Whisper large-v3
Suveränitet och hosting
Inte hostad på LLM EU i den här distributionen: begäranden besvaras av den inbyggda mock-backenden i regionen dev-mock. Inga vikter körs.
Sammanfattning
Whisper large-v3 is OpenAI’s multilingual speech-recognition and speech-translation model with 1.54B parameters under the Apache-2.0 licence. It has a fixed 30-second receptive field and processes longer audio with a sliding window, and it uses 128 mel frequency bins rather than the 80 of earlier versions. The model card warns that it was evaluated on roughly ten languages and should be evaluated in-domain before deployment.
Specifikationer
- Leverantör
- OpenAI (US)
- Kontextfönster
- Inte verifierad: leverantören har inte dokumenterat detta påstående.
- Parametrar
- 1.54B
- Modaliteter
- audio
- Licens
- apache-2.0 · licence
- Öppna vikter
- yes
- Utgivningsdatum
- 07 nov. 2023
- Uppgifter
- translation, multilingual-support, summarization
Språk
Stark: en, de, fr, es, it, pt, nl, pl
Tillräcklig: sv, da, fi, cs, ro, el, uk, ru, tr, ar, zh, ja, ko, hi
Språk
Stark
- en
- de
- fr
- es
- it
- pt
- nl
- pl
Tillräcklig
- sv
- da
- fi
- cs
- ro
- el
- uk
- ru
- tr
- ar
- zh
- ja
- ko
- hi
Inte verifierad: leverantören har inte dokumenterat detta påstående. — a language is listed as strong only where a source claims it; the card links the evidence where one exists.
När den ska användas
Styrkor
- one model for transcription and translation to English
- long-standing tooling support across every major inference stack
- Apache-2.0 licence
Begränsningar
- fixed 30-second receptive field; longer audio needs chunking logic
- the card only claims strong recognition for about ten languages
- the card advises against using it for classification or speaker attributes