Chandra OCR
github.com/datalab-to/chandra- Category
- AI Tools
- Pricing
- Freemium
- Type
- TOOL
- Builder
- datalab-to
- GitHub
- 11.8k stars
- Added
- Apr 12, 2026
About
State-of-the-art OCR model that converts images and PDFs into structured HTML/Markdown/JSON while preserving complex layouts. Handles handwriting, forms, tables, math equations, and supports 90+ languages with excellent accuracy.
Why it made the leaderboard
OCR that keeps the document's structure: images and PDFs come out as HTML, Markdown, or JSON with layout preserved — handwriting, forms, tables, and math included — across 90+ languages. From Datalab, and open source.
Tags
ocrdocument-processingpdfhandwritingmultilinguallayout-preservationforms
Tech Stack
Python
Comments (0)
No comments yet
Indexed by a proprietary survey. Corrections welcome.