OpenAI Whisper на Македонски јазик

Loss: 0.54 WER: 54

Fine tuning dataset

Common Voice Corpus 11.0

Initial observations

Although using an old dataset from 2022, the results show great performance compared to Wav2Vec 2.0

Downloads last month
23
Safetensors
Model size
242M 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.

Dataset used to train goran/whisper-small.mk