- Python 3.x
- PyQt5
- Pillow
- OpenCV
- NumPy
- pytesseract
- pyperclip3
-
Clone the repository:
git clone https://github.com/JHM69/ocr-snipping-tool.git cd ocr-snipping-tool
-
Install the required packages:
pip install -r requirements.txt
-
Tesseract Setup:
- Windows:
- Download the Tesseract installer from Tesseract at UB Mannheim.
- Install Tesseract and note the installation path (e.g.,
C:\Program Files\Tesseract-OCR\tesseract.exe
).
- Linux:
- Install Tesseract using the package manager:
sudo apt install tesseract-ocr
- Install Tesseract using the package manager:
- Windows:
-
Run the application:
- Launch the application by running:
python main.py
-
Set API Key and Tesseract Path:
- Once the application is running, you can enter the Tesseract path and Gemini API key in the provided input fields in the UI.
- Click the "Save" button to store these settings.
-
Using the Tool:
- Press
Ctrl + N
to create a new snip. - Press
Q
to quit the application.
- Press
- You can select between Tesseract and Gemini OCR engines from the dropdown menu in the application.
- You can also select the language for OCR from the settings tab.
- Supported languages include English, Bangla, Hindi, Japanese, Spanish, French, German, Chinese (Simplified), Russian, and Arabic.