/TensorFlowTTS

:stuck_out_tongue_closed_eyes: TensorFlowTTS: Real-Time State-of-the-art Speech Synthesis for Tensorflow 2 (supported including English, French, Korean, Chinese, German and Easy to adapt for other languages)

Primary LanguageJavaApache License 2.0Apache-2.0

Android Demo

This is a simple Android demo which will load converted FastSpeech2 and Multi-Band MelGAN modules to synthesize audio. In order to optimize the synthesize speed, two LinkedBlockingQueues have been implemented.

HOW-TO

  1. Import this project into Android Studio.
  2. Run the app!

LICENSE

The license use for this code is CC BY-NC 3.0. Please read the license carefully before you use it.

Contributors

Xuefeng Ding