Spaces:
Runtime error
Apply for community grant: Academic project
This is a small Norwegian Whisper model. It is trained on three different datasets, two of them (NbAiLab/NPSC and NbAiLab/NST) has already been made public on HF, the last will probably be published later.
The current performance is a WER of 15.0 on Fleurs test set. Whisper Norwegian Small (SOTA) have a WER of 24.2 on Fleurs test set. None of them is trained on Fleurs.
All the best,
Per Kummervold
Hi
@pere
- This is fantastic! Your model looks fantastic, thank you for putting in time and effort into fine-tuning the model. We've decided to assign you a T4 instance for the demo. This grant will run till 21st December 2022. After which we'll continue the grant if there's enough traction on the space.
Can't wait to see what language/ model you tackle next. Thanks again!
Don't forget to tweet/ LinkedIn your space, I'm sure the community would love to try it. Tag @huggingface and @lambdaapi when you do! 🤗