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 | Installation | Tutorials | Available Recipes | Demo

Key features :key:

• Various pretrained models nicely integrated with huggingface hub :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.
• :shield: data augmentations integrated using torch-augmentations

Demo

Noisy speech followed by enhanced version.

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

Quick Start :fire:

from mayavoz.models import Mayamodel

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

Recipes

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

See tutorials 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.

Acknowledgements

Sincere gratitude to AMPLYFI for supporting this project.