CLAP HTSAT Fused
JSON →A contrastive language-audio pretraining model using HTSAT audio encoder, enabling zero-shot audio classification and retrieval.
Dates
releasedMar 2023
Resources
API
full doc /v1/models/laion/clap-htsat-fused
A contrastive language-audio pretraining model using HTSAT audio encoder, enabling zero-shot audio classification and retrieval.