SOTA Open Source TTS

A Collection of Variational Autoencoders (VAE) in PyTorch.

Source code for "Taming Visually Guided Sound Generation" (Oral at the BMVC 2021)

[NeurIPS 2024]OmniTokenizer: one model and one weight for image-video joint tokenization.

A toolkit for non-parallel voice conversion based on vector-quantized variational autoencoder

(ECCV 2024) SignAvatars: A Large-scale 3D Sign Language Holistic Motion Dataset and Benchmark

Language Quantized AutoEncoders

Fast and scalable search of whole-slide images via self-supervised deep learning - Nature Biomedical Engineering

Torchélie is a set of utility functions, layers, losses, models, trainers and other things for PyTorch.

Demo of robust semantic communication against semantic noise

Towards training VQ-VAE models robustly!

official training and inference code of bitwise tokenizer

This repo implements VQVAE on mnist and as well as colored version of mnist images. It also implements simple LSTM for generating sample numbers using the encoder outputs of trained VQVAE

Voice conversion (VC) investigation using three variants of VAE

VQ-VAE/GAN implementation in pytorch-lightning

Inverse DALL-E for Optical Character Recognition

Experimental implementation for a sparse-dictionary based version of the VQ-VAE2 paper

State-of-the-Art VQ-VAE from Gaussian VAE without Training!

Large-Scale Bidirectional Training for Zero-Shot Image Captioning

Image Generation using VQVAE and GPT Models

Tensorflow Implementation of "Theory and Experiments on Vector Quantized Autoencoders"

Vector-Quantized Generative Adversarial Networks

Interactive VQ-VAE (Vector-Quantized Variational Autoencoder) in the browser

Implementation of basic autoencodeur, VAE and VQVAE in Flax

Official code for the NeurIPS 2022 paper "Posterior Matching for Arbitrary Conditioning".

VQGAN from LDM without hell of dependencies

Applying multiple VQ along the feature axis

implementation of VQVAE in pytorch

Torch implementation of minGPT for images latent code generation

Improving Semantic Control in Discrete Latent Spaces with Transformer Quantized Variational Autoencoders