Hi Tanmay,

The best case scenario this case would be to convert your PDF into Images before applying OCR like Tesseract.

My article below provides a step-by-step explanation on how to extract text from PDF and images:

https://towardsdatascience.com/how-to-extract-text-from-any-pdf-and-image-for-large-language-model-2d17f02875e6