Home

Awesome

Tacotron-pytorch

A pytorch implementation of Tacotron: A Fully End-to-End Text-To-Speech Synthesis Model.

<img src="png/model.png">

Requirements

Data

I used LJSpeech dataset which consists of pairs of text script and wav files. The complete dataset (13,100 pairs) can be downloaded here. I referred https://github.com/keithito/tacotron for the preprocessing code.

File description

Training the network

Generate TTS wav file

Samples

Reference

Comments