Dicklesworthstone/llama2_aided_tesseract

Enhances Tesseract OCR output using LLMs (local or API) for error correction, smart chunking, and markdown formatting of scanned PDFs

54 best points · 10 comments · 1 Hacker News post · 3,011 GitHub stars · View on GitHub

Hacker News discussions

• Show HN: Using LLama2 to Correct OCR Errors (54 points, 10 comments, by eigenvalue, 2023-08-02)