Official implementation of RAVE: A variational autoencoder for fast and high-quality neural audio synthesis (article link)
RAVE needs python 3.9
. Install the dependencies using
pip install -r requirements.txt
Both RAVE and the prior model are available in this repo. For most users we recommand to use the cli_helper.py
script, since it will generate a set of instructions allowing the training and export of both RAVE and the prior model on a specific dataset.
python cli_helper.py
However, if you want to customize even more your training, you can use the provided train_{rave, prior}.py
and export_{rave, prior}.py
scripts manually.
Once trained, you can reconstruct an entire folder containing wav files using
python reconstruct.py --ckpt /path/to/checkpoint --wav-folder /path/to/wav/folder
You can also export RAVE to a torchscript
file using export_rave.py
and use the encode
and decode
methods on tensors.
[NOT AVAILABLE YET]
RAVE and the prior model can be used in realtime inside max/msp, allowing creative interactions with both models. Code and details about this part of the project are not available yet, we are currently working on the corresponding article !
An audio example of the prior sampling patch is available in the docs/
folder.