/voice_cloning

Clone custom voices using Tacotron2 + WaveGlow + speech embedidng

Primary LanguageJupyter NotebookMIT LicenseMIT

Voice Cloning

Text to speech task that clones a custom voice in end-to-end manner.

We're using Tacotron 2, WaveGlow and speech embeddings(WIP) to acheive this.

alt

Install Dependencies

Simply run /usr/bin/bash setup.sh to create conda environment, install dependencies and activate it.

Checklist

To start, ensure you have the following

  • Anaconda or Miniconda is already installed
  • Linux distro (tested on Ubuntu 20.04) with NVidia GPU