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

6.38k stars 784 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

Replace np.NaN (deprecated in NumPy 2.0.0) with np.nan

#1725 ibevers closed 5 months ago
4
`torchaudio.info.num_frames` can give wrong results so it can provide false exceptions

#1724 grazder opened 5 months ago
2
Passthrough Pipeline cache_dir param to underlying pipelines and get_model()

#1722 benniekiss opened 5 months ago
0
[WIP] improve Binarize() performance

#1721 benniekiss opened 5 months ago
1
Add a warning when task parameters differ from those of the cache in use

#1719 clement-pages opened 5 months ago
0
How to map the transcribed text with their respective speakers in speaker diarization?

#1718 ThiruRJST closed 5 months ago
2
Fix validation preparation issue when a protocol does not define a development set

#1717 clement-pages closed 6 months ago
0
doc: add tutorial evaluating the joint diarization/separation metrics

#1716 clement-pages closed 2 months ago
2
DER above zero when using Oracle Segmentation & Oracle Clustering

#1715 mn-j closed 6 months ago
2
memory optimizations for pyannote.audio.core.inference.Inference.aggregate()

#1713 benniekiss closed 5 months ago
5
Speakers with similar pitch are difficult to distinguish

#1712 ChristianNSchmitz opened 6 months ago
3
improve(io): use (faster) soundfile backend when available

#1711 hbredin closed 6 months ago
0
fix: fix #1709

#1710 hbredin closed 6 months ago
2
Wrong usage of meta-protocols subsets in segmentation tasks

#1709 FrenchKrab closed 5 months ago
1
feat: add `fbank_only` property to `WeSpeaker` models

#1708 hbredin closed 6 months ago
0
fix: fix receptive field computation with non-zero padding

#1707 hbredin closed 6 months ago
0
chore: remove use of vmap and rearrange in stats-pooling layer

#1706 hbredin closed 6 months ago
0
doc: fix typo in powerset docstring

#1705 lukasstorck closed 6 months ago
1
Why is pyannote not using my GPU ro CPU? So slow too.

#1702 CrackerHax opened 6 months ago
5
What is the purpose of the Resegmentation and AdaptiveVoiceActivityDetection Pipeline?

#1700 asusdisciple opened 6 months ago
2
Add Push to Hub functionnality to Model and Pipeline

#1699 kamilakesbi opened 6 months ago
4
Can not reproduce "adapting_pretrained_pipeline.ipynb" on local machine

#1698 jyhan03 closed 7 months ago
4
Feat/add wavlm based embeddings model

#1696 clement-pages opened 7 months ago
2
Cannot instantiate parameters on finetuned model

#1694 Ashh-Z opened 7 months ago
5
Update speaker_verification.py for better use of the onnxruntime

#1693 CaioMizerkowski opened 7 months ago
1
Audio input as tensor or BytesIO is unexpectedly slow

#1692 Purfview closed 7 months ago
1
fix(doc): remove mention of unsupported `numpy.ndarray` waveform

#1691 Purfview closed 6 months ago
1
numpy.ndarray audio input doesn't work?

#1690 Purfview closed 5 months ago
3
Update config.yml

#1689 hbredin closed 7 months ago
0
Embeddings takes 3x the length of the audio length

#1687 cdreetz opened 7 months ago
8
improve(pipeline): do not extract embeddings in `SpeakerDiarization` pipeline when `max_speakers` is 1

#1686 hbredin closed 6 months ago
0
Speaker Diarization pipeline.get_segmentations produces integer ascending start/ends instead of something useful

#1685 bschreck closed 2 weeks ago
2
Speaker Diarizations get_segmentations() raises for several input type variants

#1684 bschreck closed 2 weeks ago
1
fix(setup): fix typer version

#1683 hbredin closed 7 months ago
0
Doc: Add tutorial notebook for offline usage of `speaker-diarization-3.1`

#1682 simonottenhauskenbun closed 7 months ago
2
doc: update CHANGELOG

#1681 hbredin closed 7 months ago
0
Error occurs following training tutorial

#1678 LVCSRer closed 7 months ago
1
'speechbrain' must be installed to use 'speechbrain/spkrec-ecapa-voxceleb' embeddings.

#1677 ijean closed 5 months ago
3
feat(separation): add PixIT task, ToTaToNet model and SpeechSeparation pipeline

#1676 joonaskalda closed 5 months ago
1
pyannote uninstalling torch cuda and install torch cpu

#1675 versus666jzx opened 8 months ago
8
improve(io): switch to torchaudio >= 2.2.0

#1674 hbredin closed 8 months ago
0
RuntimeError with Mixed CUDA Devices for Multi-GPU Training

#1673 ShiyangLai closed 2 weeks ago
2
OSError: automatic-speech-recognition is not a local folder and is not a valid model identifier listed on 'https://huggingface.co/models'

#1671 alvynabranches closed 8 months ago
1
AttributeError: 'Annotation' object has no attribute 'for_json'

#1668 alvynabranches closed 8 months ago
3
Training PyanNet/SSeRiouSS on multiple GPUs not working

#1666 Jamiroquai88 closed 8 months ago
4
Doc: Add tutorial notebook for offline usage of `speaker-diarization-3.1`

#1662 simonottenhauskenbun closed 7 months ago
5
ImportError: 'speechbrain' must be installed to use 'speechbrain/spkrec-ecapa-voxceleb' embeddings. Visit https://speechbrain.github.io for installation instructions.

#1661 YugwonWon closed 8 months ago
7
Running `speaker-diarization-3.1` with local ` wespeaker-voxceleb-resnet34-LM` needs special naming to circumvent ONNX/protobuf loading errors

#1660 simonottenhauskenbun closed 7 months ago
5
Update Pyannote with SpeechBrain 1.0

#1659 Adel-Moumen closed 5 months ago
12
Additional features in pyannote/torchmetrics

#1658 Bilal-Rahou closed 7 months ago
1

Previous Next