百度OCR模型Unlimited OCR在HuggingFace、GitHub四榜登顶

robot
Abstract generation in progress
Jinse Finance reported on June 29 that, according to 36Kr, recently, Baidu officially released and open-sourced the end-to-end OCR model Unlimited OCR.
The day after the model release, it topped the GitHub Daily Trending list and the Python list, and also ranked first on HuggingFace's global model general trend list and multimodal model trend list.
Unlimited OCR is built for long document parsing scenarios, with a total parameter size of 3B and only about 570M activation parameters during inference.
Public evaluation results show that Unlimited OCR achieved a comprehensive score of 93.92% in the OmniDocBench v1.6 benchmark test, setting a new record for end-to-end OCR.
This page may contain third-party content, which is provided for information purposes only (not representations/warranties) and should not be considered as an endorsement of its views by Gate, nor as financial or professional advice. See Disclaimer for details.
  • Reward
  • Comment
  • Repost
  • Share
Comment
Add a comment
Add a comment
No comments
  • Pinned