[MAEB] Add proper wav2clip text encoder #3849
Merged
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
KennethEnevoldsen
requested changes
Jan 5, 2026
| self.clip = CLIPModel.from_pretrained(model_name, revision=revision).to(device) | ||
| # text side (CLIP) - we use the standard OpenAI CLIP model as mentioned in paper | ||
| clip_model_name = "openai/clip-vit-base-patch32" | ||
| self.clip = CLIPModel.from_pretrained(clip_model_name).to(device) |
Contributor
There was a problem hiding this comment.
add revision as well
Contributor
There was a problem hiding this comment.
You should be able to load it directly onto the device using the device_map
| # Pad with zeros | ||
| pad_length = max_length - wav.shape[-1] | ||
| padded_wav = torch.nn.functional.pad(wav, (0, pad_length)) | ||
| padded_wav = np.pad(wav, (0, pad_length), mode="constant") |
Contributor
There was a problem hiding this comment.
torch is fine - no need to change
Contributor
Author
There was a problem hiding this comment.
Changed back. I think some dataset gave an error when using torch but can't remember which or if it was because of something else. For now, changed back to torch. They are equivalent in 1D audio arrays.
Samoed
reviewed
Jan 5, 2026
Member
There was a problem hiding this comment.
Can you remove link to submodule?
Member
|
I think this the same as #3781 |
Contributor
Author
|
Yup closing the other one. |
Contributor
Author
|
@Samoed Anything else needed here? |
AdnanElAssadi56
changed the title
Samoed
approved these changes
Jan 7, 2026
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 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Outdated suggestions cannot be applied.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.
If you add a model or a dataset, please add the corresponding checklist: