8 projects
gemini-ocr-cli
CLI tool for OCR processing using Google Gemini's vision capabilities
ocr-output-contract
Canonical OCR output contract + conformance harness shared by the OCR engine CLI family
socr
Multi-engine document OCR with cascading fallback
deepseek-ocr-cli
CLI tool for OCR using DeepSeek-OCR model via Ollama
marker-ocr-cli
CLI for PDF text extraction using Marker's layout-aware pipeline
nougat-ocr-cli
CLI for PDF text extraction using Meta's Nougat model with GPU acceleration
mistral-ocr-cli
A clean command-line tool for OCR processing using Mistral AI's API
smart-ocr
Multi-engine document OCR with cascading fallback