About audio files

[andyzgj]

Hi, I downloaded the dataset and the format of all audio files are m4a.
But the code in audioVisual_dataset used "wavfile.read()" directly.
Does that mean I have to convert the audio files from m4a to wav by myself?
Or may be I miss something important?

[dengyuanjie]

You can use 'ffmpeg' command to convert the audio files.
https://github.com/clovaai/voxceleb_trainer/blob/master/dataprep.py