Translate Anything!

About:

This module allows users to easily copy and extract text from images and pdf documents and translate them.

Run:

Run the main file in your command line with $ python main.py

Technologies Used:

• Google's tesseract-orc text recognition model
• googletrans python library for free google translate API
• TKinter python framework to create a user interface

Installation:

1. To install dependencies, run $ pip install -r requirements.txt
2. You can install tesseract-orc from ./tesseract-orc-installer/ for windows that I have included, or you can install it by visit the following link: https://github.com/UB-Mannheim/tesseract/wiki

Possible Errors:

if you experience runtime error with the googletrans python library, try installing the latest version of googletrans by running the following commands on windows.

if pip3 install googletrans does not work, try pip uninstall googletrans then pip install googletrans==3.1.0a0 to install the latest version.

If you have any feel free to contact me!