|
--- |
|
tags: |
|
- espnet |
|
- audio |
|
- speaker-recognition |
|
language: multilingual |
|
datasets: |
|
- voxceleb |
|
license: cc-by-4.0 |
|
--- |
|
|
|
## ESPnet2 SPK model |
|
|
|
### `espnet/voxcelebs12_rawnet3` |
|
|
|
This model was trained by Jungjee using voxceleb 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 0c489a83607efb8e21331a9f01df21aac58c2a88 |
|
pip install -e . |
|
cd egs2/voxceleb/spk1 |
|
./run.sh --skip_data_prep false --skip_train true --download_model espnet/voxcelebs12_rawnet3 |
|
``` |
|
```python |
|
import numpy as np |
|
from espnet2.bin.spk_inference import Speech2Embedding |
|
|
|
# from uploaded models |
|
speech2spk_embed = Speech2Embedding.from_pretrained(model_tag="espnet/voxcelebs12_rawnet3") |
|
embedding = speech2spk_embed(np.zeros(16500)) |
|
|
|
# from checkpoints trained by oneself |
|
speech2spk_embed = Speech2Embedding(model_file="model.pth", train_config="config.yaml") |
|
embedding = speech2spk_embed(np.zeros(32000)) |
|
``` |
|
|
|
<!-- Generated by scripts/utils/show_spk_result.py --> |
|
# RESULTS |
|
## Environments |
|
date: 2023-11-21 12:43:27.293418 |
|
|
|
- python version: \`3.9.16 (main, Mar 8 2023, 14:00:05) [GCC 11.2.0]\` |
|
- espnet version: \`espnet 202310\` |
|
- pytorch version: \`pytorch 2.0.1\` |
|
|
|
| | Mean | Std | |
|
|---|---|---| |
|
| Target | -0.8015 | 0.1383 | |
|
| Non-target | 0.0836 | 0.0836 | |
|
|
|
| | EER(\%) | minDCF | |
|
|---|---|---| |
|
| | 0.739 | 0.05818 | |
|
|
|
## SPK config |
|
|
|
<details><summary>expand</summary> |
|
|
|
``` |
|
config: conf/tuning/train_rawnet3_best_trnVox12_emb192_amp_subcentertopk.yaml |
|
print_config: false |
|
log_level: INFO |
|
drop_last_iter: true |
|
dry_run: false |
|
iterator_type: category |
|
valid_iterator_type: sequence |
|
output_dir: exp/spk_train_rawnet3_best_trnVox12_emb192_amp_subcentertopk_raw_sp |
|
ngpu: 1 |
|
seed: 0 |
|
num_workers: 6 |
|
num_att_plot: 0 |
|
dist_backend: nccl |
|
dist_init_method: env:// |
|
dist_world_size: 4 |
|
dist_rank: 0 |
|
local_rank: 0 |
|
dist_master_addr: localhost |
|
dist_master_port: 56599 |
|
dist_launcher: null |
|
multiprocessing_distributed: true |
|
unused_parameters: false |
|
sharded_ddp: false |
|
cudnn_enabled: true |
|
cudnn_benchmark: true |
|
cudnn_deterministic: false |
|
collect_stats: false |
|
write_collected_feats: false |
|
max_epoch: 40 |
|
patience: null |
|
val_scheduler_criterion: |
|
- valid |
|
- loss |
|
early_stopping_criterion: |
|
- valid |
|
- loss |
|
- min |
|
best_model_criterion: |
|
- - valid |
|
- eer |
|
- min |
|
keep_nbest_models: 3 |
|
nbest_averaging_interval: 0 |
|
grad_clip: 9999 |
|
grad_clip_type: 2.0 |
|
grad_noise: false |
|
accum_grad: 1 |
|
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: 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: 512 |
|
valid_batch_size: 40 |
|
batch_bins: 1000000 |
|
valid_batch_bins: null |
|
train_shape_file: |
|
- exp/spk_stats_16k_sp/train/speech_shape |
|
valid_shape_file: |
