Re:Mistral AI raises €1.7B to accelerate technological progr...
by artemisart on Tuesday September 09, 2025 @06:57AM
(#45180310)
Nvidia parakeet and canary are better and faster, here is a leaderboard: https://huggingface.co/spaces/hf-audio/open_asr_leaderboard
Re:Mistral AI raises €1.7B to accelerate technological progr...
by diggan on Tuesday September 09, 2025 @06:59AM
(#45180336)
> Nvidia parakeet and canary are better and faster
Is that based on your own experience using those and also Whisper, comparing them side-by-side? Or is that based just on those benchmark results?
Re:Mistral AI raises €1.7B to accelerate technological progr...
by artemisart on Tuesday September 09, 2025 @07:34PM
(#45191010)
Yes for parakeet, but only comparing benchmark results for canary. Whisper also has severe hallucinations on silence and noise and WhisperX helps a lot, it adds voice activity detection i.e. a model to detect when someone speaks, to filter the input before running whisper. https://github.com/m-bain/whisperX
Re:Mistral AI raises €1.7B to accelerate technological progr...
by wahnfrieden on Tuesday September 09, 2025 @07:44AM
(#45180614)
Parakeet isn’t more accurate than whisper large
As someone who is currently relying on Whisper for some things, what models are those exactly? I still haven't found anything that is accurate as Whisper (large), are those models just faster or also as accurate/more accurate?