News for hackers. Stuff that matters.
Re:Universal Speech Model by Simon321 on Thursday March 30, 2023 @02:44AM (#35368945)
I saw deepgrams claims as well an believed them also, then i tried it, it was TERRIBLE. Don't believe them. It only does well on the benchmark they trained it on. It is faster though but the quality is terrible.
Re:Universal Speech Model by somebee on Thursday March 30, 2023 @03:04AM (#35369107)
Did you try their enhanced models? We're using it for relatively high-quality audio files and their accuracy is better than the whisper small.en model. More importantly, their word level timestamps is worlds better than whisper.