facebookresearch / VisualVoice

Audio-Visual Speech Separation with Cross-Modal Consistency
Other
218 stars 35 forks source link

About audio files #16

Open andyzgj opened 2 years ago

andyzgj commented 2 years ago

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 commented 2 years ago

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