JPG, PNG and PDF to text with Tesseract OCR

sudo apt install tesseract-ocr -y

sudo nano batch_ocr.sh

#!/bin/bash

# Set the source and output directories
source_dir="/path/to/source/folder"
output_dir="/path/to/output/folder"

# Loop through image and PDF files in the source directory
for file in "$source_dir"/*.jpg "$source_dir"/*.png "$source_dir"/*.pdf; do
    filename=$(basename "$file")
    base="${filename%.*}"
    
    # Perform OCR using Tesseract
    tesseract "$file" "$output_dir/$base" -l eng
done

chmod +x batch_ocr.sh

https://linuxhint.com/install-tesseract-ocr-linux/