deepinfra/ocr-tools

deepinfra/ocr-tools

Language: Python

Stars: 5

Forks: 2

Open issues: 1

Created: 2025-08-02T22:31:20Z

Pushed: 2025-08-02T23:13:51Z

Default branch: main

Fork: no

Archived: no

README:

ocr-tools

This document is tutorial how to use olmocr endpoint on DeepInfra to parse texts from pdf

Install requirements

pip install -r requirements.txt

(if linux): sudo apt-get install poppler-utils (if macOS): brew install poppler

Run command

python3 scrape_pdf.py --model allenai/olmOCR-7B-0725-FP8 --api-key DEEPINFRA_API_KEY --pdf-path horribleocr.pdf