Torch-KWT

Torch-KWT copied to clipboard

where is the Knowledge Distillation in the code

1

hello ，distillation of knowledge is mentioned In the paper , but i didn't see in the code

huacilang

In file Torch-KWT/model/kwt.py, the PostNorm class is written as: ` class PostNorm(nn.Module): def __init__(self, dim, fn): super().__init__() self.norm = nn.LayerNorm(dim) self.fn = fn def forward(self, x, **kwargs): return self.norm(self.fn(x, **kwargs))`...

jackykj

hello，when i change the model from kwt-1 to kwt-2 or kwt -3，the results of kwt-2 and kwt-3 are worse than kwt-1. The accuracy of kwt-2 is about 91% and the...

youngJ-code

Want the implement of "TO WAKE-UP OR NOT TO WAKE-UP: REDUCING KEYWORD FALSE ALARM BY SUCCESSIVE REFINEMENT"

1

I am very interested in "TO WAKE-UP OR NOT TO WAKE-UP: REDUCING KEYWORD FALSE ALARM BY SUCCESSIVE REFINEMENT"this work.And I sincerely want to know the code implement of this work.plz.

Fylll