PDF OCR App

A small command line tool to convert PDF files to images and extract text. The default OCR engine is Tesseract but two Hugging Face models are also supported.

Requirements

• Python 3.8+
• pdf2image
• Pillow
• pytesseract
• transformers and torch for the optional Hugging Face models
• Tesseract OCR installed on your system
• Poppler utilities for PDF rendering

Install the Python dependencies via pip:

pip install -r requirements.txt

Usage

python pdf_ocr.py <file.pdf> --out-dir output --lang deu --engine tesseract

All pages of the PDF will be saved as JPG images in the output folder. The recognized text is printed to the console and written to output/output.txt.

Notes

This repository contains only a minimal example. Make sure tesseract and the language data you need are installed on your system.