Skip to content

AI ML Assets

Jump to bottom
abhisheksuga edited this page Jul 6, 2022 · 1 revision
Component Details
PRIMA Layout detection model.
Google Vision Used for OCR in Document Digitization v1.0 , v1.5. Replaced with custom trained Tesseract in latest versions.
CRAFT Used for Line detection.
Tesseract Custom trained Tesseract used for OCR.
OpenNMT Custom trained OpenNMT used for translation.
Clone this wiki locally