All Projects → caillonantoine → RAVE

caillonantoine / RAVE

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

Programming Languages

python
139335 projects - #7 most used programming language
shell
77523 projects

Projects that are alternatives of or similar to RAVE

Wgan
Tensorflow Implementation of Wasserstein GAN (and Improved version in wgan_v2)
Stars: ✭ 228 (-59.57%)
Mutual labels:  generative-model
PREREQ-IAAI-19
Inferring Concept Prerequisite Relations from Online Educational Resources (IAAI-19)
Stars: ✭ 22 (-96.1%)
Mutual labels:  generative-model
MMD-GAN
Improving MMD-GAN training with repulsive loss function
Stars: ✭ 82 (-85.46%)
Mutual labels:  generative-model
glico-learning-small-sample
Generative Latent Implicit Conditional Optimization when Learning from Small Sample ICPR 20'
Stars: ✭ 20 (-96.45%)
Mutual labels:  generative-model
trVAE
Conditional out-of-distribution prediction
Stars: ✭ 47 (-91.67%)
Mutual labels:  generative-model
eccv16 attr2img
Torch Implemention of ECCV'16 paper: Attribute2Image
Stars: ✭ 93 (-83.51%)
Mutual labels:  generative-model
Triple Gan
See Triple-GAN-V2 in PyTorch: https://github.com/taufikxu/Triple-GAN
Stars: ✭ 203 (-64.01%)
Mutual labels:  generative-model
GatedPixelCNNPyTorch
PyTorch implementation of "Conditional Image Generation with PixelCNN Decoders" by van den Oord et al. 2016
Stars: ✭ 68 (-87.94%)
Mutual labels:  generative-model
caffe-simnets
The SimNets Architecture's Implementation in Caffe
Stars: ✭ 13 (-97.7%)
Mutual labels:  generative-model
auto coding
A basic and simple tool for code auto completion
Stars: ✭ 42 (-92.55%)
Mutual labels:  generative-model
naru
Neural Relation Understanding: neural cardinality estimators for tabular data
Stars: ✭ 76 (-86.52%)
Mutual labels:  generative-model
InpaintNet
Code accompanying ISMIR'19 paper titled "Learning to Traverse Latent Spaces for Musical Score Inpaintning"
Stars: ✭ 48 (-91.49%)
Mutual labels:  generative-model
feed forward vqgan clip
Feed forward VQGAN-CLIP model, where the goal is to eliminate the need for optimizing the latent space of VQGAN for each input prompt
Stars: ✭ 135 (-76.06%)
Mutual labels:  generative-model
Sgan
Stacked Generative Adversarial Networks
Stars: ✭ 240 (-57.45%)
Mutual labels:  generative-model
cygen
Codes for CyGen, the novel generative modeling framework proposed in "On the Generative Utility of Cyclic Conditionals" (NeurIPS-21)
Stars: ✭ 44 (-92.2%)
Mutual labels:  generative-model
Tf Vqvae
Tensorflow Implementation of the paper [Neural Discrete Representation Learning](https://arxiv.org/abs/1711.00937) (VQ-VAE).
Stars: ✭ 226 (-59.93%)
Mutual labels:  generative-model
AC-VRNN
PyTorch code for CVIU paper "AC-VRNN: Attentive Conditional-VRNN for Multi-Future Trajectory Prediction"
Stars: ✭ 21 (-96.28%)
Mutual labels:  generative-model
mix-stage
Official Repository for the paper Style Transfer for Co-Speech Gesture Animation: A Multi-Speaker Conditional-Mixture Approach published in ECCV 2020 (https://arxiv.org/abs/2007.12553)
Stars: ✭ 22 (-96.1%)
Mutual labels:  generative-model
EVE
Official repository for the paper "Large-scale clinical interpretation of genetic variants using evolutionary data and deep learning". Joint collaboration between the Marks lab and the OATML group.
Stars: ✭ 37 (-93.44%)
Mutual labels:  generative-model
texturize
🤖🖌️ Generate photo-realistic textures based on source images. Remix, remake, mashup! Useful if you want to create variations on a theme or elaborate on an existing texture.
Stars: ✭ 495 (-12.23%)
Mutual labels:  generative-model

rave_logo

RAVE: Realtime Audio Variational autoEncoder

Official implementation of RAVE: A variational autoencoder for fast and high-quality neural audio synthesis (article link) by Antoine Caillon and Philippe Esling.

If you use RAVE as a part of a music performance or installation, be sure to cite either this repository or the article !

Colab

We propose a Google Colab handling the training of a RAVE model on a custom dataset !

colab_badge

Installation

RAVE needs python 3.9. Install the dependencies using

pip install -r requirements.txt

Detailed instructions to setup a training station for this project are available here.

Preprocessing

RAVE comes with two command line utilities, resample and duration. resample allows to pre-process (silence removal, loudness normalization) and augment (compression) an entire directory of audio files (.mp3, .aiff, .opus, .wav, .aac). duration prints out the total duration of a .wav folder.

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.

Realtime usage

UPDATE

If you want to use the realtime mode, you should update your dependencies !

pip install -r requirements.txt

RAVE and the prior model can be used in realtime on live audio streams, allowing creative interactions with both models.

nn~

RAVE is compatible with the nn~ max/msp and PureData external.

max_msp_screenshot

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

RAVE vst

You can also use RAVE as a VST audio plugin using the RAVE vst !

plugin_screenshot

Discussion

If you have questions, want to share your experience with RAVE or share musical pieces done with the model, you can use the Discussion tab !

Demonstation

RAVE x nn~

Demonstration of what you can do with RAVE and the nn~ external for maxmsp !

RAVE x nn~

embedded RAVE

Using nn~ for puredata, RAVE can be used in realtime on embedded platforms !

RAVE x nn~

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].