Model Card for Model ID

This Whisper model was trained and finetuned specifically for medical ASR incorporating Austrian Standard German pronunciation.

Model Description

  • Developed by: Valentina Hofecker
  • Model type: Transformer
  • Language(s) (NLP): DE (AUT)
  • Finetuned from model [optional]: Whisper Medium

Training Data

Total audio files: [ 4481] Total duration: [11.5 hours ]

File format: wav Sampling rate: [16 kHz]

Bias, Risks, and Limitations

A female voice was used for training, so there could be a minor bias against male voices.

Downloads last month
2
Safetensors
Model size
764M params
Tensor type
F32
·
Inference Examples
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.