This projects reads the text content from PDF files, translates it and saves translated text as a formatted PDF file.
Two different translating options can be used:
- Google translate python library googletrans (can be installed via pip
). To use this option, use script
translate_pdfs/translator.py - AWS Translate. This option requires you to have AWS account. You need to
obtain the AWS access key and a secret access key and configure them either
as environment variables or local files. To use AWS Translate:
translate_pds/aws_translator.py
Additional python packages that are required to install are:
PyPDF2reportlabboto3(AWS Python SDK)
AWS offer free tier to try out the AWS Translator. Free tier included 2 million characters for 12 months. Please note that after that the charges will occur and AWS will charge $15 per million characters. More info: Click Here for more info