Uberduck is a tool for fun and creativity with neural text-to-speech. This repository will get you creating your own speech synthesis models. Please see our training and synthesis notebooks. Please reach out for help and contribute!
The models in this repository used in production are the Tacotron2, SO-VITS-SVC, zero-shot RADTTS, and HiFi-GAN. Training code is included for Tacotron2, RADTTS, and HiFi-GAN. Other goodies include fill-populating inference, additional languages, and Torchmoji emotional encoding.
Download models to fine-tune from here. The notebooks are the easiest ways to try these out.
If you want to install on your own machine, create a virtual environment and install like
pip install git+https://github.com/uberduck-ai/uberduck-ml-dev.gitPlease see the tests subfolder for examples of up to date training and inference invocation.
We love contributions! Feel free to reach out to discuss contribution.
To install in development mode, run
pip install pre-commit black # format your code on commit by installing black!
git clone git@github.com:uberduck-ai/uberduck-ml-dev.git
cd uberduck-ml-dev
pre-commit install # Install required Git hooks
python setup.py develop # Install the libraryIn an environment or image with uberduck-ml-dev installed in the uberduck-ml-dev root folder, run
python -m pytest