pyannote/pyannote-audio

Issues

• huggingface_hub.errors.HFValidationError: Repo id must be in the form 'repo_name' or 'namespace/repo_name': '/home/ubuntu/whisperx/pyannote-offline/config.yaml'. Use `repo_type` argument if needed.

  #1800 opened 2 days ago by lucasmirachi
  8

• Diarization pipeline fails at end of audio file (RuntimeError: Sizes of tensors must match except in dimension 0.)

  #1752 opened 6 months ago by ccmilne
  4

• 3.3.2 or 3.3.1?!

  #1852 opened 5 days ago by FeatureSpitter
  0

• run pyannote-audio follow to tutorial and it didn't work

  #1849 opened 13 days ago by chenfuckthesky
  0

• Issue in distance threshold parameter

  #1746 opened 16 days ago by manish-kumar-iisc
  1

• Diarization Causes High System Memory Usage

  #1819 opened 3 months ago by agorman
  1

• Can pyannote-audio be set to distinguish the number of people？

  #1742 opened a month ago by Erwen222
  2

• AttributeError: partially initialized module 'torchaudio' has no attribute 'lib' (most likely due to a circular import)

  #1740 opened a month ago by behroozazarkhalili
  1

• The timeline is wrong

  #1737 opened a month ago by Lixi20
  2

• Is pyannote/diariazation pipeline very sensitive to language?

  #1821 opened 2 months ago by ywangwxd
  1

• pipeline breaks libcudnn_ops_infer library if model is not used

  #1823 opened 2 months ago by jzju
  0

• Warning suppression

  #1832 opened a month ago by antoinelaurent
  0

• 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 opened a month ago by ZhouFang928
  5

• Why is pyannote not using my GPU ro CPU? So slow too.

  #1702 opened a month ago by CrackerHax
  6

• How to report a security issue responsibly?

  #1828 opened 2 months ago by zpbrent
  0

• Can't load pyannote

  #1825 opened 2 months ago by CrackerHax
  1

• 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 opened 5 months ago by LiLiWangzz
  2

• `torchaudio.info.num_frames` can give wrong results so it can provide false exceptions

  #1724 opened 9 months ago by grazder
  3

• Using speech-separation-ami-1.0, results a distorted audio, much louder than the original

  #1818 opened 3 months ago by danielsasso
  0

• speaker-diarization-3.0 won't load, ONNX error

  #1814 opened 3 months ago by sedol1339
  2

• Running speaker-diarization-3.1 leads to GPU failure

  #1813 opened 3 months ago by sedol1339
  2

• Possible to use reference speaker embeddings in Pyannote diarization pipeline?

  #1750 opened 7 months ago by Arche151
  3

• Separation stitching is wrong when two local speakers are assigned to the same cluster

  #1811 opened 3 months ago by hbredin
  0

• Wavlm modules are always in `eval` mode when training `ToTaToNet` and `SSeRiouSS` models

  #1793 opened 3 months ago by clement-pages
  2

• ToTaToNet Model Weights not Updated when Disabling Fine-Tuning of WavLM

  #1789 opened 3 months ago by ruixCMU
  1

• What is the purpose of the Resegmentation and AdaptiveVoiceActivityDetection Pipeline?

  #1700 opened 3 months ago by asusdisciple
  2

• DER Calculation on the Aishell-4 Dataset Using pyannote.audio Model Returns NaN

  #1790 opened 4 months ago by sipercai
  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 opened 4 months ago by ai-nikolai
  2

• save speech separation results to disk throw IndexError，size of diarization.labels() and shape of sources.data is not same

  #1735 opened 4 months ago by yinyao
  6

• Determine exact the numbers of speakers in diarization pipeline

  #1781 opened 4 months ago by shron1010
  1

• Remove/Exclude overlapping segment for speaker diarization

  #1780 opened 4 months ago by hkpmatt
  3

• Speakers with similar pitch are difficult to distinguish

  #1712 opened 10 months ago by ChristianNSchmitz
  3

• [Unexpected Performance Drop] Using 44.1K sample_rate vs. default 16K leads to better performance in `pyannote/speaker-diarization-3.1`

  #1755 opened 6 months ago by ai-nikolai
  5

• VAD model

  #1754 opened 5 months ago by adriondragon
  6

• outputs of separation module is clipping

  #1729 opened 5 months ago by faroit
  6

• Speech Separation cracking the volume too high

  #1770 opened 5 months ago by ajtopper
  2

• Declaring pipeline variables causes torch.jit model fail to execute

  #1756 opened 6 months ago by WelkinYang
  1

• Dependency errors while running the evaluation notebook for the speech separation uploaded recently

  #1767 opened 6 months ago by BNarayanaReddy
  5

• High CPU usage during embeddings step of diarization

  #1753 opened 6 months ago by henriklied
  1

• numpy.NAN crash

  #1758 opened 6 months ago by KiARC
  2

• When's the next release? (for numpy 2.0 compatibility)

  #1741 opened 6 months ago by sbyrne-ellevest
  2

• AttributeError: module 'triton' has no attribute 'language'

  #1757 opened 6 months ago by Alonelymess
  3

• Question: from custom segmentation to custom diarization model

  #1748 opened 7 months ago by IzzyHibbert
  4

• After fine-tuning with MagicData-RAMC dataset，i test on Aishell-4 dadaset DER increased.

  #1738 opened 8 months ago by Arnold134777
  2

• Mismatch between DiscreteDiarizationErrorRate and DiarizationErrorRate

  #1733 opened 8 months ago by hhd52859
  3

• 3.3 dependencies

  #1727 opened 9 months ago by faroit
  2

• Wrong usage of meta-protocols subsets in segmentation tasks

  #1709 opened 9 months ago by FrenchKrab
  1

• How to map the transcribed text with their respective speakers in speaker diarization?

  #1718 opened 9 months ago by ThiruRJST
  2

• DER above zero when using Oracle Segmentation & Oracle Clustering

  #1715 opened 10 months ago by mn-j
  2

• Can not reproduce "adapting_pretrained_pipeline.ipynb" on local machine

  #1698 opened 10 months ago by jyhan03
  4