Welcome to the Word-level Sign Language Recognition project! This application is designed to recognize and translate sign language gestures into text. It utilizes four pre-trained models, each containing different vocabulary sizes (100, 300, 1000, and 2000 words). Users can choose the model that best fits their needs and easily translate sign language gestures into corresponding words.
-
Four Pre-trained Models:
- 100 words model
- 300 words model
- 1000 words model
- 2000 words model
-
User-friendly Interface:
- Choose the desired model for sign language recognition.
- Translate sign language gestures into text with ease.
- Beautifully designed pages for translation and home.
Before you begin, ensure you have the following installed:
- Python 3.8 or higher
- Django
- others required by the project
-
Clone the repository:
git clone https://github.com/AIsTushar/Word-level-Sign-Language-Recognition.git
-
Navigate to the project directory:
cd Word-level-Sign-Language-Recognition
-
Install the required dependencies:
pip install -r requirements.txt
-
Run the Django development server:
python manage.py runserver
-
Open your web browser and go to http://localhost:8000/ to access the application.
-
Access the home page to find details about the project and available models.
-
Choose a pre-trained model based on the desired vocabulary size (100, 300, 1000, or 2000 words).
-
Navigate to the translation page to start recognizing and translating sign language gestures.
- List of 100 words...
- List of 300 words...
- List of 1000 words...
- List of 2000 words...
For any inquiries or feedback, feel free to reach out via email: info@sajidifti.com.
If you'd like to contribute to this project, please follow these steps:
- Fork the repository.
- Create a new branch for your feature or bug fix.
- Make your changes and submit a pull request.
Feel free to explore and enjoy the Word-level Sign Language Recognition application! If you encounter any issues or have suggestions for improvement, don't hesitate to open an issue or contribute to the project.