m

ocr-document

OCR model for taking in images of documents as inputs and returning text as the output. It also supports non-latin characters.

Notes

Visual Text Detector

Detailed notes coming soon

  • ID
  • Model Type ID
    Visual Detector
  • Description
    OCR model for taking in images of documents as inputs and returning text as the output. It also supports non-latin characters.
  • Last Updated
    May 05, 2025
  • Privacy
    PUBLIC
  • Use Case
  • Toolkit
  • License
  • Share
    • Badge
      ocr-document