dotsocr

Open repos and models their makers tagged dotsocr, most starred first. The same for everyone.

Language and translationRepo

Multimodal-OCR3

Multimodal-OCR3 is a highly capable, experimental optical character recognition and visual processing suite designed for precise text extraction, document parsing, and markdown generation. Leveraging a powerful selection of vision-language.

  • 8
  • Python
  • Apache-2.0
  • 8 mo ago
Search GitHub and Hugging Face for dotsocr

Get , open it once and sign in. Then come back here and press the button again.