Home

This documentation web page aims to fully cover the end-to-end pipeline of using TensorFlowTTS to train and deploy text-to-speech models. Since the original repository seems to be inactive, these set of tutorials will work on this fork developed by Wilson Wongso which contains new features.

Newly Added Features

• IPA-based Acoustic models for English and Indonesian
• LightSpeech

Guides

• Installing TensorFlowTTS
• Train LightSpeech & Multi-band MelGAN
• Convert and Infer Models on TensorFlowLite
• Implementing Custom Processor
• Adding British English Support to gruut