← 최신 프로덕트

Using LLama2 to Correct OCR Errors

Enhances Tesseract OCR output using LLMs (local or API) for error correction, smart chunking, and markdown formatting of scanned PDFs. I've been disappointed by the very poor quality of results that I generally get when trying to run OCR on older scanned documents, especially ones that are typewritten or otherwise have unusual or irregular typography.

오픈소스

3,008 스타 · GitHub외부 사이트

github.com 방문외부 사이트

반응 (1)

비슷한 프로덕트

설명이 비슷한 순

  1. LLM-aided OCR

    github.com

    Correcting Tesseract OCR errors with LLMs

    Hacker News479점

  2. BetterOCR combines and corrects multiple OCR engines with an LLM

    github.com

    🔍 Better text detection by combining multiple OCR engines (EasyOCR, Tesseract, and Pororo) with 🧠 LLM.

    Hacker News63점

  3. LLM Aided Transcription Improvement

    github.com

    I recently submitted another project for using LLMs to correct errors and improve formatting of OCRed documents which was well received.

    Hacker News11점

  4. PDF to MD by LLMs

    github.com

    Extract Text/Tables/Image Descriptives by GPT4o

    Hacker News191점

  5. (YC S23) OCR that works on the messiest PDFs

    trycardinal.ai

    Hacker News21점