Whisper small/tiny/base are almost four years old (they were not updated for Whisper v2 or v3). Is there really nothing better to benchmark against by now?

▲

satvikpendem 7 hours ago | parent | next [-]

There are many [0], you can search and filter by streaming and open weight only as well.

Looks like Voxtral and Nvidia's Nemotron are best.

[0] https://artificialanalysis.ai/speech-to-text/non-streaming

▲

Chu4eeno 7 hours ago | parent | prev [-]

There's tons, Parakeet was the last I remember seeing which seemed to gain traction (independent lightweight implementations etc).

▲

garblegarble 7 hours ago | parent | next [-]

I have tried everything (that will run on a 12GB RTX 4070) and I have yet to find anything with better accuracy than Whisper V2 Large for my dataset (discord audio from TTRPG sessions, isolated per-speaker, mostly non-American accents)

	▲	Ey7NFZ3P0nzAe 3 hours ago \| parent \| next [-]
		Voxtral to me what better
	▲	xd1936 7 hours ago \| parent \| prev \| next [-]
		Same, for my English-only podcast
	▲	modeless 5 hours ago \| parent \| prev [-]
		Not v3?

▲

satvikpendem 7 hours ago | parent | prev | next [-]

Nvidia's Nemotron subsumes their older Parakeet model now even for real time streaming.

▲

daemonologist 7 hours ago | parent | prev | next [-]

Parakeet is way faster (on Nvidia hardware) but not quite as accurate in my experience.

	▲	meatmanek 6 hours ago \| parent [-]
		It's also super fast on CPU.

▲

behnamoh 7 hours ago | parent | prev [-]

Parakeet isn't as good as whisper large.