huggingface.co web signal

datalab-to/surya-ocr-2.5 · Hugging Face

By Alexis Dufresne Published October 30, 2026 at 18:12 UTC

Summary

Daniel van Strien @danielvanstrien.bsky.social: Small open OCR models are getting better at reading hard historic newspapers. Surya OCR 2.5 (689M) handled 1760s Fraktur, polytonic Greek … →
Brett Bobley @brettbobley.bsky.social amplified

Daniel van Strien @danielvanstrien.bsky.social

Small open OCR models are getting better at reading hard historic newspapers. Surya OCR 2.5 (689M) handled 1760s Fraktur, polytonic Greek and pre-reform Russian on my test pages, layout included. Big broadsheets need …
View on Bluesky →

Originally reported by huggingface.co

Original headline: datalab-to/surya-ocr-2.5 · Hugging Face