|
gptkbp:instanceOf
|
speech recognition model
|
|
gptkbp:author
|
gptkb:Sam_Altman
gptkb:Alec_Radford
gptkb:Christine_Wang
gptkb:Daniel_R._De_Freitas
gptkb:David_Luan
gptkb:Jong_Wook_Kim
gptkb:Mike_Wu
gptkb:Rewon_Child
gptkb:Susan_Xu
gptkb:Taesung_Park
|
|
gptkbp:availableOn
|
gptkb:GitHub
|
|
gptkbp:citation
|
gptkb:Robust_Speech_Recognition_via_Large-Scale_Weak_Supervision
2022
|
|
gptkbp:developedBy
|
gptkb:OpenAI
|
|
gptkbp:hasModel
|
gptkb:transformation
|
|
gptkbp:hasVariant
|
gptkb:foundation
large
medium
small
tiny
|
|
https://www.w3.org/2000/01/rdf-schema#label
|
Whisper
|
|
gptkbp:input
|
audio
|
|
gptkbp:language
|
gptkb:Python
|
|
gptkbp:license
|
gptkb:MIT_License
|
|
gptkbp:memiliki_tugas
|
automatic speech recognition
language identification
speech translation
|
|
gptkbp:notableFor
|
multilingual transcription
robustness to accents and background noise
|
|
gptkbp:openSource
|
true
|
|
gptkbp:output
|
gptkb:text
|
|
gptkbp:pretrained
|
true
|
|
gptkbp:releaseDate
|
2022
|
|
gptkbp:repository
|
https://github.com/openai/whisper
|
|
gptkbp:supportsLanguage
|
gptkb:Arabic
gptkb:Chinese
gptkb:French
gptkb:German
gptkb:Italian
gptkb:Korean
gptkb:Russian
gptkb:Spanish
Dutch
English
Japanese
Polish
Portuguese
Turkish
|
|
gptkbp:trainer
|
680,000 hours of multilingual and multitask supervised data collected from the web
|
|
gptkbp:bfsParent
|
gptkb:GitHub
gptkb:OpenAI
gptkb:OpenAI_API
gptkb:Rebecca_Curci
|
|
gptkbp:bfsLayer
|
5
|