-
Notifications
You must be signed in to change notification settings - Fork 0
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
Implements two front-ends for acoustic encoders #17
Conversation
4aaa978
to
ba3fb06
Compare
Some tests regarding the downsampling shapes (similar to #4) would be nice :) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I think the main problem is that the VGG is applied in the wrong way. Or at least inconsistent to how it usually is done. I don't think this is intended this way.
I have two questions here,
|
already added but not pushed yet :)
I was thinking about putting this as an option into the frontend: with param |
tests fail due to the seq mask update missing. I am not 100% sure how to perform the update in a clean fashion. Is there a PyTorch way to do this? |
I'm not exactly sure what you refer to. What update do you mean? You mean how to compute the seq mask which is supposed to be returned by the frontend? As I mentioned, you could apply maxpooling with the same striding and kernel size just as the other operations. |
this would also work for conv layers? |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I would change the code to only support tuples instead of both tuples and integer, this makes the code more readable and more consistent.
I'm not sure I agree. PyTorch itself also supports both. And the more common use case it that the user provides just a single int. |
Was this added in the final version of the PR, I don't seem to find it.. |
This is not specific for the Conformer so maybe
parts/conformer
is not the right place?