Closed thtran97 closed 4 years ago
This is because there exists negative-infinite values in log mel spectrogram features. This leads to the nan value when doing loss.backward().
One of the solution that i made is : converting all these negative infinite values into zeros. I am not sure whether there are any better solutions ?
This is because there exists negative-infinite values in log mel spectrogram features. This leads to the nan value when doing loss.backward().
One of the solution that i made is : converting all these negative infinite values into zeros. I am not sure whether there are any better solutions ?