sbintuitions / sarashina2.2-ocr

Vision3.9B95534Updated Mar 31, 2026

Downloads

955

Likes

34

Last updated

Mar 31, 2026

License

mit

Sarashina2.2-OCR is an end-to-end 3B-parameter OCR model developed by SB Intuitions, specifically tailored for parsing Japanese and English documents.

Tasks & library

  • image to text
  • transformers

Tags

  • transformers
  • sarashina2_vision
  • text-generation
  • multimodal
  • ocr
  • document-understanding

Technical specifications

Parameters3.9B
Librarytransformers
Languagesja, en
Licensemit