datalab-to/ocr

Detect and transcribe text in images with accurate bounding boxes, layout analysis, reding order, and table recognition, in 90 languages

68 runs
Playground API Examples README

Readme

Datalab OCR is a powerful document OCR toolkit that does:

  • OCR in 90+ languages that benchmarks favorably vs cloud services
  • Line-level text detection in any language
  • Layout analysis (table, image, header, etc detection)
  • Reading order detection
  • Table recognition (detecting rows/columns)
  • LaTeX OCR

For more information, visit https://datalab.to