quyuquan2019

Try changing the optimizer to Adam. I trained for five days and the loss dropped from 5.3 to 0.2, but when I was going to extract x-vector for LDA operation,...

How many people are in your training set? When my loss value is 0.2, I thought my model has been trained, so I plan to randomly extract 5 x-vectors and...

It is suggested that you can try to replace the original data set, use your own data set to extract x-vector, and verify whether speaker recognition can be performed. I'm...

Indeed, I think this library is great. I will not use Kaldi. I think all pytorch versions are easier to read and understand for me, but this library is a...

yes ,thanks,my friend, you code help me . now ,i start use my trainset to train this net. embedding a is hidden1 's output , and embedding b is hidden...

Cool, I hope the author can make a use of pyannote to do x-vector tutorial