thibaultcastells / frechet-audio-distance Goto Github PK

A lightweight library of Frechet Audio Distance calculation.

Currently, we support embedding from:

• VGGish by S. Hershey et al.
• PANN by Kong et al..

pip install frechet_audio_distance

from frechet_audio_distance import FrechetAudioDistance

# to use `vggish`
frechet = FrechetAudioDistance(
    model_name="vggish",
    use_pca=False, 
    use_activation=False,
    verbose=False
)
# to use `PANN`
frechet = FrechetAudioDistance(
    model_name="pann",
    use_pca=False, 
    use_activation=False,
    verbose=False
)
fad_score = frechet.score("/path/to/background/set", "/path/to/eval/set", dtype="float32")

Test 1: Distorted sine waves on vggish (as provided here) [notes]

FAD scores comparison w.r.t. to original implementation in google-research/frechet-audio-distance

Test 2: Distorted sine waves on PANN

• Run python3 -m build to build your version locally. The built wheel should be in dist/.
• pip install your local wheel version, and run pytest test/ to validate your changes.

VGGish in PyTorch: https://github.com/harritaylor/torchvggish

Frechet distance implementation: https://github.com/mseitzer/pytorch-fid

Frechet Audio Distance paper: https://arxiv.org/abs/1812.08466

PANN paper: https://arxiv.org/abs/1912.10211