Update feature_extractor.py #1038
Open
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
abodacs
suggested changes
Oct 26, 2024
| if padding: | ||
| waveform = torch.nn.functional.pad(waveform, (0, self.n_samples)) | ||
|
|
||
| window = torch.hann_window(self.n_fft).to(waveform.device) |
There was a problem hiding this comment.
I'll take a look...
There was a problem hiding this comment.
This is actually an optimization. In the old version, a new Hann window was being created and moved to the device every time call was executed. The new version creates it once during initialization and caches it as an instance variable (self.window).
faster_whisper/feature_extractor.py
Outdated
| else waveform | ||
| ) | ||
| # Move waveform to the target device if necessary | ||
| if self.device == "cuda" and not waveform.is_cuda: |
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Outdated suggestions cannot be applied.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.
Added mel filter bank caching to FeatureExtractor class to optimize memory usage and reduce computational overhead when processing multiple audio files with identical parameters, particularly beneficial for batch processing scenarios.