OCR based on Google services with some sweets
- OCR with Google Cloud Document AI
- Translation of output with Google Cloud Translation
- Multiple input files
- Different output formats (currently: .txt and .pdf)
ocr-with-benefits is based on the Google Cloud Platform API, so you need to do some steps in your GCP Console.
- Create a GCP project
- Enable API: Document AI and Translation
- Create a service account and download the private key file.
sh OCR.sh you will be prompted for additional information
I know that can be confusing, especially setting up the project in GCP, so don't hesitate to contact me for any related questions