Robust Speech Recognition via Large-Scale Weak Supervision

Animation engine for explanatory math videos

Inference code for Llama models

WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)

[CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer

Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.

A PyTorch-based Speech Toolkit

PyTorch package for the discrete VAE used for DALL·E.

The Triton Inference Server provides an optimized cloud and edge inferencing solution.

ImageBind One Embedding Space to Bind Them All

VITS: Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech

🔥 2D and 3D Face alignment library build using pytorch

PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO

Google AI 2018 BERT pytorch implementation

[ECCV 2022] ByteTrack: Multi-Object Tracking by Associating Every Detection Box

The official PyTorch implementation of Google's Gemma models

Official DeiT repository

An open-source framework for training large multimodal models.

The best OSS video generation models, created by Genmo

A high-performance Python-based I/O system for large (and small) deep learning problems, with strong support for PyTorch.

A Python library for audio data augmentation. Useful for making audio ML models work well in the real world, not just in the lab.

Contrastive Language-Audio Pretraining

NeurIPS 2025 Spotlight; ICLR2024 Spotlight; CVPR 2024; EMNLP 2024

Command line utility for forced alignment using Kaldi

VGGSfM: Visual Geometry Grounded Deep Structure From Motion

Cinemagoer is a Python package useful to retrieve and manage the data of the IMDb (to which we are not affiliated in any way) movie database about movies, people, characters and companies

Audio Large Language Models

Out of time: automated lip sync in the wild