https://github.com/shahules786/mayavoz

Pytorch based speech enhancement toolkit.
https://github.com/shahules786/mayavoz

audio-enhancement deep-learning denoiser pretrained-models python pytorch speech-enhancement

Last synced: about 1 month ago
JSON representation

Pytorch based speech enhancement toolkit.

• Host: GitHub
• URL: https://github.com/shahules786/mayavoz
• Owner: shahules786
• License: mit
• Created: 2022-08-20T04:44:35.000Z (almost 3 years ago)
• Default Branch: main
• Last Pushed: 2024-02-29T13:32:25.000Z (about 1 year ago)
• Last Synced: 2025-04-02T04:08:25.175Z (about 2 months ago)
• Topics: audio-enhancement, deep-learning, denoiser, pretrained-models, python, pytorch, speech-enhancement
• Language: Python
• Homepage:
• Size: 1.09 MB
• Stars: 336
• Watchers: 12
• Forks: 26
• Open Issues: 11
• Metadata Files:
  • Readme: README.md
  • Contributing: CONTRIBUTING.md
  • License: LICENSE

Awesome Lists containing this project

README

        


  



![GitHub Workflow Status](https://img.shields.io/github/actions/workflow/status/shahules786/mayavoz/ci.yaml?branch=main)

![GitHub](https://img.shields.io/github/license/shahules786/enhancer)

![GitHub issues](https://img.shields.io/github/issues/shahules786/enhancer?logo=GitHub)

![GitHub Repo stars](https://img.shields.io/github/stars/shahules786/enhancer?style=social)

mayavoz is a Pytorch-based opensource toolkit for speech enhancement. It is designed to save time for audio practioners & researchers. It provides easy to use pretrained speech enhancement models and facilitates highly customisable model training.

| **[Quick Start](#quick-start-fire)** | **[Installation](#installation)** | **[Tutorials](https://github.com/shahules786/enhancer/tree/main/notebooks)** | **[Available Recipes](#recipes)** | **[Demo](#demo)**

## Key features :key:

* Various pretrained models nicely integrated with [huggingface hub](https://huggingface.co/docs/hub/index) :hugs: that users can select and use without any hastle.

* :package: Ability to train and validate your own custom speech enhancement models with just under 10 lines of code!

* :magic_wand: A command line tool that facilitates training of highly customisable speech enhacement models from the terminal itself!

* :zap: Supports multi-gpu training integrated with [Pytorch Lightning](https://pytorchlightning.ai/).

* :shield: data augmentations integrated using [torch-augmentations](https://github.com/asteroid-team/torch-audiomentations)

## Demo

Noisy speech followed by enhanced version.

https://user-images.githubusercontent.com/25312635/203756185-737557f4-6e21-4146-aa2c-95da69d0de4c.mp4

## Quick Start :fire:

``` python

from mayavoz.models import Mayamodel

model = Mayamodel.from_pretrained("shahules786/mayavoz-waveunet-valentini-28spk")

model.enhance("noisy_audio.wav")

```

## Recipes

| Model     | Dataset      | STOI    | PESQ  | URL                           |

| :---:     |  :---:       | :---:   | :---: | :---:                         |

| WaveUnet  | Valentini-28spk   | 0.836   | 2.78  |  shahules786/mayavoz-waveunet-valentini-28spk      |

| Demucs    | Valentini-28spk   | 0.961   | 2.56  |  shahules786/mayavoz-demucs-valentini-28spk       |

| DCCRN     | Valentini-28spk   | 0.724   | 2.55  |  shahules786/mayavoz-dccrn-valentini-28spk         |

| Demucs     | MS-SNSD-20hrs  | 0.56 | 1.26  | shahules786/mayavoz-demucs-ms-snsd-20       |

Test scores are based on respective test set associated with train dataset.

**See [tutorials](/notebooks/) to train your custom model**

## Installation

Only Python 3.8+ is officially supported (though it might work with Python 3.7)

- With Pypi

```

pip install mayavoz

```

- With conda

```

conda env create -f environment.yml

conda activate mayavoz

```

- From source code

```

git clone url

cd mayavoz

pip install -e .

```

## Support

For commercial enquiries and scientific consulting, please [contact me](https://shahules786.github.io/).

### Acknowledgements

Sincere gratitude to [AMPLYFI](https://amplyfi.com/) for supporting this project.