audio.cpp is a 0.4B-parameter GGUF model hosted on Hugging Face for use with compatible local inference software. It is intended for developers and machine-learning practitioners running audio processing workloads on their own hardware.
Audio.cpp is a Foundation models & chat project. It focuses on running audio model inference locally without relying on hosted providers. It is built as an open-source project for developers and machine-learning practitioners. Audio.cpp is open source under the Open Source license. It runs on the web and the command line, and it can be self-hosted.
It is developed by trklou. Key capabilities include GGUF format, local inference, and audio architecture.
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