Baidu open-sources Unlimited OCR 2 for long documents
Original title: Baidu Open-Sources Unlimited OCR 2 for Hundred-Page Document Parsing
The headline says the release targets hundred-page document parsing; no further specs were in the text.
Baidu has open-sourced Unlimited OCR 2, described in the headline as a tool for parsing hundred-page documents. The captured page contained only a cookie-consent notice, so model size, license, benchmarks, and download details are not stated.
Unconfirmed: Article body was unavailable, so claims beyond the headline are unconfirmed.
- The product name in the headline is Unlimited OCR 2.
- It is framed as open source and aimed at long-document OCR.
- Vendors
- Baidu
- AI models
- Unlimited OCR 2
From the original article
14 min read at marktechpost.comBaidu has released Unlimited OCR 2, an MIT-licensed 3B OCR model that parses hundred-page documents in one request. Its SR-SWA attention keeps per-step decoding cost nearly flat, scoring 77. 1 on MarathonDocBench The post Baidu Open-Sources Unlimited OCR 2 for Hundred-Page Document Parsing appeared first on MarkTechPost.
By Asif Razzaq · marktechpost.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.