In my setup, computing PESQ of all batches takes ~50% of total training time (with DCUNet-20).
Maybe we can compute PESQ in the background (it's on CPU anyways), or compute PESQ of a subset only.
For my experiments I've changed the code to only compute PESQ of 10% of samples.
In my setup, computing PESQ of all batches takes ~50% of total training time (with DCUNet-20).
Maybe we can compute PESQ in the background (it's on CPU anyways), or compute PESQ of a subset only.
For my experiments I've changed the code to only compute PESQ of 10% of samples.