Commit Graph
2442 Commits
Author SHA1 Message Date
Hervé BREDIN 37a4290a0f Update xvector.py 2025-02-04 15:39:09 +01:00
Hervé BREDIN 703f889f50 Merge branch 'develop' into fix/fix-xvector-coreml-export 2025-02-04 15:29:10 +01:00
Ilya Gulya 74705e9a5d doc: add progress hook in README.md example (#1826) 2025-02-04 15:28:21 +01:00
Clément Pagés d6136a8d69 fix(separation): fix division by zero in separation pipeline corner cases (#1815) 2025-02-04 14:17:58 +01:00
Hervé BREDIN 43bb258a5c feat: add CLI to apply (and benchmark) pretrained pipelines 2025-01-27 11:07:13 +01:00
Hervé BREDIN fd91866315 doc: improve HF-related docstring 2025-01-27 10:53:04 +01:00
Hervé BREDIN 9cf27e6d62 feat: add segmentation error rate (#1836) 2025-01-23 14:41:34 +01:00
benniekiss 2dba593bc5 BREAKING: fix cache_dir support, rename use_auth_token to token, and other changes 2025-01-20 22:01:06 +01:00
Hervé BREDIN ea1ad3429b setup: update torch_audiomentations, pyannote.database, pyannote.metrics and typer dependencies 2025-01-15 21:45:45 +01:00
Joonas Kalda c7df18b07e fix: update pipeline parameters in separation tutorial (#1829) 2025-01-15 08:54:19 +01:00
Hervé BREDIN 3c167f201f fix: ensure round number of frames 2025-01-09 17:20:03 +01:00
Hervé BREDIN 0b7f933fd9 feat(metric): add detection, precision, and recall diarization metrics (#1808) 2024-12-13 16:42:49 +01:00
Hervé BREDIN ffc43ee48e fix: fix pipeline loading from disk and subfolders (#1807) 2024-12-09 21:44:55 +01:00
Hervé BREDIN 9b079e8220 feat: add calibration getters (#1803) 2024-11-29 12:33:17 +01:00
Hervé BREDIN c5102f8e66 doc: fix typo in FAQ 2024-11-29 10:19:17 +01:00
Hervé BREDIN c469910575 doc: fix typo in FAQ 2024-11-29 10:18:52 +01:00
Hervé BREDIN 9be9066446 doc: update FAQ to link to better pyannoteAI models 2024-11-29 10:18:27 +01:00
Hervé BREDIN f935d7e894 doc: update streaming FAQ with link to diart 2024-11-29 10:15:34 +01:00
Razi Taj Mazinani 3e39edd58f fix(doc): fix default embedding in SpeechSeparation and SpeakerDiarization docstring 2024-11-28 22:20:03 +01:00
Hervé BREDIN b86d3809fa feat: add new Calibration core object (#1799) 2024-11-28 22:16:31 +01:00
Clément Pagés 9a2368bf67 fix(separation): fix WavLM (un)freezing support in ToTaToNet/SSeRiouSS training 2024-11-26 23:24:36 +01:00
Clément Pagés d043a060b2 fix(separation): prevent leakage removal collar from being applied to diarization 2024-11-26 23:14:25 +01:00
Hervé BREDIN 4254401c5a feat: add support for models stored in pipeline subfolders (#1794) 2024-11-26 13:50:41 +01:00
antoinelaurent 385eba615b fix(task): fix corner case with small (<9) number of validation samples 2024-11-21 12:50:16 +01:00
Clément Pagés 7d84f61061 fix(separation): fix #1735 and #1747 2024-11-11 20:49:53 +01:00
Emmanuel Ferdman cf3e2b2ad4 fix(doc): fix link to pytorch (#1785) 2024-11-08 13:59:06 +01:00
Hervé BREDIN dda685f6f6 fix(augmentation): fix Mix augmentation import 2024-11-08 11:46:58 +01:00
Hervé BREDIN 540fc65acd fix(model): add missing wav2vec_frozen option 2024-11-08 11:16:09 +01:00
Hervé BREDIN 21addd6eae feat(model): add wav2vec_frozen option to freeze/unfreeze wav2vec in SSeRiouSS architecture (#1784) 2024-11-08 11:13:06 +01:00
Hervé BREDIN 053b3ab3be BREAKING(task): drop support for multilabel training (#1783)
* feat(task): add support for manual optimization
- BREAKING(task): drop support for `multilabel` training in `SpeakerDiarization` task
- BREAKING(task): drop support for `warm_up` option in `SpeakerDiarization` task
- BREAKING(task): drop support for `weigh_by_cardinality` option in `SpeakerDiarization` task
- BREAKING(task): drop support for `vad_loss` option in `SpeakerDiarization` task
2024-11-08 10:52:01 +01:00
Lebourdais 3f4a22f773 fix: fix alignment between diarization and sources 2024-10-23 16:50:30 +02:00
Clément Pagés a39991b92d fix(community): replace cpwer by min_cpwer in cpwer breakdown 2024-10-18 10:44:24 +02:00
Hervé BREDIN 1d3668541e feat: add support for k-means clustering (#1774) 2024-10-17 15:39:57 +02:00
Hervé BREDIN efc8849547 Merge branch 'develop' into fix/fix-xvector-coreml-export 2024-10-08 11:16:27 +02:00
Hervé BREDIN 5ae7a48dd2 feat: add "hidden" option to ProgressHook (#1761) 2024-10-08 11:09:37 +02:00
Hervé BREDIN 583251059d chore: remove unused return (#1759) 2024-10-08 11:04:53 +02:00
Joonas Kalda bd62a890b6 fix: fix clipping issue in speech separation pipeline (#1730)
Fixes #1729
2024-10-08 11:03:02 +02:00
Hervé BREDIN 51c049852e Merge branch 'develop' into fix/fix-xvector-coreml-export 2024-09-26 13:47:08 +02:00
Lakshmi Narayana Reddy B c718d9863e fix: fix tutorial dependency 2024-09-24 20:39:42 +02:00
Clément PagésandHervé BREDIN 061027975f doc: add tutorial evaluating the joint diarization/separation metrics (#1716)
Co-authored-by: Hervé BREDIN <hbredin@users.noreply.github.com>
2024-09-24 13:57:36 +02:00
Hervé BREDIN 0e37afc8c9 Merge tag '3.3.2' into develop
Version 3.3.2
2024-09-11 13:06:44 +02:00
Hervé BREDIN 240a7f3ef6 Merge branch 'release/3.3.2' 3.3.2 2024-09-11 13:06:31 +02:00
Hervé BREDIN faf6126b5d setup: bump version 2024-09-11 13:06:04 +02:00
Hervé BREDIN b393e55272 doc: update changelog 2024-09-11 13:05:50 +02:00
Hervé BREDIN 445a4c69bb fix: fix support for CoreML export 2024-09-11 09:12:44 +02:00
huisman 0ea4c025ee doc: fix Pipeline docstring 2024-08-19 17:17:55 +02:00
Patrice Ferlet 286ea1a4e3 fix: fix support for numpy==2.x 2024-07-01 13:39:57 +02:00
Hervé BREDIN 2e04ec7fb6 Merge tag '3.3.1' into develop
Version 3.3.1
2024-06-19 14:01:50 +02:00
Hervé BREDIN 4dd55a51b2 Merge branch 'release/3.3.1' 3.3.1 2024-06-19 14:01:37 +02:00
Hervé BREDIN 82f345a3df doc: update changelog and bump version 2024-06-19 14:01:24 +02:00