datalab-to/chandra

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

Python12K stars1.2K forks+687 today

Topics

#ai#ocr

What it does

Chandra OCR 2 is a state-of-the-art OCR model that converts images and PDFs into structured HTML, Markdown, or JSON while preserving layout information. It excels in handling complex tables, forms, handwriting, math, and multilingual documents.

Star history

Not enough history yet — 1 day(s) recorded. The daily snapshot builds this up.

Tracking

Last trending: 2026-04-25

Creator kit

Hook

Transform your document processing game with Chandra OCR 2 - the ultimate tool for converting images & PDFs into structured formats while preserving layout info. #OCR #AI

Content angles

Create tutorials on how to use Chandra OCR 2 for various document types.
Compare Chandra OCR 2's performance against other OCR tools in a detailed review.
Demonstrate the multilingual capabilities of Chandra OCR 2 with real-world examples.

Who should care

Developers, data scientists, and content creators working on document processing and AI applications.