▁tra |
|
- ▁around |
|
- ▁idea |
|
- ▁human |
|
- ous |
|
- ▁put |
|
- ▁through |
|
- ▁five |
|
- ▁why |
|
- ▁change |
|
- ▁real |
|
- ff |
|
- ible |
|
- ▁fact |
|
- ▁same |
|
- ▁jo |
|
- ▁live |
|
- ▁year |
|
- ▁problem |
|
- ▁ph |
|
- ▁four |
|
- ▁give |
|
- ▁big |
|
- ▁tell |
|
- ▁great |
|
- ▁try |
|
- ▁va |
|
- ▁ru |
|
- ▁system |
|
- ▁six |
|
- ▁plan |
|
- ▁place |
|
- ▁build |
|
- ▁called |
|
- ▁again |
|
- ▁point |
|
- ▁twenty |
|
- ▁percent |
|
- ▁nine |
|
- ▁find |
|
- ▁app |
|
- ▁after |
|
- ▁long |
|
- ▁eight |
|
- ▁imp |
|
- ▁gene |
|
- ▁design |
|
- ▁today |
|
- ▁should |
|
- ▁made |
|
- ious |
|
- ▁came |
|
- ▁learn |
|
- ▁last |
|
- ▁own |
|
- way |
|
- ▁turn |
|
- ▁seven |
|
- ▁high |
|
- ▁question |
|
- ▁person |
|
- ▁brain |
|
- ▁important |
|
- ▁another |
|
- ▁thought |
|
- ▁trans |
|
- ▁create |
|
- ness |
|
- ▁hu |
|
- ▁power |
|
- ▁act |
|
- land |
|
- ▁play |
|
- ▁sort |
|
- ▁old |
|
- ▁before |
|
- ▁course |
|
- ▁understand |
|
- ▁feel |
|
- ▁might |
|
- ▁each |
|
- ▁million |
|
- ▁better |
|
- ▁together |
|
- ▁ago |
|
- ▁example |
|
- ▁help |
|
- ▁story |
|
- ▁next |
|
- ▁hand |
|
- ▁school |
|
- ▁water |
|
- ▁develop |
|
- ▁technology |
|
- que |
|
- ▁second |
|
- ▁grow |
|
- ▁still |
|
- ▁cell |
|
- ▁believe |
|
- ▁number |
|
- ▁small |
|
- ▁between |
|
- qui |
|
- ▁data |
|
- ▁become |
|
- ▁america |
|
- ▁maybe |
|
- ▁space |
|
- ▁project |
|
- ▁organ |
|
- ▁vo |
|
- ▁children |
|
- ▁book |
|
- graph |
|
- ▁open |
|
- ▁fifty |
|
- ▁picture |
|
- ▁health |
|
- ▁thirty |
|
- ▁africa |
|
- ▁reason |
|
- ▁large |
|
- ▁hard |
|
- ▁computer |
|
- ▁always |
|
- ▁sense |
|
- ▁money |
|
- ▁women |
|
- ▁everything |
|
- ▁information |
|
- ▁country |
|
- ▁teach |
|
- ▁energy |
|
- ▁experience |
|
- ▁food |
|
- ▁process |
|
- qua |
|
- ▁interesting |
|
- ▁future |
|
- ▁science |
|
- q |
|
- '0' |
|
- '5' |
|
- '6' |
|
- '9' |
|
- '3' |
|
- '8' |
|
- '4' |
|
- N |
|
- A |
|
- '7' |
|
- S |
|
- G |
|
- F |
|
- R |
|
- L |
|
- U |
|
- E |
|
- T |
|
- H |
|
- _ |
|
- B |
|
- D |
|
- J |
|
- M |
|
- ă |
|
- ō |
|
- ť |
|
- '2' |
|
- '-' |
|
- '1' |
|
- C |
|
- <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 |
|
joint_net_conf: |
|
joint_space_size: 320 |
|
use_preprocessor: true |
|
token_type: bpe |
|
bpemodel: data/en_token_list/bpe_unigram500/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' |
|
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: global_mvn |
|
normalize_conf: |
|
stats_file: exp/asr_stats_raw_en_bpe500_sp/train/feats_stats.npz |
|
model: espnet |
|
model_conf: |
|
ctc_weight: 0.3 |
|
report_cer: false |
|
report_wer: 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: transducer |
|
decoder_conf: |
|
rnn_type: lstm |
|
num_layers: 1 |
|
hidden_size: 256 |
|
dropout: 0.1 |
|
dropout_embed: 0.2 |
|
preprocessor: default |
|
preprocessor_conf: {} |
|
required: |
|
- output_dir |
|
- token_list |
|
version: '202301' |
|
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} |
|
} |
|
``` |
|
|
