|
--- |
|
tags: |
|
- espnet |
|
- audio |
|
- diarization |
|
language: noinfo |
|
datasets: |
|
- callhome |
|
license: cc-by-4.0 |
|
--- |
|
|
|
## ESPnet2 DIAR model |
|
|
|
### `YushiUeda/callhome_adapt_simu` |
|
|
|
This model was trained by YushiUeda using callhome recipe in [espnet](https://github.com/espnet/espnet/). |
|
|
|
### Demo: How to use in ESPnet2 |
|
|
|
```bash |
|
cd espnet |
|
git checkout 0cabe65afd362122e77b04e2e967986a91de0fd8 |
|
pip install -e . |
|
cd egs2/callhome/diar1 |
|
./run.sh --skip_data_prep false --skip_train true --download_model YushiUeda/callhome_adapt_simu |
|
``` |
|
|
|
|
|
|
|
## DIAR config |
|
|
|
<details><summary>expand</summary> |
|
|
|
``` |
|
config: conf/tuning/train_diar_eda_adapt.yaml |
|
print_config: false |
|
log_level: INFO |
|
dry_run: false |
|
iterator_type: sequence |
|
output_dir: exp/diar_train_diar_eda_adapt_simu |
|
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: 43777 |
|
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 |
|
- acc |
|
- max |
|
- - train |
|
- acc |
|
- max |
|
keep_nbest_models: 10 |
|
nbest_averaging_interval: 0 |
|
grad_clip: 5 |
|
grad_clip_type: 2.0 |
|
grad_noise: false |
|
accum_grad: 4 |
|
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: |
|
- exp/diar_train_diar_eda_5_raw/latest.pth |
|
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/diar_stats_8k/train/speech_shape |
|
- exp/diar_stats_8k/train/spk_labels_shape |
|
valid_shape_file: |
|
- exp/diar_stats_8k/valid/speech_shape |
|
- exp/diar_stats_8k/valid/spk_labels_shape |
|
batch_type: folded |
|
valid_batch_type: null |
|
fold_length: |
|
- 80000 |
|
- 800 |
|
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/simu/data/swb_sre_tr_ns1n2n3n4_beta2n2n5n9_100000/wav.scp |
|
- speech |
|
- sound |
|
- - dump/raw/simu/data/swb_sre_tr_ns1n2n3n4_beta2n2n5n9_100000/espnet_rttm |
|
- spk_labels |
|
- rttm |
|
valid_data_path_and_name_and_type: |
|
- - dump/raw/simu/data/swb_sre_cv_ns1n2n3n4_beta2n2n5n9_500/wav.scp |
|
- speech |
|
- sound |
|
- - dump/raw/simu/data/swb_sre_cv_ns1n2n3n4_beta2n2n5n9_500/espnet_rttm |
|
- spk_labels |
|
- rttm |
|
allow_variable_data_keys: false |
|
max_cache_size: 0.0 |
|
max_cache_fd: 32 |
|
valid_max_cache_size: null |
|
optim: adam |
|
optim_conf: |
|
lr: 0.0001 |
|
scheduler: null |
|
scheduler_conf: {} |
|
num_spk: 4 |
|
init: null |
|
input_size: null |
|
model_conf: |
|
attractor_weight: 1.0 |
|
use_preprocessor: true |
|
frontend: default |
|
frontend_conf: |
|
fs: 8k |
|
hop_length: 128 |
|
specaug: specaug |
|
specaug_conf: |
|
apply_time_warp: false |
|
apply_freq_mask: true |
|
freq_mask_width_range: |
|
- 0 |
|
- 30 |
|
num_freq_mask: 2 |
|
apply_time_mask: true |
|
time_mask_width_range: |
|
- 0 |
|
- 40 |
|
num_time_mask: 2 |
|
normalize: global_mvn |
|
normalize_conf: |
|
stats_file: exp/diar_stats_8k/train/feats_stats.npz |
|
encoder: transformer |
|
encoder_conf: |
|
input_layer: conv2d |
|
num_blocks: 4 |
|
linear_units: 512 |
|
dropout_rate: 0.1 |
|
output_size: 256 |
|
attention_heads: 4 |
|
attention_dropout_rate: 0.1 |
|
decoder: linear |
|
decoder_conf: {} |
|
label_aggregator: label_aggregator |
|
label_aggregator_conf: |
|
win_length: 1024 |
|
hop_length: 512 |
|
attractor: rnn |
|
attractor_conf: |
|
unit: 256 |
|
layer: 1 |
|
dropout: 0.0 |
|
attractor_grad: true |
|
required: |
|
- output_dir |
|
version: '202204' |
|
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} |
|
} |
|
``` |
|
|