Sepformer Whamr Enhancement

🚀 SepFormer trained on WHAMR! for speech enhancement (8k sampling frequency)

This repository offers all the essential tools for speech enhancement (denoising + dereverberation) using a SepFormer model. The model is implemented with SpeechBrain and pretrained on the WHAMR! dataset at an 8k sampling frequency, which is a version of the WSJ0 - Mix dataset with environmental noise and reverberation at 8k. The model achieves a performance of 10.59 dB SI - SNR on the test set of the WHAMR! dataset.

🚀 Quick Start

This repository provides all the necessary tools to perform speech enhancement (denoising + dereverberation) with a SepFormer model, implemented with SpeechBrain, and pretrained on WHAMR! dataset with 8k sampling frequency. The given model performance is 10.59 dB SI - SNR on the test set of WHAMR! dataset.

✨ Features

• Audio - to - Audio: Capable of performing speech enhancement on audio files.
• Speech Enhancement: Effectively denoise and dereverberate speech.
• Trained on WHAMR!: Pretrained on the WHAMR! dataset with 8k sampling frequency.
• SepFormer Model: Based on the SepFormer architecture.
• SpeechBrain Implementation: Implemented using the SpeechBrain framework.

📦 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 speech enhancement on your own audio file

from speechbrain.inference.separation import SepformerSeparation as separator
import torchaudio

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

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

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

Inference on GPU

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

📚 Documentation

Training

The training script is currently being worked on an ongoing pull - request.

We will update the model card as soon as the PR is merged.

You can find our training results (models, logs, etc) here.

Limitations

⚠️ Important Note

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.

📚 References

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}
}

📋 About SpeechBrain

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