|
|
--- |
|
|
tags: |
|
|
- espnet |
|
|
- audio |
|
|
- language-identification |
|
|
language: multilingual |
|
|
datasets: |
|
|
- geolid |
|
|
license: cc-by-4.0 |
|
|
--- |
|
|
|
|
|
## ESPnet2 LID model |
|
|
|
|
|
### `espnet/geolid_combined_shared_trainable` |
|
|
|
|
|
This model was trained by Qingzheng-Wang using geolid 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 77e4293952083b9e32bc19a5ddc19efe45e70e4a |
|
|
pip install -e . |
|
|
cd egs2/geolid/lid1 |
|
|
./run.sh --skip_data_prep false --skip_train true --download_model espnet/geolid_combined_shared_trainable |
|
|
``` |
|
|
|
|
|
|
|
|
|
|
|
## LID config |
|
|
|
|
|
<details><summary>expand</summary> |
|
|
|
|
|
``` |
|
|
config: /work/nvme/bbjs/qwang20/espnet/egs2/lid_delta/lid1/conf/mms_1b_all_no_filter_balanced_dataset/mms_ecapa_upcon_32_44_it0.4_sharedCondProj_butUpdate_50k_lr1e-5_datasetup0.3_backup_33epoch.yaml |
|
|
print_config: false |
|
|
log_level: INFO |
|
|
drop_last_iter: false |
|
|
dry_run: false |
|
|
iterator_type: category |
|
|
valid_iterator_type: category |
|
|
output_dir: exp_all_no_filter_raw/spk_mms_ecapa_upcon_32_44_it0.4_sharedCondProj_butUpdate_50k_lr1e-5_datasetup0.3_backup_33epoch_raw |
|
|
ngpu: 1 |
|
|
seed: 3702 |
|
|
num_workers: 8 |
|
|
num_att_plot: 0 |
|
|
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: true |
|
|
sharded_ddp: false |
|
|
use_deepspeed: false |
|
|
deepspeed_config: null |
|
|
cudnn_enabled: true |
|
|
cudnn_benchmark: true |
|
|
cudnn_deterministic: false |
|
|
use_tf32: false |
|
|
collect_stats: false |
|
|
write_collected_feats: false |
|
|
max_epoch: 33 |
|
|
patience: null |
|
|
val_scheduler_criterion: |
|
|
- valid |
|
|
- loss |
|
|
early_stopping_criterion: |
|
|
- valid |
|
|
- loss |
|
|
- min |
|
|
best_model_criterion: |
|
|
- - valid |
|
|
- accuracy |
|
|
- max |
|
|
keep_nbest_models: 2 |
|
|
nbest_averaging_interval: 0 |
|
|
grad_clip: 9999 |
|
|
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: 100 |
|
|
use_matplotlib: true |
|
|
use_tensorboard: true |
|
|
create_graph_in_tensorboard: false |
|
|
use_wandb: true |
|
|
wandb_project: lid |
|
|
wandb_id: null |
|
|
wandb_entity: qingzhew-carnegie-mellon-university |
|
|
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: 2000 |
|
|
batch_size: 20 |
|
|
valid_batch_size: null |
|
|
batch_bins: 1440000 |
|
|
valid_batch_bins: null |
|
|
category_sample_size: 10 |
|
|
train_shape_file: |
|
|
- exp_all_no_filter_raw/spk_stats_16k/train/speech_shape |
|
|
valid_shape_file: |
|
|
- exp_all_no_filter_raw/spk_stats_16k/valid/speech_shape |
|
|
batch_type: catpow_balance_dataset |
|
|
upsampling_factor: 0.5 |
|
|
language_upsampling_factor: 0.5 |
|
|
dataset_upsampling_factor: 0.3 |
|
|
dataset_scaling_factor: 1.2 |
|
|
max_batch_size: 6 |
|
|
valid_batch_type: null |
|
|
fold_length: |
|
|
- 120000 |
|
|
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 |
|
|
chunk_max_abs_length: null |
|
|
chunk_discard_short_samples: true |
|
|
train_data_path_and_name_and_type: |
|
|
- - dump/raw/train_all_no_filter_lang/wav.scp |
|
|
- speech |
|
