Optimise as_windowed and apply :reflect padding to the whole input #17
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
jonatanklosko
changed the title
jonatanklosko
commented
Aug 30, 2023
| Keyword.put(opts, :padding, [{div(window_length, 2), div(window_length, 2) - 1}]) | ||
| Keyword.put(opts, :padding, [{div(window_length, 2), div(window_length, 2)}]) |
There was a problem hiding this comment.
@polvalente this changes some output shapes (the currently failing tests), but that's what torch.stft does. wdyt?
There was a problem hiding this comment.
Does it just decrease the number of windows?
There was a problem hiding this comment.
The opposite, it adds an extra window, where half of the window is padded.
polvalente
approved these changes
Aug 30, 2023
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Changes to
indexed_addtoput_slice.Also, instead of applying
:reflectpadding within each incomplete window, we apply it to the input sequence at the beginning. This is whattorch.stftdoes and what huggingface/transformers do in pre-processing.