setup_hybrid_model.py

import os
import subprocess
import sys
from pathlib import Path

def install_requirements():
    packages = [
        "torch",
        "torchvision", 
        "torchaudio",
        "transformers",
        "streamlit",
        "google-cloud-vision",
        "Pillow",
        "opencv-python",
        "numpy",
        "pandas",
        "python-dotenv",
        "scikit-learn"
    ]
    
    for package in packages:
        print(f"Installing {package}...")
        subprocess.check_call([sys.executable, "-m", "pip", "install", package])

def create_directories():
    directories = [
        "data/medical_images",
        "data/annotations", 
        "medical-ocr-model"
    ]
    
    for directory in directories:
        Path(directory).mkdir(parents=True, exist_ok=True)
        print(f"Created directory: {directory}")

def setup_pretrained_model():
    try:
        from transformers import TrOCRProcessor, VisionEncoderDecoderModel
        
        print("Downloading base TrOCR model...")
        processor = TrOCRProcessor.from_pretrained("microsoft/trocr-base-handwritten")
        model = VisionEncoderDecoderModel.from_pretrained("microsoft/trocr-base-handwritten")
        
        processor.save_pretrained("./medical-ocr-model")
        model.save_pretrained("./medical-ocr-model")
        print("Base model saved to medical-ocr-model/")
        
    except Exception as e:
        print(f"Error downloading model: {e}")

def main():
    print("Setting up Medical Prescription OCR System...")
    print("=" * 50)
    
    create_directories()
    install_requirements()
    setup_pretrained_model()
    
    print("\n" + "=" * 50)
    print("Setup completed successfully!")
    print("\nNext steps:")
    print("1. Run: python data_preparation.py")
    print("2. Configure Google Cloud credentials in .env file")  
    print("3. Run: streamlit run app.py")

if __name__ == "__main__":
    main()