mayavoz is a Pytorch-based opensource toolkit for speech enhancement. It is designed to save time for audio researchers. Is provides easy to use pretrained audio 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]()** ## Key features :key: * Various pretrained models nicely integrated with huggingface :hugs: that users can select and use without any hastle. * :package: Ability to train and validation 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. ## Quick Start :fire: ``` python from mayavoz.models import Mayamodel model = Mayamodel.from_pretrained("shahules786/mayavoz-waveunet-valentini-28spk") model("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.