Spaces:
Runtime error
Apply for community grant: Personal project
This project is part of the Whisper fine tuning sprint. I have fine tuned medium model on Italian language. Till now the model has the best WER on Italian language
The WER of the medium model fine-tuned as part of the sprint is: WER = 5.7 (evaluated on COMMON VOICE 11, test set).
Hi
@luigisaetta
- 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 23rd 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! 🤗
@reach-vb great, thanks. It is really amazing to see how well and fast it work on a T4. And even if it works really well in Italian I have discovered that it is able to transcribe in English (well, it is easy, the pre-trained model was multi-lingual). You have done a fantastic work with this sprint. Thanks.