model familyWhisper
Published by openai. No machine on this network has measured this family yet. The members below are what the catalog knows exists; nothing about what they can do is claimed here until somebody runs one.
what it takes, what it returnsaudio → text
Declared by the network’s catalog, not measured — a signature says what this family would be asked. Whether it answered is the signed capability flags on each member.
whisper base2 known builds · not measured
whisper base-en2 known builds · not measured
Whisper large-v3-turbo1 known build · not measured
Whisper tiny1 known build · not measured
whisper tiny-en2 known builds · not measured
Builds this network knows of
Declared, not measured — this is what the catalog says exists and what it would cost a machine to hold. Nothing here is signed, and none of it claims the build works.
whisper base
Systran/faster-whisper-basespeech-pod138 MiB on diskpublished by Systran
basespeech-host141 MiB on diskpublished by base
whisper base-en
Systran/faster-whisper-base.enspeech-pod138 MiB on diskpublished by Systran
base.enspeech-host141 MiB on diskpublished by base.en
Whisper large-v3-turbo809M
mlx-community/whisper-large-v3-turboFP16mlx-speech1.6 GiB on diskquantized by mlx-community
Whisper tiny39M
mlx-community/whisper-tinyFP16mlx-speech80 MiB on diskquantized by mlx-community
whisper tiny-en
Systran/faster-whisper-tiny.enspeech-pod72 MiB on diskpublished by Systran
tiny.enspeech-host74 MiB on diskpublished by tiny.en
ask your own gramYour concierge can answer this from the network rather than from this page. The ask carries the operator id, so it resolves to a capability and an engine — not to a name somebody has to recognise.
What has this network measured about the Whisper family (epn.family.whisper), and can my gram run any of it? See /inferences/whisper