Back to feed
Chandra OCR 2: Text Recognition with Layout Preservation

Chandra OCR 2: Text Recognition with Layout Preservation

Chandra OCR 2 is a modern optical character recognition model that converts images and PDF files into structured HTML, Markdown, or JSON while preserving layout information.

Key Features

  • Support for image and PDF input formats
  • Output generation in HTML, Markdown, or JSON format
  • Preservation of the source document's structure and layout

The project is available on GitHub.

10.6K views

More from this channel GitHub Community

Similar in this category Technology