stable-audio-metrics
The project provides a set of technical metrics for assessing music and audio generative models. This includes tools like Fréchet Distance, Kullback–Leibler divergence, and CLAP score across different sampling rates for more realistic evaluation scenarios, such as long-form stereo content. These metrics accommodate variable-length inputs and favor GPU acceleration for efficiency. The documentation includes clear installation and troubleshooting instructions, making it approachable for those looking to compare outputs with Stable Audio without needing to download dataset resources.
