ViT-Based ASL Recognition
American Sign Language classifier fine-tuned from a pretrained Vision Transformer — 94% accuracy on 26,000+ images.
An American Sign Language (ASL) classifier built by fine-tuning Hugging Face’s pretrained Vision Transformer (ViT), using data augmentation and class weighting to enhance robustness.
The model achieves an overall accuracy of 94% on a diverse dataset of over 26,000 images, demonstrating strong practical applicability for visual recognition tasks.
Tech: PyTorch, Hugging Face Transformers, Vision Transformer (ViT).