Tech Stack

• Python
• OpenCV
• YOLO

Project Setup

1. Clone the Repository

git clone https://github.com/wisng/ASL-CV.git

cd ASL-CV

pip install -r requirements.txt

python main.py

Train the model

1. Download datasets

- Kaggle Dataset from [nagaraj_2018](https://www.kaggle.com/datasets/grassknoted/asl-alphabet)
- Kaggle Dataset from [ayuraj](https://www.kaggle.com/datasets/ayuraj/asl-dataset)
- Roboflow Dataset from [David Lee](https://public.roboflow.com/object-detection/american-sign-language-letters)

2. Run the main.ipynb notebook

Model Overview

This project fine-tunes a YOLOv11 model for American Sign Language (ASL) recognition, utilizing three datasets mentioned above. Training was performed on an NVIDIA RTX 4090 GPU for optimal performance and efficiency.