pyannote pyannote-audio issues

pyannote / pyannote-audio

Neural building blocks for speaker diarization: speech activity detection, speaker change detection, overlapped speech detection, speaker embedding

http://pyannote.github.io

MIT License

6.37k stars 784 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

fix a bug than happens when less than min(self.batch_size, 9) examples are used in the validation

#1792 antoinelaurent closed 2 days ago
1
update weights optimization

#1791 clement-pages opened 4 days ago
3
DER Calculation on the Aishell-4 Dataset Using pyannote.audio Model Returns NaN

#1790 sipercai closed 3 days ago
4
ToTaToNet Model Weights not Updated when Disabling Fine-Tuning of WavLM

#1789 ruixCMU opened 6 days ago
0
Fix balance

#1787 FrenchKrab opened 1 week ago
0
doc: update PyTorch reference

#1785 emmanuel-ferdman closed 2 weeks ago
2
feat(model): add `wav2vec_frozen` option to freeze/unfreeze `wav2vec` in `SSeRiouSS` architecture

#1784 hbredin closed 2 weeks ago
0
BREAKING(task): drop support for multilabel training

#1783 hbredin closed 2 weeks ago
0
Determine exact the numbers of speakers in diarization pipeline

#1781 shron1010 opened 2 weeks ago
1
Remove/Exclude overlapping segment for speaker diarization

#1780 hkpmatt opened 3 weeks ago
3
Remove pytorch_metric_learning dependency

#1778 pchampio closed 3 weeks ago
3
wip: add DiariZen architecture

#1776 hbredin opened 1 month ago
0
Alignment of separation output and diarization

#1775 Lebourdais closed 1 month ago
2
feat: add support for `k-means` clustering

#1774 hbredin closed 1 month ago
0
Hi, I'm currently trying to use an updated wespeaker voice model like the one shown in the picture, but when I follow the file pyannote/audio/models/embedding/wespeaker/convert.py I can't adapt it, it shows the following error, how do I change ？

#1772 LiLiWangzz opened 1 month ago
1
replace `cpwer` by `min_cpwer` in cpwer breakdown cell

#1771 clement-pages closed 1 month ago
2
Speech Separation cracking the volume too high

#1770 ajtopper closed 1 month ago
2
fix index errors in separation pipeline

#1769 clement-pages closed 1 week ago
2
Update pyannote-audio installation version number

#1768 BNarayanaReddy closed 2 months ago
1
Dependency errors while running the evaluation notebook for the speech separation uploaded recently

#1767 BNarayanaReddy closed 2 months ago
5
improve: skip validation chunks with too many speakers

#1762 hbredin opened 2 months ago
0
feat: add "hidden" option to ProgressHook

#1761 hbredin closed 1 month ago
0
fix: fix support for CoreML export

#1760 hbredin opened 2 months ago
0
improve: remove unnecessary return

#1759 hbredin closed 1 month ago
0
numpy.NAN crash

#1758 KiARC closed 2 months ago
2
AttributeError: module 'triton' has no attribute 'language'

#1757 Alonelymess closed 2 months ago
3
Declaring pipeline variables causes torch.jit model fail to execute

#1756 WelkinYang opened 2 months ago
1
[Unexpected Performance Drop] Using 44.1K sample_rate vs. default 16K leads to better performance in `pyannote/speaker-diarization-3.1`

#1755 ai-nikolai opened 2 months ago
5
VAD model

#1754 adriondragon closed 1 month ago
6
High CPU usage during embeddings step of diarization

#1753 henriklied closed 2 months ago
1
Diarization pipeline fails at end of audio file (RuntimeError: Sizes of tensors must match except in dimension 0.)

#1752 ccmilne opened 2 months ago
3
Possible to use reference speaker embeddings in Pyannote diarization pipeline?

#1750 Arche151 opened 3 months ago
2
Doc: fix partially removed docstring

#1749 huisman closed 3 months ago
1
Question: from custom segmentation to custom diarization model

#1748 IzzyHibbert closed 3 months ago
4
[Speech Separation/ValueError] v.3.3 - "speech_separation.py", line 648, in apply np.concatenate(remaining_zeros) ValueError: need at least one array to concatenate

#1747 ai-nikolai closed 4 days ago
2
Issue in distance threshold parameter

#1746 manish-kumar-iisc opened 3 months ago
0
Can pyannote-audio be set to distinguish the number of people？

#1742 Erwen222 opened 4 months ago
1
When's the next release? (for numpy 2.0 compatibility)

#1741 sbyrne-ellevest closed 2 months ago
2
AttributeError: partially initialized module 'torchaudio' has no attribute 'lib' (most likely due to a circular import)

#1740 behroozazarkhalili opened 4 months ago
0
After fine-tuning with MagicData-RAMC dataset，i test on Aishell-4 dadaset DER increased.

#1738 Arnold134777 closed 4 months ago
2
The timeline is wrong

#1737 Lixi20 opened 4 months ago
1
save speech separation results to disk throw IndexError，size of diarization.labels() and shape of sources.data is not same

#1735 yinyao closed 1 week ago
6
When fine tuning pretrained segmentation model using pyannote.audio==3.1.1 on well-defined and registered custom finance dataset, it shows the following error message 'PicklingError: Can't pickle <class 'pyannote.database.registry.Finance'>: attribute lookup Finance on pyannote.database.registry failed'

#1734 ZhouFang928 opened 4 months ago
4
Mismatch between DiscreteDiarizationErrorRate and DiarizationErrorRate

#1733 hhd52859 closed 4 months ago
3
Fix numpy.NAN which is numpy.nan

#1732 metal3d closed 4 months ago
2
feat(clustering): Add KMeans GPU clustering support

#1731 SkywalkerDarren opened 5 months ago
1
fix: peak-normalize separated sources

#1730 joonaskalda closed 1 month ago
0
outputs of separation module is clipping

#1729 faroit closed 1 month ago
6
setup: drop support for Python 3.8

#1728 hbredin closed 5 months ago
0
3.3 dependencies

#1727 faroit closed 5 months ago
2