Model Description

This model was finetuned from whisper-medium.en for the DSTA BrainHack TIL 2024 competition on noisy, radio-sounding clips of military commands to control a turret. It has 0.43% WER on the hidden test set by DSTA.

Downloads last month: 2

Safetensors

Model size

764M params

Tensor type

F32

Inference API

Automatic Speech Recognition

This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.