Oktai Tatanov

@MTlab @gamewang123 @MengXinChengXuYuan I have the same problem. Any idea what problem is?

@kirtov you can follow at #10

@wengong-jin Don't you think that it can influence on training and, therefore, result? Because your program could be use previous state of list. Can you check that moment? It refers...

@wengong-jin great! I checked too and didn't find bugs due to this issue. Thank you and I suggest to close this issue as soon as you will update your code...

@qmpzzpmq you can use `torchaudio.transforms.MelSpectrogram` as alternative

@qmpzzpmq for example, check this issue: https://github.com/pytorch/audio/issues/157#issuecomment-513872666

@knighton is it already in release? I still have this problem (PermissionError: [Errno 13] Permission denied: '/000000_locals')

@ritheshkumar95 @eeishaan could you check this issue? It looks like published configs have empty `rates` list => no one MSD discriminator is initialized. References: https://github.com/descriptinc/descript-audio-codec/blob/main/conf/final/44khz.yml#L16 https://github.com/descriptinc/descript-audio-codec/blob/main/dac/model/discriminator.py#L203

@pseeth