Anuj Diwan

ajd12342's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

authored a paper about 1 month ago

ParaSpeechCLAP: A Dual-Encoder Speech-Text Model for Rich Stylistic Language-Audio Pretraining

Paper • 2603.28737 • Published Mar 30

updated a collection about 1 month ago

ParaSpeechCLAP: Dual-Encoder Speech-Text Model

Collection

The ParaSpeechCLAP models and datasets used to train them. • 9 items • Updated about 1 month ago

updated 5 datasets about 1 month ago

ajd12342/paraspeechcaps-situational-train

Viewer • Updated Apr 6 • 96.2k • 24

ajd12342/paraspeechcaps-intrinsic-train

Viewer • Updated Apr 6 • 945k • 100

ajd12342/paraspeechclap-eval-combined

Viewer • Updated Apr 6 • 1.43k • 143

ajd12342/paraspeechclap-eval-situational

Viewer • Updated Apr 6 • 1.43k • 122

ajd12342/paraspeechclap-eval-intrinsic

Viewer • Updated Apr 6 • 9.4k • 209

updated 3 models about 1 month ago

ajd12342/paraspeechclap-combined

Audio Classification • Updated Apr 6

ajd12342/paraspeechclap-situational

Audio Classification • Updated Apr 6

ajd12342/paraspeechclap-intrinsic

Audio Classification • Updated Apr 6

updated a collection about 2 months ago

ParaSpeechCLAP: Dual-Encoder Speech-Text Model

Collection

The ParaSpeechCLAP models and datasets used to train them. • 9 items • Updated about 1 month ago

published 2 datasets about 2 months ago

ajd12342/psc-intrinsic-test-dataset-v3-zsc-pitch

Viewer • Updated Jun 21, 2025 • 1.44k • 5

ajd12342/psc-intrinsic-test-dataset-v3-zsc-texture

Viewer • Updated Jun 21, 2025 • 1.09k • 6