Commit Graph
2381 Commits
Author SHA1 Message Date
Hervé BREDIN aa943213ef feat(model): add option to finetune wav2vec 2024-05-13 14:24:52 +02:00
Hervé BREDIN 8342e44cd8 BREAKING(task): deprecate a bunch of unused options 2024-05-13 13:52:57 +02:00
Hervé BREDIN a73ded27f2 fix(doc): fix title level 2024-05-12 22:09:11 +02:00
Hervé BREDIN ba1c4f5e7c doc: update README.md to reference pyannoteAI 2024-05-10 22:38:11 +02:00
Hervé BREDIN 48b68022f7 Merge tag '3.2.0' into develop
Version 3.2.0
2024-05-08 11:44:42 +02:00
Hervé BREDIN 70a8507878 Merge branch 'release/3.2.0' 3.2.0 2024-05-08 11:42:17 +02:00
Hervé BREDIN bb4dd2eed4 git: update version 2024-05-08 11:40:45 +02:00
Hervé BREDIN e01134dbdd doc: update changelog 2024-05-08 11:40:27 +02:00
Hervé BREDIN 07a85a7c06 doc: update changelog 2024-05-08 11:36:04 +02:00
Hervé BREDIN 461580848a fix(hook): fix torch.Tensor support in ArtifactHook 2024-05-08 11:21:44 +02:00
Hervé BREDIN 7a90137452 feat: add fbank_only property to WeSpeaker models (#1708) 2024-05-08 11:16:19 +02:00
Hervé BREDIN 9a61ec26d9 fix: fix receptive field computation with non-zero padding (#1707) 2024-05-08 10:38:18 +02:00
Hervé BREDIN 5d56a11fd8 chore: remove use of vmap in stats-pooling layer (#1706) 2024-05-07 17:16:14 +02:00
Lukas 4407a66023 doc: fix typo in powerset docstring 2024-05-05 21:12:39 +02:00
Hervé BREDIN 2a7206762f Update README.md 2024-04-24 21:53:36 +02:00
Hervé BREDIN 704f87414a doc: update README 2024-04-22 13:04:10 +02:00
Hervé BREDIN f9009e2ef8 github: update config.yml (#1689) 2024-04-18 17:45:40 +02:00
Simon Ottenhaus 1a397b0153 community: add tutorial for offline use of pyannote/speaker-diarization-3.1 2024-04-05 14:19:53 +02:00
Hervé BREDIN cf876c2f60 doc: update CHANGELOG (#1681) 2024-04-04 17:08:57 +02:00
Hervé BREDIN dc49f37356 improve(io): switch to torchaudio >= 2.2.0 (#1674)
fix: fixes #1576
2024-03-17 07:40:03 +01:00
Hervé BREDIN bad61792a8 doc: update link to premium survey 2024-03-04 10:09:39 +01:00
Clément Pagés 99ed3d6de3 improve(ux): improve error message on missing specifications 2024-02-25 21:00:25 +01:00
Clément Pagés d83c0f8ea9 fix(cli): update CLI with latest APIs 2024-02-25 20:49:08 +01:00
Clément Pagés 5b3ed06129 doc: update tutorials notebooks 2024-02-25 20:37:47 +01:00
FrenchKrab a810a5a53a fix: fix seeding in create_rng_for_worker (#1649) 2024-02-15 08:27:52 +01:00
Hervé BREDIN 6e22f41af9 improve(pipeline): track all Module instances (not just Model's) (#1646) 2024-02-08 16:18:10 +01:00
Hervé BREDIN 8b66bfd7ea fix(util): ensure integer receptive field size (#1645) 2024-02-08 16:17:32 +01:00
FrenchKrab c3cc56cba5 fix(task): fix estimation of training set size (#1644) 2024-02-08 16:16:46 +01:00
Hervé BREDIN e611d1c7ab feat(model): add receptive_field property and num_frames method to every model (#1642) 2024-02-03 19:22:27 +01:00
Hervé BREDIN e4d850c8cf fix: fix computation of conv1d receptive field (#1640) 2024-02-02 16:52:59 +01:00
Hervé BREDIN eba4419c8b improve(metric): add support for number of speakers mismatch in diarization_error_rate metric 2024-02-01 10:46:37 +01:00
Hervé BREDIN fea5c2951e feat(metric): add reduce option to diarization_error_rate metric (#1635) 2024-01-31 21:55:36 +01:00
FrenchKrabandHervé BREDIN d115e9ac94 feat(powerset): add Powerset.permutation_mapping to help with permutation in powerset space
Co-authored-by: Hervé BREDIN <hbredin@users.noreply.github.com>
2024-01-30 11:21:08 +01:00
Clément Pagés 9d22113e69 ci: update ci model used for tests 2024-01-25 17:34:23 +01:00
Hervé BREDIN e43138278a feat: add pyannote.audio.sample.SAMPLE_FILE (#1629) 2024-01-25 10:42:32 +01:00
Hervé BREDIN c0b9e79aa8 BREAKING(model): get rid of Model.example_output in favor of num_frames, receptive_field, and dimension properties (#1617) 2024-01-24 21:47:01 +01:00
FrenchKrab 293d8fc33e improve: add missing Optional typing 2024-01-24 11:26:28 +01:00
Clément Pagés c921f441f6 fix: remove use of unsigned type (#1616) 2024-01-15 16:33:27 +01:00
Clément PagésandHervé BREDIN b41b176e3f fix: fix support for non-ASCII characters
Fixes #1608 #1612 

Co-authored-by: Hervé BREDIN <hbredin@users.noreply.github.com>
2024-01-15 13:11:21 +01:00
Clément PagésandHerve Bredin 9e4ec5f6e0 feat(task): add option to cache training metadata to disk
Co-authored-by: Herve Bredin <hbredin@users.noreply.github.com>
2024-01-12 10:46:46 +01:00
Hervé BREDIN d41ce0a73d doc: fix typo in README 2024-01-11 13:04:18 +01:00
Hervé BREDIN 8f477fada9 fix(task): fix random generators (#1594)
Before this change, each worker would select the same files, resulting in less randomness than expected.
2024-01-09 13:06:09 +01:00
Hervé BREDIN eda0c51b13 Delete .github/ISSUE_TEMPLATE/feature_request.md 2024-01-08 17:05:05 +01:00
Hervé BREDIN eb2e813b36 github: update config.yml (#1607) 2024-01-08 17:04:22 +01:00
Hervé BREDIN 27cd91f87c github: create config.yml 2024-01-08 17:02:40 +01:00
Hervé BREDIN 42ef141298 github: add bug_report.yml template 2024-01-08 16:53:52 +01:00
Hervé BREDIN 808b170bd6 feat: add MRE template 2024-01-08 16:36:24 +01:00
Hervé BREDIN e21e7bb35f ci: deactivate FAQtory 2024-01-08 09:52:19 +01:00
Clément Pagésandclement-pages 80634c9029 fix: update isort version to 5.12.0 in pre-commit-config (#1596)
Co-authored-by: clement-pages <clement.pages@irit.fr>
2023-12-22 09:16:12 +01:00
Hervé BREDIN 7bd88d5f13 feat(pipeline): add Waveform and SampleRate preprocessors (#1593) 2023-12-20 21:26:42 +01:00