nomel3h agoHN ↗Word-level timestamps. Each word has precise start/end times and confidence scores.Neat. This is missing from many models.
exizt882h agoHN ↗I don't understand how these benchmarks get things so wrong. Nova-3 is by far the best model on the market in WER. Azure's STT is atrocious. And yet every benchmark rates Azure's STT higher than Nova-3's.
No weights, sadly. Bit of a nothingburger release.
Neat. This is missing from many models.
Mistral STT offers it, which is an open model.
I don't understand how these benchmarks get things so wrong. Nova-3 is by far the best model on the market in WER. Azure's STT is atrocious. And yet every benchmark rates Azure's STT higher than Nova-3's.
Mai 2 transcribe is giving me better results than nova
If only they had ZDR
$0.10/hour is a good price vs $0.30/hour for Gemini Transcribe 3.5.