training/generate_nlp_data.py

import os
import json

def generate_nlp_dataset(output_file="training/nlp_data.json"):
    """
    Creates a pairing of (Common OCR Mistakes -> Correct Word).
    This dataset can be used to 'train' the spellchecker's dictionary 
    or fine-tune a specialized NLP model.
    """
    data = [
        {"input": "th3", "target": "the"},
        {"input": "p3ople", "target": "people"},
        {"input": "v0ice", "target": "voice"},
        {"input": "no4hij", "target": "nothing"},
        {"input": "Ia", "target": "in"},
        {"input": "0f", "target": "of"},
        {"input": "joshu4", "target": "joshua"},
        {"input": "he11o", "target": "hello"},
        {"input": "w0r1d", "target": "world"},
        {"input": "re-ling", "target": "feeling"},
        {"input": "odia", "target": "who"},
        {"input": "wheo", "target": "who"},
        {"input": "4!", "target": "voice"},
        {"input": "314", "target": "a"}
    ]
    
    os.makedirs(os.path.dirname(output_file), exist_ok=True)
    with open(output_file, 'w') as f:
        json.dump(data, f, indent=4)
    
    print(f"NLP Dataset created: {output_file}")

if __name__ == "__main__":
    generate_nlp_dataset()