Create a python envirnoment preferrably 3.9.0
and install all the requirements as stated in requirements.txt
. Using the following command
pip install -r requirements.txt
This is a required dependancy to perform the OCR using Tesseract.
Download and install tesseract-OCR from the following link
https://digi.bib.uni-mannheim.de/tesseract/tesseract-ocr-w64-setup-5.3.3.20231005.exe
Navigate to C://Program Files//Tesseract-OCR
and add it to your system envirnoment variable.
Unzip the Release 23.11.0
folder and move the Poppler 23.11.0
folder to C://Program Files
Navigate to C:\Program Files\poppler-23.10.0\Library\bin
copy the path and set it as the envirnoment variable.
Navigate to the directory and run
python main.py
By default it will take a pdf from the data folder and perform OCR using both tesseract
and easyocr
you can customize this in the code.
Also a Speeach Recognition
module is been integrated which runs after the OCR code. By default it accepts voice as input and does not accept a .mp3
or any other sort of audio
file.
Refer the output
folder to checkout the OCR extraction output. It is not very good as of now.