fschmid56 / EfficientAT

This repository aims at providing efficient CNNs for Audio Tagging. We provide AudioSet pre-trained models ready for downstream training and extraction of audio embeddings.
MIT License
233 stars 44 forks source link

Document ffmpeg requirement #22

Closed hendriks73 closed 1 year ago

hendriks73 commented 1 year ago

Hi there,

great work! Trying to run it I stumbled over the undocumented FFmpeg requirement (I believe torchaudio's StreamReader is the culprit). So I added info about ffmpeg <4.4 requirement. See also https://stackoverflow.com/q/76155851/942774

Cheers,

-hendrik

fschmid56 commented 1 year ago

Thanks!