|
--- |
|
tags: |
|
- espnet |
|
- audio |
|
- codec |
|
language: multilingual |
|
datasets: |
|
- libritts |
|
license: cc-by-4.0 |
|
--- |
|
|
|
## ESPnet2 Codec model |
|
|
|
### `espnet/libritts_soundstream24k` |
|
|
|
This model was trained by ftshijt using libritts 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 734f1235b3dd3c444822b6337fbb2e417e75e321 |
|
pip install -e . |
|
cd egs2/libritts/codec1 |
|
./run.sh --skip_data_prep false --skip_train true --download_model espnet/libritts_soundstream24k |
|
``` |
|
|
|
|
|
|
|
## Codec config |
|
|
|
<details><summary>expand</summary> |
|
|
|
``` |
|
config: conf/train_soundstream4.yaml |
|
print_config: false |
|
log_level: INFO |
|
drop_last_iter: false |
|
dry_run: false |
|
iterator_type: chunk |
|
valid_iterator_type: null |
|
output_dir: exp/codec_train_soundstream4_raw_fs24000 |
|
ngpu: 1 |
|
seed: 777 |
|
num_workers: 1 |
|
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 |
|
cudnn_enabled: true |
|
cudnn_benchmark: false |
|
cudnn_deterministic: false |
|
collect_stats: false |
|
write_collected_feats: false |
|
max_epoch: 120 |
|
patience: null |
|
val_scheduler_criterion: |
|
- valid |
|
- loss |
|
early_stopping_criterion: |
|
- valid |
|
- loss |
|
- min |
|
best_model_criterion: |
|
- - valid |
|
- mel_loss |
|
- min |
|
- - train |
|
- mel_loss |
|
- min |
|
- - train |
|
- total_count |
|
- max |
|
keep_nbest_models: 5 |
|
nbest_averaging_interval: 0 |
|
grad_clip: -1 |
|
grad_clip_type: 2.0 |
|
grad_noise: false |
|
accum_grad: 1 |
|
no_forward_run: false |
|
resume: true |
|
train_dtype: float32 |
|
use_amp: false |
|
log_interval: 50 |
|
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 |
|
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: 5000 |
|
batch_size: 8 |
|
valid_batch_size: null |
|
batch_bins: 1000000 |
|
valid_batch_bins: null |
|
train_shape_file: |
|
- exp/codec_stats_raw/train/audio_shape |
|
valid_shape_file: |
|
- exp/codec_stats_raw/valid/audio_shape |
|
batch_type: unsorted |
|
valid_batch_type: null |
|
fold_length: |
|
- 256000 |
|
sort_in_batch: descending |
|
shuffle_within_batch: false |
|
sort_batch: descending |
|
multiple_iterator: false |
|
chunk_length: 24000 |
|
chunk_shift_ratio: 0.5 |
|
num_cache_chunks: 64 |
|
chunk_excluded_key_prefixes: [] |
|
chunk_default_fs: null |
|
train_data_path_and_name_and_type: |
|
- - dump/raw/train-clean-460/wav.scp |
|
- audio |
|
- sound |
|
valid_data_path_and_name_and_type: |
|
- - dump/raw/dev-clean/wav.scp |
|
- audio |
|
- sound |
|
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: 0.0002 |
|
betas: |
|
- 0.5 |
|
- 0.9 |
|
eps: 1.0e-09 |
|
weight_decay: 0.0 |
|
scheduler: exponentiallr |
|
scheduler_conf: |
|
gamma: 0.999875 |
|
optim2: adam |
|
optim2_conf: |
|
lr: 0.0002 |
|
betas: |
|
- 0.5 |
|
- 0.9 |
|
eps: 1.0e-09 |
|
