ainewsblitz.com

Breaking

Datalab Releases Chandra OCR, an Open-Source Model for PDFs, Tables and Handwriting Across 90+ Languages

Datalab Releases Chandra OCR, an Open-Source Model for PDFs, Tables and Handwriting Across 90+ Languages
  • Open Source
  • Foundation Models
  • Software Dev & Coding

Datalab has released Chandra OCR, an open-source document-recognition model that converts images and PDFs into structured Markdown, HTML or JSON while handling complex tables, handwriting, forms and mathematical notation across more than 90 languages. The model, distributed for free for individuals, researchers and smaller startups, has drawn attention for tackling the hard cases that have long frustrated traditional optical character recognition tools.

Continue reading

The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.

$20
Read this article
$29/month
Unlimited — all 27,934 articles, the full archive, and comprehension quizzes
Save 72%
$98/year
≈ $8.17/month
Unlimited, billed once a year