unlimited-ocr
unlimited-ocr is Unlimited OCR Works: Welcome the Era of One-shot Long-horizon Parsing. - baidu/Unlimited-OCR. It is ranked #654 on the AI Radar, in RAG & memory, first seen 10 days ago and shared in 5 posts (26.1k views).
GitHub - baidu/Unlimited-OCR: Unlimited OCR Works: Welcome the Era of One-shot Long-horizon Parsing. · GitHub Skip to content Navigation Menu Sign in Appearance settings Search / Sign in Sign up Appearance settings You signed in with another tab or window. Reload to refresh your session. You signed out in another tab or window. Reload to refresh your session. You switched accounts on another tab or window. Reload to refresh your session. Dismiss alert {{ message }} Repository navigation Unlimited-OCR Public Notifications You must be signed in to change notification settings Fork 3k ( 3k ) Star 28.6k ( 28.6k ) You must be signed in to star a…
What people said about unlimited-ocr on X
👀OCR最严厉的父亲，百度文心又发新模型了。 今天，百度开源了文心Unlimited OCR2，直接拿3600多页的《哈利·波特》七部全集做OCR测试，甚至还顺手把1200多页的《三体》全集也给解析了一遍。 我看了一下技术报告，这次还挺有意思的。 对比百度之前的一代Unlimited OCR，当时就靠着可以一次性解析几十页文档的能力，在HuggingFace上拿到了超过1000万次下载，GitHub也积累了将近3万Stars。 但上一代其实还留下了一个很麻烦的问题。 虽然它通过滑动窗口机制，解决了长文档解析过程中部分KV Cache不断膨胀的问题，但每次生成新的Token，模型仍然需要关注前面所有页面的视觉信息。…
— @MaxForAI, 9 days ago · 98 likes · see the post
Unlimited-OCR-2, same 6-page PDF, three machines, mlx-vlm main. 🔥 Unlimited-OCR-2 is Baidu's open document-parsing model (MIT license, 3.3B parameters). It reads a whole multi-page PDF in one request. I ran the same 6 pages of its own technical report on three machines: the DGX Spark (Hugging Face and SGLang) and…
— @ivanfioravanti, 9 days ago · 65 likes · see the post
長文書ベンチでSOTA級のOCRがOSS公開、アツ🔥 Unlimited-OCR-2はBaidu が作った、長い文書を対象にした OCR モデル。 ベンチを見てもらったらわかるけど、かなりの長文にも対応しているので、使い道はほぼ無限大ですね。 同じ大きさのモデルの中で頭ひとつ抜けている性能を発揮していて、OmniDocBench v1.5 の総合スコアは 93.23 です。 他のより大きなモデルと比べても性能が高い。 Gemini-2.5 Pro（88.03）、GPT-4o（75.02） 現時点のOCRモデルだと結構最強クラスなので、SOTA級の響に偽りなし。 ■動作要件等 パラメータは約 3B の MoEで、重みは BF16…
— @studio_yebisu, 10 days ago · 46 likes · see the post
Alternatives to unlimited-ocr
- Boo Bench — Leaderboard + paper
- auto-ontology — Auto Ontology 🔥
- arXiv.org — Contextual embeddings represent chunks of a document with respect to the document's global context. These models are…
- liteparse — A fast, helpful, and open-source document parser. Contribute to run-llama/liteparse development by creating an account…
- ModelBest — ModelBest — On-Device Open-Source Model Platform
- OpenDocRouter — Set the model to llamaindex/ocria-1 in your parse request to try it. New accounts start with $5 in credit
unlimited-ocr in numbers
- Rank on the AI Radar: #654 of 10395
- Shared in 5 posts by 5 accounts: @MaxForAI, @ivanfioravanti, @studio_yebisu, @MaziyarPanahi
- 26.1k views on those posts
- First seen 10 days ago, last shared 8 days ago
- Pricing seen by AGK Intelligence: open source
- Market: RAG & memory
FAQ
What is unlimited-ocr?
Unlimited OCR Works: Welcome the Era of One-shot Long-horizon Parsing. - baidu/Unlimited-OCR It was first shared on X 10 days ago and is ranked #654 on the AI Radar.
Is unlimited-ocr free?
It is open source.
Who shared unlimited-ocr?
5 accounts on X, including @MaxForAI, @ivanfioravanti, @studio_yebisu, in 5 posts totalling 26.1k views.
Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 65.6k posts from 5k X accounts over the last 14 days, 10.4k tools, 19 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-06 14:25 UTC. Full method.