malarinv
/
tacotron2
mirror of https://github.com/malarinv/tacotron2
1
0
Fork 0
Code Issues Releases Wiki Activity
147 Commits
10 Branches
0 Tags
3.3 MiB
Python 96.9%
Makefile 3.1%
 
 
Go to file
Malar 6d3679d760 relax scipy version 2021-07-02 23:21:45 +05:30
glow added glow as module 2019-11-29 00:20:01 +05:30
taco2 1. added rpyc server optional package 2020-03-05 16:59:55 +05:30
.gitignore 1. create a class for the tts api 2019-07-01 14:47:55 +05:30
AUTHORS.rst packaged taco2 2019-09-21 01:19:30 +05:30
HISTORY.rst 1. clean-up 2019-10-04 16:15:30 +05:30
MANIFEST.in packaged taco2 2019-09-21 01:19:30 +05:30
Makefile 1. remove unneeded files 2019-10-04 16:24:36 +05:30
README.md 1. clean-up 2019-10-04 16:15:30 +05:30
common.mk 1. remove unneeded files 2019-10-04 16:24:36 +05:30
glow_old.py 1. update waveglow 2019-10-04 15:27:59 +05:30
setup.cfg update setup.py artifact and add dunder files 2019-10-02 00:42:02 +05:30
setup.py relax scipy version 2021-07-02 23:21:45 +05:30

README.md

Taco2 TTS

image

Generates speech audio from text

Table of Contents

Features

  • TTS using Tacotron2

Installation

To install the packages and its dependencies run.

python setup.py install

or with pip

pip install .

The installation should work on Python 3.6 or newer. Untested on Python 2.7

Usage

from taco2.tts import TTSModel
tts_model = TTSModel("/path/to/tacotron2_model","/path/to/waveglow_model") # Loads the models
SPEECH_AUDIO = tts_model.synth_speech(TEXT) # Returns the wav buffer

If '/path/to/waveglow_model' is None Griffin-Lim vocoder will be used.