README.md

metadata

title: ImageToOCRPdf
emoji: 📄
colorFrom: blue
colorTo: purple
sdk: streamlit
sdk_version: 1.36.0
app_file: app.py
pinned: false

📄 Image / PDF → Searchable PDF (OCR)

This Hugging Face Space converts images (PNG/JPG/JPEG) and PDF files into fully searchable OCR PDFs using Tesseract OCR and Poppler.

✔ Supports images
✔ Supports multi-page PDFs
✔ Works fully in-browser
✔ Download the final searchable PDF

---

🚀 How It Works

This app uses:

• Streamlit for UI
• Tesseract OCR for text extraction
• pdf2image to convert PDFs into images
• Pillow for image processing
• Poppler backend for high-quality PDF rendering

---

📥 Supported Upload Types

• PNG
• JPG / JPEG
• PDF (multi-page supported)

---

▶️ Run Locally

Install Python dependencies