GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
balaji1312
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
balaji1312
Model Tree
openai/whisper-large-v3
Input Modalities
Output Modalities
Supported Functionality
The checkpoint bundles the frozen Whisper backbone together with the trained AURA parameters.
Loading requires the custom modeling code in the aura repository. 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-largev3-nonspeech-aura --local-dir whisper-largev3-nonspeech-aurapython $rootdir/src/bin/decode_asr.py --model whisper-largev3-nonspeech-aura --processor whisper-largev3-nonspeech-aura \--wav_scp data/urbansound8k/wav.scp --trn_scp data/urbansound8k/text \--result_ref_file ref.txt --result_hyp_file hyp.txt
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},}