🚀 SepFormer trained on WHAM! for speech enhancement (8k sampling frequency)
This repository offers all the essential tools for speech enhancement (denoising) using a SepFormer model. Implemented with SpeechBrain, it's pretrained on the WHAM! dataset at 8k sampling frequency. WHAM! is a version of the WSJ0 - Mix dataset with environmental noise and reverberation at 8k. For a better experience, we recommend learning more about SpeechBrain. The provided model achieves 14.35 dB SI - SNR on the test set of the WHAM! dataset.
✨ Features
- Tags: audio - to - audio, Speech Enhancement, WHAM!, SepFormer, Transformer, pytorch, speechbrain
- License: apache - 2.0
- Metrics: SI - SNR, PESQ
Property |
Details |
Model Type |
SepFormer |
Training Data |
WHAM! dataset (8k sampling frequency) |
Performance |
14.35 dB SI - SNR on the test set of WHAM! dataset |
Release |
Test - Set SI - SNR |
Test - Set PESQ |
01 - 12 - 21 |
14.35 |
3.07 |
📦 Installation
Install SpeechBrain
First, install SpeechBrain using the following command:
pip install speechbrain
💡 Usage Tip
We recommend reading our tutorials and learning more about SpeechBrain.
💻 Usage Examples
Basic Usage
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-wham-enhancement", savedir='pretrained_models/sepformer-wham-enhancement')
est_sources = model.separate_file(path='speechbrain/sepformer-wham-enhancement/example_wham.wav')
torchaudio.save("enhanced_wham.wav", est_sources[:, :, 0].detach().cpu(), 8000)
Advanced Usage
Inference on GPU
To perform inference on the GPU, add run_opts={"device":"cuda"}
when calling the from_hparams
method.
Training
The training script is currently being worked on in 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](https://drive.google.com/drive/folders/1bbQvaiN - R79M697NnekA7Rr0jIYtO6e3).
Limitations
⚠️ Important Note
The SpeechBrain team does not provide any warranty on the performance achieved by this model when used on other datasets.
📚 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},
}
📄 License
This project is licensed under the apache - 2.0 license.
About SpeechBrain
- Website: https://speechbrain.github.io/
- Code: https://github.com/speechbrain/speechbrain/
- HuggingFace: https://huggingface.co/speechbrain/