1 build of Whisper large-v3-turbo measured on real machines — different packagers, precisions and engines, each a different file with its own numbers. The best each engine proved is first; every build has its own page with the machines and signatures behind it. 809M parameters, as the vendor states.
no context proved on this engine yet
proved by at least one build: Speech in
| build | publisher | precision | engine | whose work | context proved | best tok/s | machines |
|---|---|---|---|---|---|---|---|
| openai/whisper-large-v3-turbo | openai | FP16 | speech-hf | vendor | — | — | 2 |