Sepformer Libri2mix

🚀 SepFormer trained on Libri2Mix

This repository offers all the essential tools for audio source separation using a SepFormer model implemented with SpeechBrain and pre - trained on the Libri2Mix dataset. Learning more about SpeechBrain can enhance your experience. The model achieves a performance of 20.6 dB on the test set of the Libri2Mix dataset.

✨ Features

• Source Separation: Perform audio source separation with a SepFormer model.
• Pretrained on Libri2Mix: The model is pretrained on the Libri2Mix dataset.
• Good Performance: Achieves 20.6 dB on the test set of the Libri2Mix dataset.

You can listen to example results obtained on the test set of WSJ0 - 2/3Mix through here.

📦 Installation

Install SpeechBrain

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

pip install speechbrain

💡 Usage Tip

We encourage you to read our tutorials and learn more about SpeechBrain.

💻 Usage Examples

Perform source separation on your own audio file

from speechbrain.pretrained import SepformerSeparation as separator
import torchaudio

model = separator.from_hparams(source="speechbrain/sepformer-libri2mix", savedir='pretrained_models/sepformer-libri2mix')

# for custom file, change path
est_sources = model.separate_file(path='speechbrain/sepformer-wsj02mix/test_mixture.wav') 

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

⚠️ Important Note

The system expects input recordings sampled at 8kHz (single channel). If your signal has a different sample rate, resample it (e.g, using torchaudio or sox) before using the interface.

Inference on GPU

To perform inference on the GPU, add run_opts={"device":"cuda"} when calling the from_hparams method.

🔧 Technical Details

Training

The model was trained with SpeechBrain (fc2eabb7). To train it from scratch follows these steps:

1. Clone SpeechBrain:

git clone https://github.com/speechbrain/speechbrain/

2. Install it:

cd speechbrain
pip install -r requirements.txt
pip install -e .

3. Run Training:

cd  recipes/Libri2Mix/separation
python train.py hparams/sepformer.yaml --data_folder=your_data_folder

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.

📄 License

This project is licensed under the Apache 2.0 License.

📚 Documentation

Referencing SpeechBrain

@misc{speechbrain,
  title={{SpeechBrain}: A General-Purpose Speech Toolkit},
  author={Mirco Ravanelli and Titouan Parcollet and Peter Plantinga and Aku Rouhe and Samuele Cornell and Loren Lugosch and Cem Subakan and Nauman Dawalatabad and Abdelwahab Heba and Jianyuan Zhong and Ju-Chieh Chou and Sung-Lin Yeh and Szu-Wei Fu and Chien-Feng Liao and Elena Rastorgueva and François Grondin and William Aris and Hwidong Na and Yan Gao and Renato De Mori and Yoshua Bengio},
  year={2021},
  eprint={2106.04624},
  archivePrefix={arXiv},
  primaryClass={eess.AS},
  note={arXiv:2106.04624}
}

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}
}

@article{subakan2023exploring,
  author={Subakan, Cem and Ravanelli, Mirco and Cornell, Samuele and Grondin, François and Bronzi, Mirko},
  journal={IEEE/ACM Transactions on Audio, Speech, and Language Processing}, 
  title={Exploring Self-Attention Mechanisms for Speech Separation}, 
  year={2023},
  volume={31},
  pages={2169-2180},
}

About SpeechBrain

• Website: https://speechbrain.github.io/
• Code: https://github.com/speechbrain/speechbrain/
• HuggingFace: https://huggingface.co/speechbrain/