---
title: Streamlit OCR Application
emoji: 📷
colorFrom: blue
colorTo: green
sdk: streamlit
sdk_version: "1.25.0"  
app_file: app.py
pinned: false
---

# Streamlit OCR

## Overview
This project is a Streamlit-based Optical Character Recognition (OCR) application hosted on Hugging Face Spaces. It allows users to extract text from images using various OCR engines and includes a chatbot feature for enhanced interaction.

## Features
- **Live Camera Feed with OCR Support**: Capture and process images in real-time to extract text.
- **Display of Extracted Text**: View the recognized text directly on the screen.
- **Adjustable Confidence Score**: Modify the confidence threshold for displaying extracted text.
- **Freeze Button**: Use the freeze function to perform chatbot inference on the most recent text.

## Usage
You can access the application directly on Hugging Face Spaces: [Streamlit OCR + Chatbot App](https://st-ocr.streamlit.app/)

## Configuration
To run this application on Hugging Face Spaces, ensure you have the following configuration:
- **Repository Structure**: Include all necessary files such as `app.py` for Streamlit, and any model or data files required for OCR and chatbot functionalities.
- **Dependencies**: List all dependencies in a `requirements.txt` file to ensure they are installed in the Hugging Face environment.
- **Space Settings**: Configure the Space settings to use Streamlit as the runtime environment.

## TODOS
- [ ] Improve the freeze function for smoother operation.
- [ ] Fix existing bugs to enhance user experience.

## Completed Tasks ✓
- [x] Implemented OCR capability.
- [x] Added freeze function for text inference.
- [x] Integrated chatbot API call.
- [x] Merged code with Streamlit framework.
- [x] Enhanced OCR processing speed.
- [x] Added multilingual support.

## Contributing
Contributions are welcome! Please feel free to submit a pull request or open an issue for any bugs or feature requests.

## License
This project is licensed under the MIT License. See the [LICENSE](LICENSE) file for more details.