We had trouble setting up the Tesseract library in Python and Mac M1. This led to us having to install additional dependencies and alter the versions of some other dependencies to make it work perfectly.

We also faced issues setting up the Text-to-Speech engine and storing its output in MP3 files.

We found it challenging to implement the novel method in the best possible way to optimize in the best possible way to perform the best possible contrasting while also ensuring the output isn't too noisy.