charleslwang/parakeet-tdt-0.6b-HD

Parakeet-TDT 0.6B HD

Official checkpoint for the paper "Huntington Disease Automatic Speech Recognition with Biomarker Supervision."

Model description

This model is an HD-adapted version of NVIDIA Parakeet-TDT 0.6B v2, tuned for automatic speech recognition on speech affected by Huntington disease (HD). It is the strongest model in the ParakeetHD suite and serves as the main disease-adapted recognizer in the paper.

What this model does

The model transcribes English read / controlled clinical speech from speakers with Huntington disease and healthy controls. It is intended as a research model for studying robust ASR under hyperkinetic motor-speech disruption.

Training

The model was adapted from nvidia/parakeet-tdt-0.6b-v2 using parameter-efficient encoder-side adapters while keeping the pretrained backbone frozen.

Evaluation

On the reported HD test set, this model achieved:

• —WER: 4.95
• —Substitutions: 2.09
• —Deletions: 1.29
• —Insertions: 1.57

Intended use

This model is intended for:

• —research on pathological / atypical speech recognition,
• —benchmarking ASR on Huntington disease speech,
• —studying error behavior under hyperkinetic disruption.

It is not intended for clinical diagnosis, treatment decisions, or standalone medical use.

Limitations

• —Trained and evaluated on a relatively small, high-fidelity clinical corpus.
• —Primarily reflects controlled / read speech rather than spontaneous conversational speech.
• —May not generalize to severe out-of-distribution impairment, other languages, or other recording conditions.

Citation

If you use this model, please cite:

@article{wang2026huntington,
  title={Huntington Disease Automatic Speech Recognition with Biomarker Supervision},
  author={Wang, Charles L. and Chen, Cady and Gong, Ziwei and Hirschberg, Julia},
  journal={arXiv preprint arXiv:2603.11168},
  year={2026},
  url={https://arxiv.org/abs/2603.11168}
}