|
- sound |
|
|
- - dump/raw/train_all_no_filter_lang/utt2spk |
|
|
- lid_labels |
|
|
- text |
|
|
valid_data_path_and_name_and_type: |
|
|
- - dump/raw/dev_ml_superb2_lang/wav.scp |
|
|
- speech |
|
|
- sound |
|
|
- - dump/raw/dev_ml_superb2_lang/utt2spk |
|
|
- lid_labels |
|
|
- 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: 1.0e-05 |
|
|
betas: |
|
|
- 0.9 |
|
|
- 0.98 |
|
|
scheduler: tristagelr |
|
|
scheduler_conf: |
|
|
max_steps: 12500 |
|
|
warmup_ratio: 0.1 |
|
|
hold_ratio: 0.4 |
|
|
decay_ratio: 0.5 |
|
|
init_lr_scale: 0.6 |
|
|
final_lr_scale: 0.1 |
|
|
init: null |
|
|
use_preprocessor: true |
|
|
input_size: null |
|
|
target_duration: 3.0 |
|
|
spk2utt: dump/raw/train_all_no_filter_lang/spk2utt |
|
|
spk_num: 157 |
|
|
sample_rate: 16000 |
|
|
num_eval: 10 |
|
|
rir_scp: '' |
|
|
model: upstream_condition |
|
|
model_conf: |
|
|
lang2vec_conditioning_layers: |
|
|
- 32 |
|
|
- 36 |
|
|
- 40 |
|
|
- 44 |
|
|
lid_conditioning_layers: [] |
|
|
frozen_ecapa: false |
|
|
apply_intermediate_lang2vec_loss: true |
|
|
apply_intermediate_lid_class_loss: false |
|
|
apply_intermediate_lang2vec_condition: true |
|
|
apply_intermediate_lid_class_condition: false |
|
|
inter_lang2vec_loss_weight: 0.4 |
|
|
inter_lid_class_loss_weight: 0.0 |
|
|
cutoff_gradient_from_backbone: false |
|
|
cutoff_gradient_before_condtrans: true |
|
|
independent_module: true |
|
|
use_gate: false |
|
|
gate_type: null |
|
|
shared_conditioning_proj: true |
|
|
frontend: s3prl_condition |
|
|
frontend_conf: |
|
|
frontend_conf: |
|
|
upstream: hf_wav2vec2_condition |
|
|
path_or_url: facebook/mms-1b |
|
|
download_dir: ./hub |
|
|
multilayer_feature: true |
|
|
specaug: null |
|
|
specaug_conf: {} |
|
|
normalize: utterance_mvn |
|
|
normalize_conf: |
|
|
norm_vars: false |
|
|
encoder: ecapa_tdnn |
|
|
encoder_conf: |
|
|
model_scale: 8 |
|
|
ndim: 512 |
|
|
output_size: 1536 |
|
|
pooling: chn_attn_stat |
|
|
pooling_conf: {} |
|
|
projector: rawnet3 |
|
|
projector_conf: |
|
|
output_size: 192 |
|
|
encoder_condition: identity |
|
|
encoder_condition_conf: {} |
|
|
pooling_condition: chn_attn_stat |
|
|
pooling_condition_conf: {} |
|
|
projector_condition: rawnet3 |
|
|
projector_condition_conf: {} |
|
|
preprocessor: lid |
|
|
preprocessor_conf: |
|
|
fix_duration: false |
|
|
sample_rate: 16000 |
|
|
noise_apply_prob: 0.0 |
|
|
noise_info: |
|
|
- - 1.0 |
|
|
- dump/raw/musan_speech.scp |
|
|
- - 4 |
|
|
- 7 |
|
|
- - 13 |
|
|
- 20 |
|
|
- - 1.0 |
|
|
- dump/raw/musan_noise.scp |
|
|
- - 1 |
|
|
- 1 |
|
|
- - 0 |
|
|
- 15 |
|
|
- - 1.0 |
|
|
- dump/raw/musan_music.scp |
|
|
- - 1 |
|
|
- 1 |
|
|
- - 5 |
|
|
- 15 |
|
|
rir_apply_prob: 0.0 |
|
|
rir_scp: dump/raw/rirs.scp |
|
|
use_lang2vec: true |
|
|
lang2vec_type: geo |
|
|
loss: aamsoftmax_sc_topk_lang2vec |
|
|
loss_conf: |
|
|
margin: 0.5 |
|
|
scale: 30 |
|
|
K: 3 |
|
|
mp: 0.06 |
|
|
k_top: 5 |
|
|
lang2vec_dim: 299 |
|
|
lang2vec_type: geo |
|
|
lang2vec_weight: 0.2 |
|
|
required: |
|
|
- output_dir |
|
|
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} |
|
|
} |
|
|
``` |
|
|
|
