/RAVE

Official implementation of the RAVE model: a Realtime Audio Variational autoEncoder

Primary LanguagePythonMIT LicenseMIT

rave_logo

RAVE: Realtime Audio Variational autoEncoder

Official implementation of RAVE: A variational autoencoder for fast and high-quality neural audio synthesis (article link)

Installation

RAVE needs python 3.9. Install the dependencies using

pip install -r requirements.txt

Training

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.

Reconstructing audio

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.

MAX / MSP - PureData usage

[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 !

max_msp_screenshot

An audio example of the prior sampling patch is available in the docs/ folder.