Hacker News new | ask | show | jobs
by Manfred 455 days ago
Models need a large set of training data to work properly and dialects are usually underrepresented in the training data.
1 comments

The National Library and public service television has done some work in this area.

You can find models here:

https://huggingface.co/KBLab

More information in swedish about the process here:

https://www.kb.se/samverkan-och-utveckling/nytt-fran-kb/nyhe...