Rookie

I also use GTX 1080ti gpus. The dataset is the noisy dataset of the DNS Challenge I synthesized, not the Voice_Bank dataset with 28 speakers.And I haven’t changed your network,...

I found that there are a few lines of code in train.py that take a lot of time, but we don’t really need this piece of data. if (index +...

I also used Torch-Pruning to prune lstm, but it didn’t work. It seems that the tool does not support the pruning operation of lstm.