weight_decay: 0.0 |
|
scheduler2: exponentiallr |
|
scheduler2_conf: |
|
gamma: 0.999875 |
|
generator_first: true |
|
model_conf: {} |
|
use_preprocessor: true |
|
codec: soundstream |
|
codec_conf: |
|
sampling_rate: 24000 |
|
generator_params: |
|
hidden_dim: 512 |
|
encdec_channels: 1 |
|
encdec_n_filters: 32 |
|
encdec_n_residual_layers: 3 |
|
encdec_ratios: |
|
- 8 |
|
- 5 |
|
- 4 |
|
- 2 |
|
encdec_activation: ELU |
|
encdec_activation_params: |
|
alpha: 1.0 |
|
encdec_norm: weight_norm |
|
encdec_kernel_size: 7 |
|
encdec_residual_kernel_size: 7 |
|
encdec_last_kernel_size: 7 |
|
encdec_dilation_base: 2 |
|
encdec_causal: false |
|
encdec_pad_mode: reflect |
|
encdec_true_skip: false |
|
encdec_compress: 2 |
|
encdec_lstm: 2 |
|
decoder_trim_right_ratio: 1.0 |
|
decoder_final_activation: null |
|
decoder_final_activation_params: null |
|
quantizer_n_q: 32 |
|
quantizer_bins: 1024 |
|
quantizer_decay: 0.99 |
|
quantizer_kmeans_init: true |
|
quantizer_kmeans_iters: 50 |
|
quantizer_threshold_ema_dead_code: 2 |
|
quantizer_target_bandwidth: |
|
- 2 |
|
- 4 |
|
- 8 |
|
- 16 |
|
- 32 |
|
sample_rate: 24000 |
|
discriminator_params: |
|
scales: 3 |
|
scale_downsample_pooling: AvgPool1d |
|
scale_downsample_pooling_params: |
|
kernel_size: 4 |
|
stride: 2 |
|
padding: 2 |
|
scale_discriminator_params: |
|
in_channels: 1 |
|
out_channels: 1 |
|
kernel_sizes: |
|
- 15 |
|
- 41 |
|
- 5 |
|
- 3 |
|
channels: 128 |
|
max_downsample_channels: 1024 |
|
max_groups: 16 |
|
bias: true |
|
downsample_scales: |
|
- 2 |
|
- 2 |
|
- 4 |
|
- 4 |
|
- 1 |
|
nonlinear_activation: LeakyReLU |
|
nonlinear_activation_params: |
|
negative_slope: 0.1 |
|
scale_follow_official_norm: false |
|
complexstft_discriminator_params: |
|
in_channels: 1 |
|
channels: 32 |
|
strides: |
|
- - 1 |
|
- 2 |
|
- - 2 |
|
- 2 |
|
- - 1 |
|
- 2 |
|
- - 2 |
|
- 2 |
|
- - 1 |
|
- 2 |
|
- - 2 |
|
- 2 |
|
chan_mults: |
|
- 1 |
|
- 2 |
|
- 4 |
|
- 4 |
|
- 8 |
|
- 8 |
|
n_fft: 1024 |
|
hop_length: 256 |
|
win_length: 1024 |
|
stft_normalized: false |
|
generator_adv_loss_params: |
|
average_by_discriminators: false |
|
loss_type: mse |
|
discriminator_adv_loss_params: |
|
average_by_discriminators: false |
|
loss_type: mse |
|
use_feat_match_loss: true |
|
feat_match_loss_params: |
|
average_by_discriminators: false |
|
average_by_layers: false |
|
include_final_outputs: true |
|
use_mel_loss: true |
|
mel_loss_params: |
|
range_start: 6 |
|
range_end: 11 |
|
window: hann |
|
n_mels: 80 |
|
fmin: 0 |
|
fmax: null |
|
log_base: null |
|
fs: 24000 |
|
lambda_quantization: 0.0 |
|
lambda_commit: 1.0 |
|
lambda_reconstruct: 1.0 |
|
lambda_adv: 1.0 |
|
lambda_mel: 45.0 |
|
lambda_feat_match: 2.0 |
|
cache_generator_outputs: true |
|
required: |
|
- output_dir |
|
version: '202402' |
|
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} |
|
} |
|
``` |
|
|
