Wispr Flow - Don’t type, just speak
Mini toolsolmOCR
By Ai2
olmOCR provides both a toolkit and LLM-sized OCR models for high-fidelity document linearization. It focuses on turning messy PDFs or scanned pages into structured text suitable for downstream LLMs, with attention to layout, tables, math, and handwritten content. The project ships several 7B and 8B image-to-text models plus a pipeline that outputs markdown, making it a strong backbone for building RAG systems or datasets from large scientific and business corpora.
Image
Gen 4
Overview
olmOCR is AllenAI’s open-source document recognition pipeline and model family that converts PDFs and images into clean text, preserving reading order, tables, equations, and handwriting.
About Ai2
Ai2 is a 501(c)(3) non-profit AI research institute founded in 2014 by the late Paul Allen (Microsoft co-founder), dedicated to conducting high-impact, open AI research and engineering for the common good, including open language models (OLMo), scientific AI tools (Semantic Scholar, Asta), environmental AI platforms, and embodied robotics research.
Industry:
Artificial Intelligence
Company Size:
313
Location:
Seattle, Washington, US
Website:
allenai.org
Last updated: April 6, 2026
