Awesome

Fingerspelling PoseNet: Enhancing Fingerspelling Translation with Pose-Based Transformer Models:

Paper Link: Arxiv

1. Download the Chicago Fingerspelling dataset from Here

2. Extract Pose using Media-Pipe 2.1. Install Media-Pipe Here

3. Run Media-Pipe on input data using extract_pose_mediapipe.py

python extract_pose_mediapipe.py

4. Run

python train_with_lm.py

Pre-trained models

To access the pre-trained model, use this link.