Output hiddens states from all the transformer layers of huggingface_wav2vec #1570
Conversation
This file contains hidden or 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
Adel-Moumen
requested changes
Sep 17, 2022
Collaborator
Adel-Moumen
left a comment
There was a problem hiding this comment.
Thanks for the PR!
Please fix some minor issues.
Note: I will refactor the hugging face interface so it might be possible that this code will change in the future.
Collaborator
Author
|
Hi @Adel-Moumen, thanks for the review, the fix is done. |
Adel-Moumen
approved these changes
Sep 17, 2022
Collaborator
Adel-Moumen
left a comment
There was a problem hiding this comment.
lgtm ! Thanks for the pr. 🤗
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.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.
Hello, this PR intends to add an option to ouput all the layers of
HuggingFaceWav2Vec2. Some works have shown that different layers of wav2vec/HuBert/WavLM have different impact on different speech tasks. So this change may allow to study this effect.An attribute
output_all_hiddens(default:False) is added:If True: outputs the hidden states from all transformer layers
If False: outputs the hidden states only from the last transformer layer