---
license: apache-2.0
language: en
library_name: transformers
pipeline_tag: automatic-speech-recognition
base_model: openai/whisper-medium.en
tags:
- whisper
- automatic-speech-recognition
- peft
- representation-editing
- aura
- myst
---

# Whisper-medium MyST (AURA)

Whisper-medium adapted to the **MyST** child speech corpus with **AURA** (Activation-editing with Uncertainty-Routed Adaptation),
from the paper *"AURA: Uncertainty-Routed Activation Editing for Acoustic Grounding in Speech Foundation Models"* (IEEE SLT 2026).

- **Base model:** `openai/whisper-medium.en`
- **Method:** AURA scale-and-shift edits on the cross-attention heads of every decoder layer, controlled by Hard-Concrete head gates and the uncertainty-routed dynamic gate; the Whisper weights stay frozen
- **Code:** https://github.com/balaji1312/aura

## Usage

The checkpoint bundles the frozen Whisper backbone together with the trained AURA parameters.
Loading requires the custom modeling code in the [aura repository](https://github.com/balaji1312/aura). Download the model and decode with `src/bin/decode_asr.py` there:

```bash
git clone https://github.com/balaji1312/aura && export rootdir=$(realpath aura)
huggingface-cli download balaji1312/whisper-medium-myst-aura --local-dir whisper-medium-myst-aura
python $rootdir/src/bin/decode_asr.py --model whisper-medium-myst-aura --processor whisper-medium-myst-aura \
  --wav_scp data/test/wav.scp --trn_scp data/test/text \
  --result_ref_file ref.txt --result_hyp_file hyp.txt
```

## Citation

```bibtex
@inproceedings{shankar2026aura,
  author    = {Shankar, Natarajan Balaji and Wang, Zilai and Wang, Zihan and Shi, Mohan and Zhang, Kaiyuan and Alwan, Abeer},
  title     = {{AURA}: Uncertainty-Routed Activation Editing for Acoustic Grounding in Speech Foundation Models},
  booktitle = {IEEE Spoken Language Technology Workshop (SLT)},
  year      = {2026},
}
```