| # Requirements for Advanced Multi-Language OCR System | |
| # Compatible with Hugging Face Spaces | |
| # Gradio Web Interface for HuggingFace Spaces | |
| gradio>=4.0.0 | |
| # FastAPI Web Service Dependencies (for backend compatibility) | |
| fastapi>=0.104.0 | |
| uvicorn[standard]>=0.23.0 | |
| python-multipart>=0.0.6 | |
| # Core OCR Dependencies | |
| opencv-python>=4.8.0 | |
| pytesseract>=0.3.10 | |
| pdf2image>=1.16.0 | |
| pillow>=9.0.0 | |
| numpy>=1.24.0 | |
| tqdm>=4.65.0 | |
| # Pix2Text for advanced mathematical expression extraction | |
| pix2text>=1.0.0 | |
| # AI/ML Dependencies for Math Extraction | |
| torch>=2.0.0 | |
| torchvision>=0.15.0 | |
| transformers>=4.20.0 | |
| # Additional utilities | |
| unicodedata2>=15.0.0 | |
| # System dependencies that may be needed for Hugging Face Spaces | |
| # These are usually pre-installed in HF Spaces but listed for completeness | |
| # poppler-utils # For pdf2image (system package) | |
| # tesseract-ocr # Tesseract binary (system package) | |
| # tesseract-ocr-ben # Bengali language pack (system package) | |
| # Optional: GPU support for faster processing | |
| # torch-audio # Uncomment if using GPU | |
| # Note: Install CUDA-compatible PyTorch for GPU acceleration | |