Statements (23)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
AI audio generation model
|
| gptkbp:architecture |
transformer-based
|
| gptkbp:availableOn |
gptkb:GitHub
|
| gptkbp:developedBy |
gptkb:Meta_AI
|
| gptkbp:generation |
audio from text prompts
|
| https://www.w3.org/2000/01/rdf-schema#label |
AudioGen
|
| gptkbp:input |
gptkb:text
|
| gptkbp:language |
English
|
| gptkbp:license |
gptkb:MIT_License
|
| gptkbp:notablePublication |
AudioGen: Textually Guided Audio Generation
|
| gptkbp:openSource |
true
|
| gptkbp:output |
audio
|
| gptkbp:relatedTo |
gptkb:MusicGen
gptkb:Meta_AI_Research |
| gptkbp:releaseYear |
2023
|
| gptkbp:supports |
environmental sounds
music generation sound effects generation |
| gptkbp:type |
text-to-audio model
|
| gptkbp:uses |
autoregressive modeling
|
| gptkbp:website |
https://audiogen.github.io/
|
| gptkbp:bfsParent |
gptkb:Audiocraft
|
| gptkbp:bfsLayer |
6
|