This project aims to develop a machine learning model capable of performing lip reading using TensorFlow for the main network and YOLOv8 for lip detection and cropping from videos.
- TensorFlow (with GPU support for accelerated learning)
- YOLOv8
- CUDA-enabled GPU (for TensorFlow GPU acceleration)
- Python 3.x
- Clone the repository: git clone https://github.com/patrick-3008/lip-reading.git cd lip-reading
- Install dependencies: Ensure you have Python 3.x installed. Then install required Python packages: Make sure to have TensorFlow installed with GPU support. You might need to install CUDA and cuDNN as per TensorFlow's GPU requirements.
- Download YOLOv8 weights: Download the YOLOv8 weights from the official YOLO website or repository and place them in the yolo_weights/ directory.
This project was developed by Patrick Nashaat, Alfred Saad and Filopateer Fouad.
Contributions are welcome! Please fork the repository and submit pull requests.
- Inspired by the work on lip reading and deep learning.
- Special thanks to the TensorFlow and YOLO communities for their contributions.
email: patricknaashat@yahoo.com