For the training data, there may be different save formats, bitrates, file lengths. Need to see if there's already a built-in way to deal with this using pytorch.torchaudio, or if there's another utility to bring in. May also need to create and AudioUtil.py class to deal with this in a customized way.
For the training data, there may be different save formats, bitrates, file lengths. Need to see if there's already a built-in way to deal with this using pytorch.torchaudio, or if there's another utility to bring in. May also need to create and AudioUtil.py class to deal with this in a customized way.