Statements (28)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
speech recognition system
|
| gptkbp:architecture |
gptkb:transformation
|
| gptkbp:developer |
gptkb:OpenAI
|
| https://www.w3.org/2000/01/rdf-schema#label |
OpenAI Whisper
|
| gptkbp:input |
audio
|
| gptkbp:license |
gptkb:MIT_License
|
| gptkbp:memiliki_tugas |
automatic speech recognition
language identification |
| gptkbp:notableFeature |
robust to accents, background noise, and technical language
|
| gptkbp:output |
gptkb:text
|
| gptkbp:platform |
cross-platform
|
| gptkbp:programmingLanguage |
gptkb:Python
|
| gptkbp:releaseDate |
2022-09-21
|
| gptkbp:repository |
https://github.com/openai/whisper
|
| gptkbp:size |
gptkb:foundation
large medium small tiny |
| gptkbp:sourceModel |
open source
|
| gptkbp:supportsLanguage |
multiple languages
|
| gptkbp:trainer |
680,000 hours of multilingual and multitask supervised data
|
| gptkbp:uses |
translator
transcription speech-to-text |
| gptkbp:website |
https://openai.com/research/whisper
|
| gptkbp:bfsParent |
gptkb:Automatic_Speech_Recognition
|
| gptkbp:bfsLayer |
7
|