39 Forks
136 Stars
136 Watchers

Voice-synthesis

This repository is an implementation of Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis (SV2TTS) with a vocoder that works in real-time. SV2TTS is a three-stage deep learning framework that allows to create a numerical representation of a voice from a few seconds of audio, and to use it to condition a text-to-speech model trained to generalize to new voices.

How to download and setup Voice-synthesis

Open terminal and run command
git clone https://github.com/smoke-trees/Voice-synthesis.git
git clone is used to create a copy or clone of Voice-synthesis repositories. You pass git clone a repository URL.
it supports a few different network protocols and corresponding URL formats.

Also you may download zip file with Voice-synthesis https://github.com/smoke-trees/Voice-synthesis/archive/master.zip

Or simply clone Voice-synthesis with SSH
[email protected]:smoke-trees/Voice-synthesis.git

If you have some problems with Voice-synthesis

You may open issue on Voice-synthesis support forum (system) here: https://github.com/smoke-trees/Voice-synthesis/issues