Whisper API confuses the language

[kukarella]

we use Whisper API to transcribe video, and today we noticed a bug. When we transcribe BBC video (in English) the transcription is returned in Welsh.

[supershaneski]

yup. known behavior. check this:

[SOLVED] Whisper translates into Welsh

Summary created by AI. In this lengthy discussion, users primarily grappled with an anomaly in the Whisper transcription service: it purportedly translated one of pudepiedj’s podcast episodes into Welsh despite the input audio’s language being English. Intriguingly, he observed this phenomenon despite specifying ‘English’ as the language in the API call. One potential cause posited for such behavior was certain English accents being mistaken for being Welsh by the Whisper model. Users, such as…