|
- exp/spk_stats_16k_sp/valid/speech_shape |
|
batch_type: folded |
|
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: [] |
|
train_data_path_and_name_and_type: |
|
- - dump/raw/voxceleb12_devs_sp/wav.scp |
|
- speech |
|
- sound |
|
- - dump/raw/voxceleb12_devs_sp/utt2spk |
|
- spk_labels |
|
- text |
|
valid_data_path_and_name_and_type: |
|
- - dump/raw/voxceleb1_test/trial.scp |
|
- speech |
|
- sound |
|
- - dump/raw/voxceleb1_test/trial2.scp |
|
- speech2 |
|
- sound |
|
- - dump/raw/voxceleb1_test/trial_label |
|
- spk_labels |
|
- 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: 0.001 |
|
weight_decay: 5.0e-05 |
|
amsgrad: false |
|
scheduler: cosineannealingwarmuprestarts |
|
scheduler_conf: |
|
first_cycle_steps: 71280 |
|
cycle_mult: 1.0 |
|
max_lr: 0.001 |
|
min_lr: 5.0e-06 |
|
warmup_steps: 1000 |
|
gamma: 0.75 |
|
init: null |
|
use_preprocessor: true |
|
input_size: null |
|
target_duration: 3.0 |
|
spk2utt: dump/raw/voxceleb12_devs_sp/spk2utt |
|
spk_num: 21615 |
|
sample_rate: 16000 |
|
num_eval: 10 |
|
rir_scp: '' |
|
model_conf: |
|
extract_feats_in_collect_stats: false |
|
frontend: asteroid_frontend |
|
frontend_conf: |
|
sinc_stride: 16 |
|
sinc_kernel_size: 251 |
|
sinc_filters: 256 |
|
preemph_coef: 0.97 |
|
log_term: 1.0e-06 |
|
specaug: null |
|
specaug_conf: {} |
|
normalize: null |
|
normalize_conf: {} |
|
encoder: rawnet3 |
|
encoder_conf: |
|
model_scale: 8 |
|
ndim: 1024 |
|
output_size: 1536 |
|
pooling: chn_attn_stat |
|
pooling_conf: {} |
|
projector: rawnet3 |
|
projector_conf: |
|
output_size: 192 |
|
preprocessor: spk |
|
preprocessor_conf: |
|
target_duration: 3.0 |
|
sample_rate: 16000 |
|
num_eval: 5 |
|
noise_apply_prob: 0.5 |
|
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: 0.5 |
|
rir_scp: dump/raw/rirs.scp |
|
loss: aamsoftmax_sc_topk |
|
loss_conf: |
|
margin: 0.3 |
|
scale: 30 |
|
K: 3 |
|
mp: 0.06 |
|
k_top: 5 |
|
required: |
|
- output_dir |
|
version: '202308' |
|
distributed: true |
|
``` |
|
|
|
</details> |
|
|
|
|
|
|
|
### Citing |
|
|
|
```BibTex |
|
@article{jung2024espnet, |
|
title={ESPnet-SPK: full pipeline speaker embedding toolkit with reproducible recipes, self-supervised front-ends, and off-the-shelf models}, |
|
author={Jung, Jee-weon and Zhang, Wangyou and Shi, Jiatong and Aldeneh, Zakaria and Higuchi, Takuya and Theobald, Barry-John and Abdelaziz, Ahmed Hussen and Watanabe, Shinji}, |
|
journal={arXiv preprint arXiv:2401.17230}, |
|
year={2024} |
|
} |
|
@article{jung2022pushing, |
|
title={Pushing the limits of raw waveform speaker recognition}, |
|
author={Jung, Jee-weon and Kim, You Jin and Heo, Hee-Soo and Lee, Bong-Jin and Kwon, Youngki and Chung, Joon Son}, |
|
journal={Proc. Interspeech}, |
|
year={2022} |
|
} |
|
``` |
|
|
|
@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={Proc. Interspeech}, |
|
pages={2207--2211}, |
|
doi={10.21437/Interspeech.2018-1456}, |
|
url={http://dx.doi.org/10.21437/Interspeech.2018-1456} |
|
} |
|
``` |
|
|
|
|
