Whisper large-v3-turbo

OpenAI

Catalogue only Open weights

Sovereignty and hosting

Catalogue only

This model is catalogued for reference. It is not hosted on LLM EU yet, and no first-party endpoint serves it here. Requests to it go to the provider directly, under that provider's own terms.

Summary

Whisper large-v3-turbo is a distilled version of Whisper large-v3 with 809M parameters, released under the MIT licence. It keeps the same 30-second receptive field and the multilingual language coverage of large-v3 but decodes faster, which is the reason to prefer it where latency matters. The model card is the shared Whisper card and publishes no benchmark table specific to this variant.

Specifications

Provider
OpenAI (US)
Context window
Not verified: the provider has not documented this claim.
Parameters
0.81B
Modalities
audio
License
mit · licence
Open weights
yes
Release date
01 Oct 2024
Tasks
translation, multilingual-support, cheap

Languages

Strong: en, de, fr, es, it, pt, nl, pl

Adequate: sv, da, fi, cs, ro, el, uk, ru, tr, ar, zh, ja, ko, hi

Languages

Strong

  • en
  • de
  • fr
  • es
  • it
  • pt
  • nl
  • pl

Adequate

  • sv
  • da
  • fi
  • cs
  • ro
  • el
  • uk
  • ru
  • tr
  • ar
  • zh
  • ja
  • ko
  • hi

Not verified: the provider has not documented this claim. — a language is listed as strong only where a source claims it; the card links the evidence where one exists.

When to use it

Strengths

  • roughly half the parameters of large-v3 at lower latency
  • MIT licence, more permissive than the Apache-2.0 parent
  • same multilingual transcription coverage as large-v3

Limits

  • a distillation of large-v3, so transcription accuracy is below the parent model
  • no benchmark table specific to this variant is published on the model card
  • fixed 30-second receptive field, so longer audio needs chunking logic