Focus on prompting and generating

Autoware - the world's leading open-source software project for autonomous driving

Navigator, our self-driving vehicle software stack

A curated list of world models for autonomous driving. Keep updated.

A driving dataset for the development and validation of fused pose estimators and mapping algorithms

Add n-gram and large language model (LLM) support to Whisper models.

openpilot is an operating system for robotics. Currently, it upgrades the driver assistance system on 300+ supported cars.

🚀🎬 ShortGPT - Experimental AI framework for youtube shorts / tiktok channel automation

An open-source OpusClip alternative

Official code implementation of General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model

Jockey is a conversational video agent.

Sample code and workshop materials for the demonstration of multimodal video understanding with TwelveLabs

[EMNLP-2024] Build multimodal language agents for fast prototype and production

Self-Adapting Language Models

"ViMax: Agentic Video Generation (Director, Screenwriter, Producer, and Video Generator All-in-One)"

The agentic video editing framework

Weighted Cross-entropy for Low-Resource Languages in Multilingual Speech Recognition

Learning Long-Term Spatial-Temporal Graphs for Active Speaker Detection (ECCV 2022)

an optimized, production-ready implementation of active speaker detection

Audio-Visual Active Speaker Detection with PyTorch on AVA-ActiveSpeaker dataset

The repository for Springer IJCV 2025 (LR-ASD: Lightweight and Robust Network for Active Speaker Detection)

Frame is an AI-powered, open-source vibe video editor, offering a Professional VIDEO cuting alternative for creators. With Cursor-like interaction, it automates editing, enhances videos, and delive…

🎥 Python and OpenCV-based scene cut/transition detection program & library.

AI-powered tool to turn long videos into short, viral-ready clips. Combines transcription, speaker diarization, scene detection & 9:16 resizing — perfect for creators & smart automation.

Neural building blocks for speaker diarization: speech activity detection, speaker change detection, overlapped speech detection, speaker embedding

Faster Whisper transcription with CTranslate2

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)

An open-source, real-time streaming Automatic Speech Recognition (ASR) model for Thai, optimized for low-latency CPU deployment.