ParaSpeechCLAP: A Dual-Encoder Speech-Text Model for Rich Stylistic Language-Audio Pretraining
Paper • 2603.28737 • Published
ParaSpeechCLAP: Dual-Encoder Speech-Text Model
The ParaSpeechCLAP models and datasets used to train them.
-
-
ajd12342/paraspeechclap-intrinsic
Audio Classification • Updated -
ajd12342/paraspeechclap-situational
Audio Classification • Updated -
ajd12342/paraspeechclap-combined
Audio Classification • Updated -
ajd12342/paraspeechcaps-intrinsic-train
Viewer • Updated • 945k • 62 -
ajd12342/paraspeechcaps-situational-train
Viewer • Updated • 96.2k • 53 -
ajd12342/paraspeechclap-eval-intrinsic
Viewer • Updated • 9.4k • 90 -
ajd12342/paraspeechclap-eval-situational
Viewer • Updated • 1.43k • 53 -
ajd12342/paraspeechclap-eval-combined
Viewer • Updated • 1.43k • 57