Training with spanish datasets?

Question

Training with spanish datasets?

Closed this issue 3 months ago · 1 comments

Hi, found this project from Laurin's response posted on this huggingface thread. My team and I are looking for a model that can detect these disfluencies (filler words, etc.) in the spanish language. Is this feature in your roadmap? If so, what ETA do you contemplate approximately? Thanks!

Answer 1 · 2024-09-15T12:59:56.000Z

Hey @rmajasol :) We do not intend to enable this feature anytime soon for spanish. However we hope that the recipe to extend these results to the spanish language is clear from the paper and this repo.