A powerful multi-format Document → Text converter built using:

• Tesseract OCR
• EasyOCR
• PyMuPDF
• pdf2image
• python-docx / python-pptx

Supports:

• 🖼️ Images: JPG, PNG, TIFF, BMP, WEBP
• 📄 PDFs: Text-based & Scanned PDFs
• 📝 DOCX files (Office Word)
• 📊 PPTX files (Office PowerPoint)

Also includes:

• 🔍 Automatic Important Details Extractor (Emails, Phones, Dates, Key:Value pairs)
• 📁 Automatic output folder generation
• 🧹 Optional spell correction
• 🖥️ Full Streamlit Web App UI

• Multi-OCR merge: Tesseract + EasyOCR
• PDF text-mode detection → uses direct extraction when possible

Automatically extracts:

• Emails
• Phone numbers
• Date formats
• Key:Value structured text

Built with Streamlit, featuring:

• File upload
• OCR progress
• Download TXT output
• Download JSON details
• Text preview panel

Image preprocessing:

• Grayscale
• Denoising
• Adaptive thresholding

Install system packages:

• Tesseract OCR → https://github.com/UB-Mannheim/tesseract/wiki
• Poppler for Windows → add bin/ to PATH

sudo apt install tesseract-ocr poppler-utils