Hugging Face's logo

Spaces:
Dragneel
/
Manga_OCR
Running

App Files Community
Manga_OCR / README.md
Drag2121's picture
Drag2121
tesseract
a91e387
preview code
|
raw
history blame contribute delete
4.34 kB
metadata
title: My FastAPI App
emoji: 🚀
colorFrom: blue
colorTo: purple
sdk: docker
sdk_version: 0.1.0
app_file: app.py
pinned: false

Manga OCR Translator

A powerful tool for translating manga, comics, and light novels using OCR (Optical Character Recognition) and machine translation.

Features

  • Text Detection: Automatically detects text in manga images using PyTesseract
  • Text Translation: Translates detected text to your preferred language
  • PDF Support: Upload and translate entire PDF manga files
  • URL Support: Translate manga directly from web URLs
  • Modern UI: Clean, responsive Gumroad-like user interface
  • Multiple Languages: Support for Japanese, Korean, Chinese, and more

Requirements

Before running the application, ensure you have the following installed:

  • Python 3.8+
  • Tesseract OCR - Must be installed and available in PATH
  • Required Python packages from requirements.txt

Installing Tesseract OCR

Windows

  1. Download the installer from UB Mannheim
  2. Install and add to PATH environment variable
  3. Default installation path: C:\Program Files\Tesseract-OCR\tesseract.exe

macOS 

brew install tesseract

Linux (Ubuntu/Debian) 

sudo apt update
sudo apt install tesseract-ocr
sudo apt install libtesseract-dev
# Install language data packages as needed
sudo apt install tesseract-ocr-jpn tesseract-ocr-chi-sim tesseract-ocr-kor

Installation

  1. Clone the repository:
git clone https://github.com/yourusername/manga-ocr-translator.git
cd manga-ocr-translator
  1. Install Python dependencies:
pip install -r requirements.txt
  1. Set the Tesseract executable path in your environment (only if not in PATH):
# In your environment or at the top of utils/ocr.py
import pytesseract
pytesseract.pytesseract.tesseract_cmd = r'C:\Program Files\Tesseract-OCR\tesseract.exe'  # Windows example

Usage

Starting the Server

Run the application:

python app.py

Then open a web browser and navigate to:

http://localhost:8000

Using the Web Interface

  1. Access the main page at http://localhost:8000
  2. Choose either URL or PDF upload method
  3. Configure source and target languages
  4. Submit for translation
  5. View and download the translated images

API Endpoints

The application also provides API endpoints for integration:

  • POST /translate/url - Translate manga from a URL
  • POST /translate/pdf - Translate manga from a PDF file
  • GET /api/info - Get API information

Development

Project Structure 

manga-ocr-translator/
├── app.py                 # Main FastAPI application
├── requirements.txt       # Python dependencies
├── static/                # Static files
│   ├── translated/        # Translated images output
│   └── ui/                # UI assets
│       ├── index.html     # Main UI page
│       ├── styles.css     # CSS styles
│       └── scripts.js     # JavaScript functionality
└── utils/                 # Utility modules
    ├── ocr.py             # OCR functionality using pytesseract
    ├── image.py           # Image processing utilities
    ├── pdf.py             # PDF handling
    ├── translation.py     # Translation services
    └── web.py             # Web scraping utilities

Configuration

You can configure the application by modifying the following files:

  • app.py: Main application settings
  • utils/ocr.py: OCR settings and language mapping
  • requirements.txt: Package dependencies

Troubleshooting

Common Issues

  1. Tesseract not found: Ensure Tesseract is installed and the correct path is set
  2. Missing language data: Install additional language data packages for Tesseract
  3. Slow performance: Consider using a GPU for faster processing

License

This project is licensed under the MIT License - see the LICENSE file for details.

Acknowledgements