Dicklesworthstone/llm_aided_ocr

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

58
/ 100
Established

This project helps anyone working with scanned documents by taking a PDF and transforming its raw text into a much more accurate, readable, and well-formatted document. It cleans up common scanning errors, organizes the content into logical sections, and can even format it using Markdown. This is ideal for researchers, analysts, or anyone who frequently extracts information from old reports, books, or archived files.

2,885 stars. Actively maintained with 2 commits in the last 30 days.

Use this if you need to reliably extract clean, structured text from scanned PDFs, especially those with quality issues or complex layouts.

Not ideal if you primarily work with born-digital PDFs or already have perfectly clean text, as the overhead of advanced correction may not be necessary.

document-digitization text-extraction archival-research data-entry content-preparation
No Package No Dependents
Maintenance 13 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 19 / 25

How are scores calculated?

Stars

2,885

Forks

206

Language

Python

License

Last pushed

Mar 03, 2026

Commits (30d)

2

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/Dicklesworthstone/llm_aided_ocr"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.