Add diarization recipe v3 #347
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
|
The news part should be updated |
|
I think it is better to link the local directory and path.sh file directly if we reuse them. |
Update News section in README.md
Update clustering method
czy97
approved these changes
Aug 20, 2024
examples/voxconverse/v3/README.md
Outdated
| * Refer to [voxceleb sv recipe](https://github.com/wenet-e2e/wespeaker/tree/master/examples/voxceleb/v2) | ||
| * [pretrained model path](https://wespeaker-1256283475.cos.ap-shanghai.myqcloud.com/models/voxceleb/voxceleb_resnet34_LM.onnx) | ||
| * Speaker activity detection model: oracle SAD (from ground truth annotation) or system SAD (VAD model pretrained by silero, https://github.com/snakers4/silero-vad) | ||
| * Clustering method: spectral clustering |
There was a problem hiding this comment.
The clustering method should be umap + dbscan?
| @@ -29,7 +29,7 @@ | |||
| from wespeaker.cli.utils import get_args | |||
| from wespeaker.models.speaker_model import get_speaker_model | |||
| from wespeaker.utils.checkpoint import load_checkpoint | |||
| from wespeaker.diar.spectral_clusterer import cluster | |||
| from wespeaker.diar.umap_clusterer import cluster | |||
There was a problem hiding this comment.
@JiJiJiang I am not sure whether we should change the client script.
There was a problem hiding this comment.
Yes, just keep it as the better one.
|
|
||
| import torch | ||
| import silero_vad | ||
| from wespeaker.utils.file_utils import read_scp | ||
|
|
||
|
|
||
| def get_args(): | ||
| parser = argparse.ArgumentParser(description='') |
There was a problem hiding this comment.
should we also edit the v1 and v2 version, if we change the arguments of this script?
There was a problem hiding this comment.
Yes, also update the results if change into silero vad v5.1.
JunyiPeng00
pushed a commit
to JunyiPeng00/wespeaker_hubert
that referenced
this pull request
Jul 31, 2025
* Add diarization recipe v3 * resolve pylint issues and add missing modifications * eliminate trailing whitespace * deterministic clustering; update README.md * fix args usage in umap_clusterer.py * local import; remove unused diarization args; self.model.eval() when init * compact embedding clustering procedure into a single source file * link to local and path.sh; update requirements.txt and extract_emb.py * fix lint error: extract_emb.py * Update README.md Update News section in README.md * Update voxconverse/v3/README.md Update clustering method * Update README.md --------- Co-authored-by: Zhengyang Chen <chenzhengyang117@gmail.com>
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.
Add diarization recipe v3 for voxconverse dataset.
Highlights
Results
Dev set
Test set
Footnotes
Spot the conversation: speaker diarisation in the wild, https://arxiv.org/pdf/2007.01216.pdf ↩ ↩2 ↩3 ↩4 ↩5