📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG

A fast, helpful, and open-source document parser

This package enables inference of header hierarchy in the docling PDF parsing pipeline.

The fastest repo in history to surpass 100K stars ⭐. Better Harness Tools that make real things done. Built in Rust using oh-my-codex.

Multilingual Document Layout Parsing in a Single Vision-Language Model

Public repository for the LLM course at MVA

A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization.

A real-time and multilingual speech translation model

Outcome driven agent development framework that evolves

Omnilingual ASR Open-Source Multilingual SpeechRecognition for 1600+ Languages

Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audio codec.

The best ChatGPT that $100 can buy.

Master programming by recreating your favorite technologies from scratch.

A feature-rich command-line audio/video downloader

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

SoTA open-source TTS

The open-source CapCut alternative

Official code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"

1 min voice data can also be used to train a good TTS model! (few shot voice cloning)

State-of-the-art audio codec with 90x compression factor. Supports 44.1kHz, 24kHz, and 16kHz mono/stereo audio.

Home for "How To Scale Your Model", a short blog-style textbook about scaling LLMs on TPUs

Use Microsoft Edge's online text-to-speech service from Python WITHOUT needing Microsoft Edge or Windows or an API key

Reference PyTorch implementation and models for DINOv3

gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI

GLM-4.5: An open-source large language model designed for intelligent agents by Z.ai

Qwen3-Coder is the code version of Qwen3, the large language model series developed by Qwen team, Alibaba Cloud.

An implementation of Shazam's song recognition algorithm.

A tool for converting FERC filings published in XBRL into SQLite databases