Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
TurboOCR, >200 img/s OmnidocBench. TensorRT FP16, PP-OCRv6, HTTP + gRPC
| Date | Stars |
|---|---|
| 2026-07-24 | 550 |
| 2026-07-25 | 556 |
| 2026-07-28 | 556 |
| 2026-07-30 | 556 |
| 2026-08-06 | 556 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
35.0
growth rate 0.00%/day
<p align="center"> <img src="tests/benchmark/comparison/images/banner.png" alt="TurboOCR — the fastest GPU document parser." width="100%"> </p> <p align="center"> <strong>English</strong> | <a href="README_zh.md">简体中文</a> </p> <p align="center"> <strong>The fastest GPU document parser — OCR · layout · tables · formulas → Markdown, at 200–559 images/s on one GPU.</strong><br> C++ / CUDA / TensorRT / PP-OCRv6 — Linux + NVIDIA GPU </p> <h3 align="center">🎉 v3.0 — now powered by PP-OCRv6</h3> <p align="center"> <sub>New <code>medium</code> / <code>small</code> / <code>tiny</code> tiers · higher accuracy · faster defaults · <a href="docs/build/upgrading-v3.md">breaking changes</a></sub> </p> <p align="center"> <a href="https://github.com/aiptimizer/TurboOCR"><strong>⭐ Star TurboOCR on GitHub</strong></a> — it helps others (and agents) find it. </p> <p align="center"> <img src="https://img.shields.io/badge/throughput-up_to_559_img%2Fs-blue?style=flat-square&logo=speedtest&logoColor=white" alt="up to 559 img/s"> <a href="https://turboocr.com"><img src="https://img.shields.io/badge/website-turboocr.com-3B82F6?style=flat-square&logo=googlechrome&logoColor=white" alt="turboocr.com"></a> <a href="https://github.com/aiptimizer/TurboOCR/releases/latest"><img src="https://img.shields.io/github/v/release/aiptimizer/TurboOCR?style=flat-square&logo=github&logoColor=white" alt="Release"></a> <a href="https://ghcr.io/aiptimizer/turboocr"><img src="https://img.shields.io/badge/docker-ghcr.io-2496ED?style=flat-square&logo=docker&logoColor=white" alt="Docker"></a> <img src="https://img.shields.io/badge/C%2B%2B20-00599C?style=flat-square&logo=cplusplus&logoColor=white" alt="C++20"> <img src="https://img.shields.io/badge/CUDA-76B900?style=flat-square&logo=nvidia&logoColor=white" alt="CUDA"> <img src="https://img.shields.io/badge/TensorRT-10.16-76B900?style=flat-square&logo=nvidia&logoColor=white" alt="TensorRT 10.16"> <img src="https://img.shields.io/badge/gRPC-4285F4?style=flat-square&logo=google&logoColor=white" alt="gRPC"> <a href="https://github.com/PaddlePaddle/PaddleOCR"><img src="https://img.shields.io/badge/PP--OCRv6-PaddleOCR-0053D6?style=flat-square&logo=paddlepaddle&logoColor=white" alt="PaddleOCR"></a> <img src="https://img.shields.io/badge/license-MIT-blue?style=flat-square&logo=opensourceinitiative&logoColor=white" alt="MIT License"> </p> <p align="center"> <a href="#quick-start">Quick Start</a> · <a href="#getting-higher-accuracy">Accuracy</a> · <a href="#benchmarks">Benchmarks</a> · <a href="#models">Models</a> · <a href="docs/build/upgrading-v3.md">v3 changes</a> · <a href="#api">API</a> · <a href="docs/index.md">Docs</a> </p> --- An extremely fast GPU **document parser** — not just OCR. PP-OCRv6 detection + recognition, plus layout, tables (→ HTML), formulas (→ LaTeX) and reading-order **Markdown**, the whole pipeline on a single multi-stream CUDA/TensorRT engine, locally (no VLM), behind HTTP and gRPC. Whole-page OCR runs at **up to 559 images/s on receipts** (one RTX 5090), and full structured parsing (layout + tables + formulas) at **~20 pages/s** — where VLM document parsers like PaddleOCR-VL run ~1 page/s. On forms and receipts it is accurate and 15–90× faster than classic OCR engines. - 🚀 **559 img/s (receipts) · 520 (forms) · 200+ (dense docs) on one RTX 5090 — fastest by default - 🎯 **Accurate on forms & receipts** — competitive with PaddleOCR-VL, PaddleOCR-Python, RapidOCR, EasyOCR and Tesseract ([benchmarks](#benchmarks)) - 🧠 **PP-OCRv6** — one model covers Latin + Chinese + Japanese; pick `tiny` (default) / `small` / `medium` - 🌐 **More scripts** — Arabic, Cyrillic, Korean, Thai, Greek via retained PP-OCRv5 recognizers - 📄 **PDF native** — pages rendered and OCR'd in parallel, optional page-image export & auto-rotation - 🧩 **Layout + reading order** — PP-DocLayoutV3 (25 classes) and class-aw
Excerpt of 16,517 characters
Read on GitHub
244
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:27252169b15e4140, topic:ocr, topic:document-parsing, readme:ocr
matched fp:27252169b15e4140, topic:tensorrt
matched fp:27252169b15e4140, topic:rag