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

Issue during testing while training with 80 Fbins hyperparameter #118

Closed
csetanmayjain opened this issue Dec 6, 2022 · 6 comments
Closed

Comments

@csetanmayjain
Copy link

Hi,
I train a new model after changing Fbins to 80. The model trained successfully, but when I tried to test the model on some test cases, getting the following error:

RuntimeError: The size of tensor a (80) must match the size of tensor b (40) at non-singleton dimension 2

I just change the hyperparameter in conf file, apart from this, do we need to make change anywhere else in the code?
Is it something hard coded?

@mlxu995
Copy link
Collaborator

mlxu995 commented Dec 10, 2022

please make sure that the configs in testing are identical to that for training.

@csetanmayjain
Copy link
Author

those are the same only
even I'm taking the configuration from training only for testing

@mlxu995
Copy link
Collaborator

mlxu995 commented Jan 15, 2023

It sees that the cmvn used for testing is not identical to the one used for training. If you changed the work dir and the cmvn file?

@csetanmayjain
Copy link
Author

I didn't make any changes in the directory

@mlxu995
Copy link
Collaborator

mlxu995 commented Jan 15, 2023

I trained a model that also set Fbins to 80. It seems nothing abnormal when testing it.
Could you make a new work dir and re-run the script from stage 0.

@csetanmayjain
Copy link
Author

sure, I will give it a try again

@mlxu995 mlxu995 closed this as completed May 26, 2023
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