Making large AI models cheaper, faster and more accessible

Official implementation of the paper "BigCodec: Pushing the Limits of Low-Bitrate Neural Speech Codec"

LLaQo, a Large Language Query-based Coach in the domain of expressive performance

A toolkit for computing Fréchet Inception Distance (FID) & Fréchet Video Distance (FVD) metrics.

A toolkit for computing Fréchet Inception Distance (FID) & Fréchet Video Distance (FVD) metrics.

WaveGAN on GTZAN Music genre classification dataset

Official PyTorch implementation of BigVGAN (ICLR 2023)

OmniTokenizer: one model and one weight for image-video joint tokenization.

[CVPR'23] MM-Diffusion: Learning Multi-Modal Diffusion Models for Joint Audio and Video Generation

Official JAX implementation of MAGVIT: Masked Generative Video Transformer

Official implementation of Diffusion Autoencoders

PyTorch Lightning + Hydra. A very user-friendly template for ML experimentation. ⚡🔥⚡

⏰ Collaboratively track deadlines of conferences recommended by CCF (Website, Python Cli, Wechat Applet) / If you find it useful, please star this project, thanks~

A family of diffusion models for text-to-audio generation.

Codebase for the paper 'EncodecMAE: Leveraging neural codecs for universal audio representation learning'

Autoregressive Model Beats Diffusion: 🦙 Llama for Scalable Image Generation

Official implementations for paper: Zero-shot Image Editing with Reference Imitation

[ICLR 2023] Official implementation of the paper "DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection"

Annotated Flow Matching paper

[NeurIPS 24] CV-VAE: A Compatible Video VAE for Latent Generative Video Models

Open-Sora: Democratizing Efficient Video Production for All

From Audio Encoders to Piano Judges: Benchmarking Performance Understanding for Solo Piano

Localized watermarking for AI-generated speech audios, with SOTA on robustness and very fast detector

A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)

This repo contains the code for our paper An Image is Worth 32 Tokens for Reconstruction and Generation

Python packaging and dependency management made easy

PyTorch implementation of Tacotron speech synthesis model.

Implementation of Rotary Embeddings, from the Roformer paper, in Pytorch

Implementation of Video Diffusion Models, Jonathan Ho's new paper extending DDPMs to Video Generation - in Pytorch