HumanSignal / label-studio-ml-backend

Configs and boilerplates for Label Studio's Machine Learning backend
Apache License 2.0
585 stars 261 forks source link

enable multi-page-document-annotation with OCR #521

Closed fdejax90 closed 7 months ago

ar9 commented 5 months ago

@fdejax90 thank you for sharing this code. I take it you were you able to get the multi-page automated OCR annotations to work? I tried to use the same code in tesseract.py but it is not working. I ensured the config file on the project also has the same keys referenced in tesseract.py. Any pointers would be appreciated.

EDIT: never mind, I was able to get it to work! There was an issue in my docker setup. Thanks again for sharing this code!!