Whisper large-v3-turbo

OpenAI

Samo katalog Otvoreni utezi

Suverenost i hosting

Samo katalog

Ovaj je model u katalogu za referencu. Još nije hostan na LLM EU i nijedna vlastita krajnja točka ga ovdje ne poslužuje. Zahtjevi za njega idu izravno pružatelju, prema uvjetima tog pružatelja.

Sažetak

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.

Specifikacije

Pružatelj
OpenAI (US)
Kontekstni prozor
Nije provjereno: pružatelj nije dokumentirao ovu tvrdnju.
Parametri
0.81B
Modaliteti
audio
Licenca
mit · licence
Otvoreni utezi
yes
Datum izlaska
01. lis 2024.
Zadaci
translation, multilingual-support, cheap

Jezici

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

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

Jezici

Jako

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

Zadovoljavajuće

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

Nije provjereno: pružatelj nije dokumentirao ovu tvrdnju. — a language is listed as strong only where a source claims it; the card links the evidence where one exists.

Kada ga koristiti

Prednosti

  • 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

Ograničenja

  • 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