/waveglow

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

Primary LanguagePythonApache License 2.0Apache-2.0

WaveGlow

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

Quick Start:

  1. Install requirements:
pip install -r requirements.txt
  1. 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
  1. Extract features: feature extracting pipeline is the same as tacotron

  2. Training with default hyperparams:

python train.py
  1. 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.