toannhu / waveglow-1

A Flow-based Generative Network for Speech Synthesis

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool


WaveGlow: a Flow-based Generative Network for Speech Synthesis

Ryan Prenger, Rafael Valle, and Bryan Catanzaro

In our recent paper, we propose WaveGlow: a flow-based network capable of generating high quality speech from mel-spectrograms. WaveGlow combines insights from Glow and WaveNet in order to provide fast, efficient and high-quality audio synthesis, without the need for auto-regression. WaveGlow is implemented using only a single network, trained using only a single cost function: maximizing the likelihood of the training data, which makes the training procedure simple and stable.

Our PyTorch implementation produces audio samples at a rate of more than 500 kHz on an NVIDIA V100 GPU and Mean Opinion Scores show that it delivers audio quality as good as the best publicly available WaveNet implementation.

Visit our website for audio samples.


  1. Clone our repo and initialize submodule
git clone
git submodule init
git submodule update
  1. Install requirements (same as those from submodule) pip3 install -r tacotron2/requirements.txt

Generate audio with our pre-existing model

  1. Download our published model
  2. Download mel-spectrograms
  3. Generate audio python3 -f <(ls mel_spectrograms/*.pt) -w -o . --is_fp16 -s 0.6

Train your own model

  1. Download LJ Speech Data. In this example it's in data/
  2. Make a list of the file names to use for training/testing
ls data/*.wav | tail -n+10 > train_files.txt
ls data/*.wav | head -n10 > test_files.txt
  1. Train your WaveGlow networks
mkdir checkpoints
python -c config.json

For multi-GPU training replace with Only tested with single node and NCCL. 5. Make test set mel-spectrograms
python -f test_files.txt -o . -c config.json 6. Do inference with your network

ls *.pt > mel_files.txt
python3 -f mel_files.txt -w checkpoints/waveglow_10000 -o . --is_fp16 -s 0.6


A Flow-based Generative Network for Speech Synthesis

License:BSD 3-Clause "New" or "Revised" License


Language:Python 100.0%