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 1200 kHz on an NVIDIA V100 GPU. 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 cd waveglow git submodule init git submodule update
-
Install requirements (pytorch 1.0 and others)
pip3 install -r requirements.txt
- Download our published model
- Download mel-spectrograms
- Generate audio
python3 inference.py -f <(ls mel_spectrograms/*.pt) -w waveglow_old.pt -o . --is_fp16 -s 0.6
N.b. use convert_model.py
to convert your older models to the current model
with fused residual and skip connections.
-
Download LJ Speech Data. In this example it's in
data/
-
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
train.py
withdistributed.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