Nutlope/llama-ocr
npm library for OCR using Llama 3.2 Vision, outputs markdown from images
View on index · View in 3D Map
Related repos
- Extracts text from images using Apple Vision framework
- Extracts text from images into structured Markdown
- extracts text from images, screenshots, or PDFs using OCR, works offline, open source
- Official code for GOT-OCR2.0, an end-to-end OCR model implementation
- OCR utility for copying text from images or videos
- Extracts text from images locally in the browser
- Extracts text from images and PDFs using vision models through Ollama, available as Python package and web app
- OCR pipeline with local LLM field extraction
- OCR for scanned PDFs with LLM-powered text correction
- Generates synthetic text images for OCR training
