#olmocr — Public Fediverse posts

Ah, the age-old quest for the elusive "plain text" hidden within the arcane tomes of #PDF lore 😱. Introducing #OlmOCR, the magical #open-source incantation that demands a sacrifice of #JavaScript before revealing the secrets of your own documents 📜. Because clearly, nothing screams "user-friendly" like the classic techie combo of forced scripting and DIY text extraction 🔧.
https://olmocr.allenai.org/ #text-extraction #HackerNews #ngated

OlmOCR: Open-source tool to extract plain text from PDFs — https://olmocr.allenai.org/
#HackerNews #OlmOCR #OpenSource #PDFText #Extraction #Tool #OCR #Tech #Innovation

OlmOCR: Open-source tool to extract plain text from PDFs — https://olmocr.allenai.org/
#HackerNews #OlmOCR #OpenSource #PDFText #Extraction #Tool #OCR #Tech #Innovation

#OlmOCR Runs on #macOS with #LMStudio: Simple #PDF Text Extraction 📄

#OlmOCR by #AllenAI now works on regular #macOS systems without specialized #GPU requirements using #LMStudio as inference server

🧵 👇 #OCR #ai #llm

New setup guide explains how to extract accurate text from PDFs while preserving reading order, handling tables, equations and handwriting with open-source tools on standard Mac hardware.

• 🖥️ Download and run #LMStudio as local inference server to host the #OlmOCR model