🏆 #110 overall#14 of 701 in OCR & Documents🔥 active this week

datalab-to /surya

OCR, layout analysis, reading order, table recognition in 90+ languages

$ git clone https://github.com/datalab-to/surya.git
GitHub social preview for datalab-to/surya
Stars
21.6K
21,599
This week
—
Forks
1.6K
1,569
Language
Python
License
Apache-2.0
Created
Jan 10, 2024
2.9 years old
Last push
Nov 13, 2026
🔥 this week

Categories

GitHub topics

More in OCR & Documents

OCR & Documents

datalab-to/chandra🔥 active

▲ +32 ★ this week

OCR model that handles complex tables, forms, handwriting with full layout.

PythonApache-2.0updated Nov 16, 2026
GitHub ↗★ 12.7K⑂ 1.3K
OCR & Documents

bytedance/Dolphin

The official repo for “Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting”, ACL, 2025.

PythonOtherupdated Mar 25, 2026
GitHub ↗★ 9.1K⑂ 771
OCR & Documents

mindee/doctr🔥 active

▲ +11 ★ this week

docTR (Document Text Recognition) - a seamless, high-performing & accessible library for OCR-related tasks powered by Deep Learning. Ongoing development and maintenance by t2k.

PythonApache-2.0updated Nov 17, 2026
GitHub ↗★ 6.4K⑂ 692
OCR & Documents

kotaro-kinoshita/yomitoku

▲ +12 ★ this week

YomiTokuはAIを活用した日本語文書解析エンジンを提供するPythonパッケージです。 Yomitoku is an AI-powered document image analysis package designed specifically for the Japanese language.

Pythonno licenseupdated Nov 10, 2026
GitHub ↗★ 1.7K⑂ 67
OCR & Documents

opendatalab/MinerU🔥 active

▲ +520 ★ this week

Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.

PythonOtherupdated Nov 16, 2026
GitHub ↗★ 83.8K⑂ 6.9K
OCR & Documents

datalab-to/marker🔥 active

Convert PDF to markdown + JSON quickly with high accuracy

PythonApache-2.0updated Nov 14, 2026
GitHub ↗★ 41K⑂ 3K

Data from GitHub · snapshot Nov 17, 2026