👐OpenHands: Sign Language Recognition Library

Making Sign Language Recognition Accessible

Check the documentation on how to use the library:
ReadTheDocs: 👐OpenHands

Installation

• For stable version: pip install --upgrade OpenHands
• For latest development version: pip install git+https://github.com/AI4Bharat/OpenHands

License

This project is released under the Apache 2.0 license.

Datasets used

Please cite the respective datasets if you used them in your research. Also check the licensing terms for the dataset used.

Dataset	Link
AUTSL	Link
CSL	Link
DEVISIGN	Link
GSL	Link
INCLUDE	Link
LSA64	Link
WLASL	Link

Extraction of poses

For datasets without the pose data, poses can be extracted from the videos using this script.

Citation

If you find our work useful in your research, please consider citing us:

@misc{2021_openhands_slr_preprint,
      title={OpenHands: Making Sign Language Recognition Accessible with Pose-based Pretrained Models across Languages}, 
      author={Prem Selvaraj and Gokul NC and Pratyush Kumar and Mitesh Khapra},
      year={2021},
      eprint={2110.05877},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}

@inproceedings{
      nc2022addressing,
      title={Addressing Resource Scarcity across Sign Languages with Multilingual Pretraining and Unified-Vocabulary Datasets},
      author={Gokul NC and Manideep Ladi and Sumit Negi and Prem Selvaraj and Pratyush Kumar and Mitesh M Khapra},
      booktitle={Thirty-sixth Conference on Neural Information Processing Systems Datasets and Benchmarks Track},
      year={2022},
      url={https://openreview.net/forum?id=zBBmV-i84Go}
}