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.

Setup

Make sure the library libsndfile1 installed, e.g., on Ubuntu

sudo apt-get install libsndfile1

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 .

Install CMUdict for nltk

CMUdict from nltk is used to transform text into phonemes.

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

Related Research

• Deep Voice 3: Scaling Text-to-Speech with Convolutional Sequence Learning
• Neural Speech Synthesis with Transformer Network
• FastSpeech: Fast, Robust and Controllable Text to Speech.
• WaveFlow: A Compact Flow-based Model for Raw Audio

Examples

• Train a DeepVoice3 model with ljspeech dataset
• Train a TransformerTTS model with ljspeech dataset
• Train a FastSpeech model with ljspeech dataset
• Train a WaveFlow model with ljspeech dataset

Copyright and License

Parakeet is provided under the Apache-2.0 license.