Package profile
msclap
- Summary: CLAP (Contrastive Language-Audio Pretraining) is a model that learns acoustic concepts from natural language supervision and enables “Zero-Shot” inference. The model has been extensively evaluated in 26 audio downstream tasks achieving SoTA in several of them including classification, retrieval, and captioning.
- Author: Benjamin Elizalde
- License: MIT License
- Number of releases: 5
- First release: 1.3.1 on 2023-10-12
- Latest release: 1.3.4 on 2025-05-23
- Latest release size: 30.4 KB (pure Python wheel)