clap-htsat-fused is an open-source transformer-based model for audio classification and sound event recognition. Developed by LAION, it enables developers and researchers to identify and categorize sounds in audio data for various AI applications.
Clap Htsat Fused is a Voice, TTS & speech project. It focuses on automating the classification and recognition of sound events in audio data. It is built as an open-source project for audio AI developers and researchers. Clap Htsat Fused is open source under the Open Source license. It runs on the web, the command line, and API, and it can be self-hosted.
Behind Clap Htsat Fused is LAION, and it first shipped in 2022. The project is developed in the open on GitHub with 747 stars. Among its 5 catalogued features are audio classification, sound event recognition, and transformer-based.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do