Commit Graph
94 Commits
Author SHA1 Message Date
Hervé BREDIN 9faa8fc8a8 setup: update most dependencies (#1323)
- setup: switch to torch 2.0+ and lightning 2.0+
- setup: switch to torchaudio 2.0+ and soundfile 0.12+
- setup: switch to pyannote.core 5.0+ and pyannote.database 5.0+
- setup: switch to speechbrain 0.5.14+

- BREAKING(task): rename `Segmentation` task to `SpeakerDiarization`
- BREAKING(task): remove support for variable chunk duration

- BREAKING(pipeline): remove `SpeakerSegmentation` pipeline (in favor of `SpeakerDiarization` pipeline)
- BREAKING(pipeline): remove support `FINCHClustering` and `HiddenMarkovModelClustering`

- BREAKING: drop support for Python 3.7
2023-04-17 15:32:37 +02:00
Hervé BREDIN 39a261a0eb feat: add FAQ based on faqtory (#1283) 2023-03-16 15:04:26 +01:00
Hervé BREDIN 840562795e doc: add "How I reached..." blog post 2022-12-02 15:14:08 +01:00
Hervé BREDIN e469e066b7 doc: add link to adaptation tutorial 2022-12-02 14:58:52 +01:00
Hervé BREDIN a1e99ee550 doc: describe offline use (#1169)
* related bugs: #1119 #1128 #1130
* related discussions: #1123 #1103 #1126 #1121
2022-11-29 18:14:49 +01:00
Rhenan 8b5ed07299 doc: add hf.co/pyannote/segmentation to readme (#1127) 2022-10-29 07:54:53 +02:00
Hervé BREDIN d992509ff8 Update README.md 2022-10-27 22:04:37 +02:00
Hervé BREDIN 82a07add2e git: update version number 2022-10-27 22:01:38 +02:00
Hervé BREDIN b7343ccc04 doc: update README 2022-10-27 21:52:32 +02:00
Hervé BREDIN cca33169bb doc: update changelog 2022-10-27 21:52:19 +02:00
Hervé BREDIN f700d6ea8d feat: add support for private and gated hf.co models (#1064) 2022-10-27 21:21:17 +02:00
Hervé BREDIN 3147e2bfe9 Update README.md 2022-07-21 20:50:01 +02:00
Hervé BREDIN 776b2ea9e2 Update README.md 2022-07-21 20:49:26 +02:00
Hervé BREDIN b0b39073db doc: update changelog and version 2022-07-20 13:47:40 +02:00
Hervé BREDIN 07bc89300c fix: get ready for the Grand release 2022-07-20 13:34:47 +02:00
Amit Kesari 0c55421639 fix: fix broken HF link 2022-07-20 13:08:42 +02:00
Hervé BREDIN 1dc8520fed feat: switch to better and faster speaker diarization pipeline (#993) 2022-07-20 12:06:07 +02:00
Hervé BREDIN 7b8560527f doc: update README 2022-07-15 18:17:19 +02:00
Hervé BREDIN 099cb324cf doc: add citation section
Fixes #1037
2022-07-15 16:02:24 +02:00
Micah Engle-Eshleman 24a03b4be8 doc: recommend PyTorch 1.11 for SpeechBrain compatibility (#1030)
The latest version of PyTorch (1.12) is incompatible with SpeechBrain (used for diarization pipeline)

