JNT

How to use the cpu training model?

2

I want to run the code on the cpu before using the GPU.

train.toml出错

6

你好呀，我在复现你的工作的时候发现，train.toml出错了，我发现是因为snr_range = [-5,20]和metrics = ["WB_PESQ", "NB_PESQ", "STOI", "SI_SDR"]这里有问题，把这两行注释掉就没问题。我在网上没找到解决方法，请问您遇到过这样的问题吗？期待您的回复

关于复现网络出现的问题

5

作者您好，昨天的问题不知道怎么就不见了。我邮箱收到了您的回复，训练loss是正常的。我现在依然在查找问题的根源所在。如果您能把test 模型的源码公开，这对我解决问题会有很大的帮助。有一点需要咨询一下您，计算loss时为什么是返回三个值？期望您的回复。 昨天的问题是：测试模型时输出为静音。

your work's torch version

1

Thanks your creative work. But I encountered a problem in the process of reproduction, and I suspect it was a version problem.The questions are as follows： File "D:\DLSPEECHENHANCEMENT\Uformer\Uformer-main\uformer\conv2d_cplx.py", line 37,...

update the detailed README please

9

Hello, I am a rookie of speech enhancement based on deep learning, could you update the detailed README ? thank you very much