1.1.0

What's Changed

• Added support for Python 3.12 & 3.13
• Fixed incompatibility between MERT & transformer
• Upgraded dependencies
• Update model_loader.py by @yc-li20 in #7
• Update README.md by @yc-li20 in #8
• Update model_loader.py by @yc-li20 in #13
• Fix sqrt import by @timohromadka in #17
• Revert "Fix sqrt import" by @hgamper in #18
• Adding reference by @yc-li20 in #34

Full Changelog: 1.0.0...1.1.0

1.0.0

🎉 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)
• CLAP (LAION)
• Encodec
• MERT
• VGGish
• DAC
• CDPAM