Fixes #855
2022-07-15 08:41:20 +02:00
Hervé Bredin b6ceec568a Merge branch 'develop' of github.com:pyannote/pyannote-audio into develop 2022-02-18 09:48:46 +01:00
Hervé Bredin d1555e4500 doc: add FAQ section 2022-02-18 09:48:34 +01:00
Hervé BREDIN ac72a05544 doc: mention Prodigy recipe 2022-02-18 09:16:51 +01:00
Hervé BREDINandJ-Petiot 538b00476f feat: add pyannote.audio Prodigy recipe (#896)
Co-authored-by: J-Petiot <jpetiot@sylvebarbe.localdomain>
2022-02-17 16:45:16 +01:00
Hervé BREDIN 6845ace2da Update README.md 2022-02-11 16:14:53 +01:00
Hervé BREDIN 065c6ff22e feat: add pyannote-audio-train CLI (#881)
feat: add pyannote.audio.utils.preprocessors utility module
BREAKING: update PyanNet.sincnet.stride default value to 10
BREAKING: rename Segmentation Hydra config to SpeakerSegmentation
2022-02-11 16:13:52 +01:00
Hervé Bredin 6ad4ba877d doc: update README 2022-02-08 21:31:24 +01:00
Hervé BREDIN 5ded480ba1 feat: add NearestClusterAssignment utility class (#867) 2022-01-28 12:32:56 +01:00
Hervé BREDIN b5794f46d1 feat: add initial documentation (#841) 2022-01-08 22:20:41 +01:00
Hervé BREDIN 2e83450678 feat: add fine-tuning tutorial (#631) 2021-12-15 13:36:56 +01:00
Hervé BREDIN 0621f25559 feat: add offline speaker diarization pipeline (#666)
* BREAKING: repurpose "mode" option to use zero-padding in Audio.crop with out-of-bounds segments
* BREAKING: rename "fixed" option to "duration" in Audio.crop
* BREAKING: remove Segmentation pipeline
* BREAKING: rename returns_cost to return_cost in permutate
* feat: add Inference.{trim | aggregate | stitch} methods
* feat: add pyannote.audio.pipelines.clustering module
* feat: add wrapper for Speechbrain speaker embedding
* feat: add "binarize" utility function
* doc: add documentation for high-level API
* setup: switch to pyannote.core 4.3
2021-12-07 15:43:02 +01:00
Hervé BREDIN 1c6fd10710 Update README.md 2021-09-06 15:43:10 +02:00
Hervé BREDIN d8112ea849 fix: fix demo link 2021-08-09 09:20:52 +02:00
Hervé BREDIN b2cea93fc7 fix: fix link to demo 2021-07-16 10:43:48 +02:00
Hervé BREDIN 03484f0dd7 doc: link to pyannote's AMI diarization setup fork 2021-06-17 14:12:57 +02:00
Hervé BREDIN b810445728 doc: link to pyannote models 2021-06-17 14:11:08 +02:00
Hervé BREDIN 7f90409756 fix: update installation instructions and requirements (#653) 2021-04-07 14:43:46 +02:00
Hervé BREDIN ed684943fe feat: make finetuning (or transfer learning) of pretrained models easier and more reliable (#606)
- feat: track task-dependent layers (i.e. layers that are completely reset when switching task)
- feat: add finetuning / transfer learning callback and use it in CLI
- fix: remove (broken) support for setting `Model.{optimizer, scheduler}` attributes
- doc: update README and CLI to reflect the above fix
2021-02-03 21:33:09 +01:00
Hervé BREDIN 54868ff99b feat: allow customization of optimizer and scheduler (#598) 2021-01-28 12:13:58 +01:00
Hervé BREDIN 0b9be93ee1 chore: replace load_from_checkpoint by Model.from_pretrained (#588)
* chore: import Model from package root
* chore: import Inference from package root
2021-01-20 16:39:08 +01:00
Hervé Bredin 54ddc0b076 doc: mention streamlit demo in README 2021-01-15 13:24:35 +01:00
Hervé Bredin 8696421140 doc: update README with 2.0 highlights 2021-01-15 13:19:10 +01:00
Hervé BREDIN 10f8932e89 doc: update installation instructions 2021-01-14 17:01:29 +01:00
Hervé BREDIN 8a86468d44 chore: simplify the API even more 2021-01-14 14:33:17 +01:00
Hervé BREDIN 06d3b6116c feat: add Hydra-based "pyannote-audio-train" CLI
* closes #476 (CLI)
* closes #514 (support for AutoLR)
* closes #485 (hyper-parameter optimization with Hydra’s Ax sweeper)
* closes #412 (log graph to Tensorboard)
2020-11-18 10:59:39 +01:00
Harry Coultas Blum ea1d1c55ea improve: make task dataloaders reproducible 2020-11-08 22:43:13 +01:00
Hervé BREDIN ad69a34cad fix: fix installation instruction 2020-11-08 22:43:13 +01:00
Hervé BREDIN caad9666f3 doc: update README 2020-11-08 22:43:12 +01:00
Harry ede954b7a0 Added readme instructions 2020-11-08 22:43:12 +01:00
Hervé BREDIN ba0835f44e Initial commit 2020-11-08 22:40:46 +01:00