https://github.com/alphacep/tn2-wg

Tacotron2 + Waveglow Russian
https://github.com/alphacep/tn2-wg

Last synced: 11 months ago
JSON representation

Tacotron2 + Waveglow Russian

• Host: GitHub
• URL: https://github.com/alphacep/tn2-wg
• Owner: alphacep
• License: bsd-3-clause
• Archived: true
• Created: 2019-07-03T21:39:46.000Z (almost 7 years ago)
• Default Branch: master
• Last Pushed: 2020-01-11T18:36:54.000Z (over 6 years ago)
• Last Synced: 2024-11-02T20:29:42.401Z (over 1 year ago)
• Language: Python
• Size: 219 KB
• Stars: 43
• Watchers: 4
• Forks: 11
• Open Issues: 2
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
This code is based on NVIDIA implementation of Tacotron2 and Waveglow. It

is shaved to reduce dependencies and simplify code

https://github.com/NVIDIA/tacotron2

https://github.com/NVIDIA/waveglow

## Hardware requirements

For realtime synthesis it requires GPU card like GTX 1080 or RTX 2080

## Models

Download model here ~900Mb

http://alphacephei.com/tts/tacotron-models.tar.gz

Unpack them into folder tacotron-models here.

## Usage

Unpack models to models folder and run test.py, it will create the audio file test.wav