News for hackers. Stuff that matters.

A comment on Launch HN: Uplift (YC S25) – Voice models for under-served languages. Parent comment

Re:Launch HN: Uplift (YC S25) – Voice models for under-serve... by zaidqureshi on Tuesday August 19, 2025 @09:17AM (#44951162)
The model itself can work well for new languages, its just the process of data gathering and maintaining high quality of data is what we have to figure out as we scale across languages.

Currently the model is only given data for these languages so it doesn't know anything else.

[ Parent | on HN ]
Re:Launch HN: Uplift (YC S25) – Voice models for under-serve... by mandeepj on Tuesday August 19, 2025 @10:56AM (#44952291)
> just the process of data gathering and maintaining high quality of data is what we have to figure out as we scale across languages.

À crawler and data ingestion pipeline will not help with that?

[ Parent | on HN ]
Re:Launch HN: Uplift (YC S25) – Voice models for under-serve... by zaidqureshi on Tuesday August 19, 2025 @11:00AM (#44952349)
Gathering audio data online is not that hard, but getting it accurately labelled is challenging, as the speech understanding systems for those languages aren't there either, so we can't automatically do that
[ Parent | on HN ]
Re:Launch HN: Uplift (YC S25) – Voice models for under-serve... by akshayp29 on Tuesday August 19, 2025 @09:26AM (#44951258)
Cool - makes sense!
[ Parent | on HN ]