🎉 First release!
**Core Features**:
* Easily and efficiently compute audio embeddings with various models.
* Compute FAD∞ scores between two datasets for evaluation.
* Use pre-computed statistics ("weights") to compute FAD∞ scores from existing baselines.
* Compute per-song FAD to find outliers in the dataset.
**Supported Models**:
* [CLAP (Microsoft)](https://github.com/microsoft/CLAP)
* [CLAP (LAION)](https://github.com/LAION-AI/CLAP)
* [Encodec](https://github.com/facebookresearch/encodec)
* [MERT](https://huggingface.co/m-a-p/MERT-v1-95M)
* [VGGish](https://github.com/tensorflow/models/blob/master/research/audioset/vggish/README.md)
* [DAC](https://github.com/descriptinc/descript-audio-codec)
* [CDPAM](https://github.com/pranaymanocha/PerceptualAudio)