MAEB Model MuQ-MuLan#2909
Merged
isaac-chung merged 6 commits intoembeddings-benchmark:maebfrom Jul 21, 2025
Merged
Conversation
…o input types. Updated tensor conversion logic for numpy arrays and lists, ensuring compatibility with existing torch tensor formats. Improved resampling handling for audio inputs.
isaac-chung
reviewed
Jul 16, 2025
| requires_package(self, "muq", "pip install 'mteb[muq]'") | ||
| from muq import MuQMuLan | ||
|
|
||
| self.model_name = model_name |
Collaborator
There was a problem hiding this comment.
Is this used anywhere else?
Comment on lines
+47
to
+50
| def _handle_batch( | ||
| self, batch: AudioData | Iterable[tuple[AudioData, str]] | ||
| ) -> list[torch.Tensor]: | ||
| """Handle a single batch of audio data.""" |
Collaborator
There was a problem hiding this comment.
Seeing a lot of repeated code with the other PRs. Maybe we can extract and reuse this in mteb/models/audio_utils.py or something.
|
|
||
| return text_embeds.cpu().numpy() | ||
|
|
||
| def encode( |
Collaborator
There was a problem hiding this comment.
encode is really just for text embeddings. It has been confused and we should also fix the rest of the audio models separately.
| loader=partial(MuQMuLanWrapper, model_name="OpenMuQ/MuQ-MuLan-large"), | ||
| name="OpenMuQ/MuQ-MuLan-large", | ||
| languages=["eng-Latn", "zho-Hans"], # English and Chinese support | ||
| revision="8a081dbcf84edd47ea7db3c4ecb8fd1ec1ddacfe8a081dbcf84edd47ea7db3c4ecb8fd1ec1ddacfe", |
Collaborator
There was a problem hiding this comment.
Is this a GH commit hash?
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Added Audio Retrieval Model:
OpenMuQ/MuQ-MuLan-largeResults:
JamAltArtistA2ARetrieval.json
JamAltLyricA2TRetrieval.json
JamAltLyricT2ARetrieval.json