WaveGlow: A Flow-based Generative Network for Speech Synthesis

Sep 23, 2021 1 min read

WaveGlow

A PyTorch implementation of the WaveGlow: A Flow-based Generative Network for Speech Synthesis

Quick Start:

Install requirements:

pip install -r requirements.txt

Download dataset:

wget http://festvox.org/cmu_arctic/cmu_arctic/packed/cmu_us_slt_arctic-0.95-release.tar.bz2
tar xf cmu_us_slt_arctic-0.95-release.tar.bz2

Extract features: feature extracting pipeline is the same as
Training with default hyperparams:

python train.py

Synthesize from model:

python generate.py --checkpoint=/path/to/model --local_condition_file=/path/to/local_conditon

Notes:

This is not official implementation, some details are not necessarily correct.
Work in progress.

GitHub

Speech Network Text-to-Speech

John was the first writer to have joined pythonawesome.com. He has since then inculcated very effective writing and reviewing culture at pythonawesome which rivals have found impossible to imitate.