language: en
thumbnail: null
tags:
- Source Separation
- Speech Separation
- Audio Source Separation
- WSJ0-3Mix
- SepFormer
- Transformer
license: apache-2.0
datasets:
- WSJ0-3Mix
metrics:
- SI-SNRi
- SDRi
SepFormer trained on WSJ0-3Mix
This repository provides all the necessary tools to perform audio source separation with a SepFormer model, implemented with SpeechBrain, and pretrained on WSJ0-3Mix dataset. For a better experience we encourage you to learn more about SpeechBrain. The model performance is 19.8 dB SI-SNRi on the test set of WSJ0-3Mix dataset.
| Release | Test-Set SI-SNRi | Test-Set SDRi |
|---|---|---|
| 09-03-21 | 19.8dB | 20.0dB |
Install SpeechBrain
First of all, please install SpeechBrain with the following command:
pip install speechbrain
Please notice that we encourage you to read our tutorials and learn more about SpeechBrain.
Perform source separation on your own audio file
from speechbrain.pretrained import SepformerSeparation as separator
import torchaudio
model = separator.from_hparams(source="speechbrain/sepformer-wsj03mix", savedir='pretrained_models/sepformer-wsj03mix')
est_sources = model.separate_file(path='speechbrain/sepformer-wsj03mix/test_mixture_3spks.wav')
torchaudio.save("source1hat.wav", est_sources[:, :, 0].detach().cpu(), 8000)
torchaudio.save("source2hat.wav", est_sources[:, :, 1].detach().cpu(), 8000)
torchaudio.save("source3hat.wav", est_sources[:, :, 2].detach().cpu(), 8000)
Inference on GPU
To perform inference on the GPU, add run_opts={"device":"cuda"} when calling the from_hparams method.
Training
The model was trained with SpeechBrain (fc2eabb7). To train it from scratch follows these steps:
- Clone SpeechBrain:
git clone https://github.com/speechbrain/speechbrain/
- Install it:
cd speechbrain
pip install -r requirements.txt
pip install -e .
- Run Training:
cd recipes/WSJ0Mix/separation
python train.py hparams/sepformer.yaml --data_folder=your_data_folder
Note: change num_spks to 3 in the yaml file.
You can find our training results (models, logs, etc) here.
Limitations
The SpeechBrain team does not provide any warranty on the performance achieved by this model when used on other datasets.
Referencing SpeechBrain
@misc{SB2021,
author = {Ravanelli, Mirco and Parcollet, Titouan and Rouhe, Aku and Plantinga, Peter and Rastorgueva, Elena and Lugosch, Loren and Dawalatabad, Nauman and Ju-Chieh, Chou and Heba, Abdel and Grondin, Francois and Aris, William and Liao, Chien-Feng and Cornell, Samuele and Yeh, Sung-Lin and Na, Hwidong and Gao, Yan and Fu, Szu-Wei and Subakan, Cem and De Mori, Renato and Bengio, Yoshua },
title = {SpeechBrain},
year = {2021},
publisher = {GitHub},
journal = {GitHub repository},
howpublished = {\url{https://github.com/speechbrain/speechbrain}},
}
Referencing SepFormer
@inproceedings{subakan2021attention,
title={Attention is All You Need in Speech Separation},
author={Cem Subakan and Mirco Ravanelli and Samuele Cornell and Mirko Bronzi and Jianyuan Zhong},
year={2021},
booktitle={ICASSP 2021}
}
About SpeechBrain
SpeechBrain is an open-source and all-in-one speech toolkit. It is designed to be simple, extremely flexible, and user-friendly. Competitive or state-of-the-art performance is obtained in various domains.
Website: https://speechbrain.github.io/