Re:Show HN: LibreASR – An On-Premises, Streaming Speech Reco...
by iceychris on Sunday November 15, 2020 @06:30AM
(#25100331)
Yes, probably. The data I trained on mostly reflects UK and US accents.
[ Parent
| on HN ]
Re:Show HN: LibreASR – An On-Premises, Streaming Speech Reco...
by OnlyMortal on Sunday November 15, 2020 @06:38AM
(#25100381)
IBM kept their US and UK models apart. May have been historic or dataset size.
As a FYI, I was told “the money” was in specific “dictionaries” for medical professionals and so forth. Apparently, doctors liked to dictate straight into text. Might be worth trying that $$$€€€£££?