Go to file
lifuchen 9b86f2008d fix a bug of transformertts when use data parallel. 2020-02-19 12:55:15 +00:00
examples fix a bug of transformertts when use data parallel. 2020-02-19 12:55:15 +00:00
images Add logo parakeet 2020-02-06 12:42:00 +08:00
notebooks fix import errors 2019-11-25 08:53:11 +00:00
parakeet deepvoice3: update logging functionalities 2020-02-17 14:53:37 +00:00
tests add_TransformerTTS 2019-12-16 09:04:22 +00:00
.gitignore move data.py and rename some files 2020-02-16 17:54:11 +00:00
LICENSE Init deepvoice3 commit 2019-11-13 14:22:46 +00:00
README.md modified README.md of install libsndfile1 2020-02-19 03:00:17 +00:00
setup.py Modified installation related content in README. 2020-02-18 09:42:24 +00:00

README.md

Parakeet

Parakeet aims to provide a flexible, efficient and state-of-the-art text-to-speech toolkit for the open-source community. It is built on Paddle Fluid dynamic graph, with the support of many influential TTS models proposed by Baidu Research and other academic institutions.


Installation

Install Paddlepaddle

See install for more details. This repo requires paddlepaddle's version is above 1.7.

Install Parakeet

# git clone this repo first
cd Parakeet
pip install -e .

Setup

Make sure libsndfile1 installed:

sudo apt-get install libsndfile1 

Install CMUdict for nltk

CMUdict from nltk is used to transform text into phonemes.

import nltk
nltk.download("punkt")
nltk.download("cmudict")

Supported models

Examples