metadata
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.
Demo: How to use in ESPnet2
Follow the ESPnet installation instructions if you haven't done that already.
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
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
- Commit date:
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
expand
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
Citing ESPnet
@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:
@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}
}