Crazylov3

> Hey > > Does it work if you use 0.9 instead of -0.9? No, It doesn't

> What's the sample rate? it is 8000

> And what do you mean with cpu version github? Are you refering to https://github.com/iver56/audiomentations? Yep, that what i mean.

Torch-pitch-shift works fine, thank you!

By default, pytorch do it for you, automatically

Hi, could you share the training code with me as well? [email protected] Thanks!

You couldn't use shortcut if you use nn.Sequential :)

The main purpose of the shortcut (also known as skip connection) in deep neural networks is to help with the flow of information and improve gradient flow during training. In...

In general, you can use shortcut everywhere you want. If you have only 1 configs, it will easy to implement shortcut in a block, then you can put these block...

@007fox-bit Are you still working on this. I also try to re-train this model. However, I face with issue related to binary description training. Have you done yet?