Closed LqNoob closed 2 years ago
Hi there,
We do not need very accurate normalization stats. In the inference stage, we don't use any SpecAug (i.e., freqm=timem=0
) but reuse the same norm stats. You can certainly try using 48 or 0, and see which performs better, I assume they are similar.
-Yuan
Hi, thank you for your great work!
I have a question regarding the differences of the parameter values('freqm' ). When computing the normalization stats -- mean and std, the parameter values are 24. But during model training, it's 48. Why are their values different in these two processes?