metadata

language: en
thumbnail: null
tags:
  - Source Separation
  - Speech Separation
  - Audio Source Separation
  - WHAM!
  - SepFormer
  - Transformer
license: apache-2.0
datasets:
  - WHAM!
metrics:
  - SI-SNRi
  - SDRi

SepFormer trained on WHAM!

This repository provides all the necessary tools to perform audio source separation with a SepFormer model, implemented with SpeechBrain, and pretrained on WHAM! dataset. For a better experience we encourage you to learn more about SpeechBrain. The given model performance is 16.3 dB SI-SNRi on the test set of WHAM! dataset.

Release	Test-Set SI-SNRi	Test-Set SDRi
09-03-21	16.3 dB	16.7 dB

Install SpeechBrain

First of all, please install SpeechBrain with the following command:

pip install \\we hide ! SpeechBrain is still private :p

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 separator
import torchaudio

model = separator.from_hparams(source="speechbrain/sepformer-wham")

mix, fs = torchaudio.load("yourspeechbrainpath/samples/audio_samples/test_mixture.wav")

est_sources = model.separate(mix)
est_sources = est_sources / est_sources.max(dim=1, keepdim=True)[0]

torchaudio.save("source1hat.wav", est_sources[:, :, 0].detach().cpu(), 8000)
torchaudio.save("source2hat.wav", est_sources[:, :, 1].detach().cpu(), 8000)

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}
}