karson

a easy problem

17

The initial paper directly uses $\epsilon$ minus the noise estimated by model in the training stage,why the way you use divides by square root 1-$a_0$ additionally?

I notice there is a "snr_process" function in inference.py and there may be a "scoring" file in valid.But I can't find them in this repository

I try to train your model in my device or use your pretrained model directly on Voicebank dataset.But the both performance is different from that in your paper.I can only...

基本上刚进入就退出，而任务需要5秒停留