This script translates manga pages using CLOUD VISION API to recognize text in images [planning to change to tesseract], Translate API to translate the extracted text and PIL to manipulate images.

For update notes follow me on Twitter.

Before	After

Before	After

• Python 3.7+
• Google Cloud Vision API
• Google Cloud Translate API

You have to get the service account of your google cloud project with access granted to the google api's listed above to run this code.

This code is just for development purposes yet so to run it you'll have to open it in a notepad or something that you rather be using.

Once you've opened it just change the img_in variable with the source image path that you want to translate.

Ex:

if __name__ == '__main__':
    img_in = './images/sample4.jpg'

Now you just have to run it and wait for the out.png be generated at the root folder of this project.

Thanks for using!