olmOCR 2
AI2's second-gen OCR model that "checks its own answers" — claims to beat GPT-4V
★ pending verification stars, verified 2026-09-30Category: Translation / Doc Parsing / OCRHugging Face ↗
No direct GitHub link yet — star count pending verification before we write it up.
AI2's second-generation OCR model that can "verify its own answers", claiming to surpass GPT-4V.
Translate documents, parse PDFs, and extract text with OCR.
Similar open-source projects
微软 MarkItDown
★ 187,737Microsoft's open-source Python tool — convert PDF/Word/PPT/audio/YouTube to clean Markdown
DeepSeek-OCR
★ 23,926DeepSeek's novel OCR document model — "contextual optical compression"