Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

speaker_loss.weight is not in the model. #5

Closed
yzyouzhang opened this issue Jan 29, 2022 · 1 comment
Closed

speaker_loss.weight is not in the model. #5

yzyouzhang opened this issue Jan 29, 2022 · 1 comment

Comments

@yzyouzhang
Copy link

yzyouzhang commented Jan 29, 2022

Thanks for your repo. I have successfully replicated the baseline2 performance.
I encounter the following messages when I run python save_embeddings.py. It did not crash the program but I wonder where is the second line printed from since I did not find it. I am also not sure if it will cause potential issues.

Device: cuda
speaker_loss.weight is not in the model.
Getting embedgins from set trn...

Thanks.

@Jungjee
Copy link
Collaborator

Jungjee commented Jan 29, 2022

Hi,
It is from using below code.
It's related to the output layer (the one with softmax non-linearity) and
causes no problems.

def load_parameters(trg_state, path):

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants