A Flow-based Generative Network for Speech Synthesis
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.
Clone our repo and initialize submodule
git clone https://github.com/NVIDIA/waveglow.git git submodule init git submodule update
Install requirements (same as those from submodule)
pip3 install -r tacotron2/requirements.txt
python3 inference.py -f <(ls mel_spectrograms/*.pt) -w waveglow_old.pt -o . --is_fp16 -s 0.6
Download LJ Speech Data. In this example it's in
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
Train your WaveGlow networks
mkdir checkpoints python train.py -c config.json
For multi-GPU training replace
distributed.py. Only tested with single node and NCCL.
Make test set mel-spectrograms
python mel2samp.py -f test_files.txt -o . -c config.json
Do inference with your network
ls *.pt > mel_files.txt python3 inference.py -f mel_files.txt -w checkpoints/waveglow_10000 -o . --is_fp16 -s 0.6