datalab-to/chandra

OCR model that converts images to structured formats while preserving layout

View on index · View in 3D Map

Related repos

• OCR toolkit for 90+ languages, tables, and layouts
• Generates synthetic text images for OCR training
• turns documents into structured data with OCR and layout analysis
• Official code for GOT-OCR2.0, an end-to-end OCR model implementation
• Extracts text from images using Apple Vision framework
• extracts text from images, screenshots, or PDFs using OCR, works offline, open source
• 7B text-to-image model for text rendering
• text-to-image model for fast high-res AI image generation
• translation and OCR tool for quick setup
• Extracts text from images into structured Markdown