100 Commits
Author SHA1 Message Date
Hervé Bredin b3768175b5 fix: fix "embedding_batch_size" docstring 2022-02-21 13:34:37 +01:00
Hervé Bredin bc12b83df2 doc: preparing changelog 2022-02-18 11:22:52 +01:00
Hervé Bredin a351c096a2 github: remove test-v2 action 2022-02-18 11:19:13 +01:00
Hervé Bredin 413d6a48cc Merge branch 'master' into develop 2022-02-18 11:17:33 +01:00
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 a654bee4d5 fix: log pretrained model validation before fine-tuning
fixes #744
2022-02-17 17:04:34 +01:00
Hervé Bredin cb053f50a7 fix: fix LowerTemporalResolution preprocessor 2022-02-14 15:17:10 +01:00
Hervé Bredin 6ad4ba877d doc: update README 2022-02-08 21:31:24 +01:00
Hervé Bredin 5cbb572cad fix: fix support for Python 3.7 2022-02-08 16:59:59 +01:00
Hervé Bredin da4f978a42 chore: remove use of (3.8+) {variable=} syntax 2022-02-08 10:32:46 +01:00
Hervé Bredin a731a31366 fix: fix progress hook internal counter 2022-01-31 16:42:38 +01:00
Hervé Bredin d2cc015a01 feat: add build_permutation_graph utility function 2022-01-31 13:32:44 +01:00
Hervé Bredin fd0c42c77a fix: fix computation of same_chunk matrix 2022-01-28 14:08:17 +01:00
Hervé Bredin fc81b001dd fix: increase support to avoid rounding errors 2022-01-28 14:07:55 +01:00
Hervé Bredin 11f1344cc6 chore: update hook names in SpeakerSegmentation pipeline 2022-01-26 14:27:34 +01:00
Hervé Bredin 0b79366013 fix: fix SpeakerSegmentation.default_parameters 2022-01-26 14:20:20 +01:00
Hervé Bredin b29ef09256 feat: add default SpeakerDiarizationMixin.classes() method 2022-01-20 13:54:37 +01:00
Hervé Bredin f15c651f1d chore: split to_diarization into two parts 2022-01-19 15:53:57 +01:00
Hervé Bredin 97b89cb54d feat: add SlidingDiarizationErrorRate utility metric 2022-01-19 15:51:19 +01:00
Hervé Bredin 156fe04bb9 doc: improve Inference.stitch docstring 2022-01-19 15:50:11 +01:00
Hervé Bredin 0a368c6bcb setup: switch to pyannote.metrics 3.2 2022-01-12 16:07:10 +01:00
Hervé Bredin 70dbf764a0 doc: update VAD tutorial 2021-12-16 15:06:42 +01:00
Hervé Bredin 0102657513 fix: clarify the need for speechbrain 2021-12-16 09:46:06 +01:00
Hervé Bredin 4e558df3ee fix: fix Audio.crop with negative start time and mode="pad" 2021-12-14 17:03:21 +01:00
Hervé Bredin 39e78dac2f Merge branch 'develop' of https://github.com/pyannote/pyannote-audio into develop 2021-12-03 14:18:02 +01:00
Hervé Bredin 5058225fbc Merge branch 'develop' of https://github.com/pyannote/pyannote-audio into develop 2021-09-21 12:04:20 +02:00
Hervé Bredin 995ddee906 fix: fix estimation of number of batches per epoch 2021-09-21 12:02:38 +02:00
Hervé Bredin 88ff6e1349 Merge branch 'develop' of https://github.com/pyannote/pyannote-audio into develop 2021-09-20 10:17:56 +02:00
Hervé Bredin 6697fc8118 Merge branch 'develop' of https://github.com/pyannote/pyannote-audio into develop 2021-09-13 15:17:42 +02:00
Hervé Bredin 8424f59edd fix: switch to triangular 2021-09-13 15:17:24 +02:00
Hervé Bredin 9f3db894f7 Merge branch 'develop' of https://github.com/pyannote/pyannote-audio into develop 2021-09-11 11:22:25 +02:00
Hervé Bredin 7ba433a861 fix: switch to triangular 2021-09-11 11:21:40 +02:00
Hervé Bredin c492e10263 Merge branch 'develop' of https://github.com/pyannote/pyannote-audio into develop 2021-09-10 16:07:12 +02:00
Hervé Bredin 23c4eaaed5 Merge branch 'develop' of https://github.com/pyannote/pyannote-audio into develop 2021-09-08 16:06:12 +02:00
Hervé Bredin 39633d9d3a fix: remove augmentation tests 2021-09-08 14:34:31 +02:00
Hervé Bredin a188f1d305 Merge branch 'develop' of https://github.com/pyannote/pyannote-audio into develop 2021-08-04 14:37:47 +02:00
Hervé Bredin 436216c26d Merge branch 'develop' of https://github.com/pyannote/pyannote-audio into develop 2021-06-22 14:42:14 +02:00
Hervé Bredin 246318153d Merge branch 'develop' of https://github.com/pyannote/pyannote-audio into develop 2021-06-08 21:07:06 +02:00
Hervé Bredin 062bd7bd9a git: add AMI-diarization-setup submodule 2021-04-27 13:44:58 +02:00
Hervé Bredin de97df6990 Merge branch 'develop' of https://github.com/pyannote/pyannote-audio into develop 2021-04-13 15:40:13 +02:00
Hervé Bredin 18ed481c7e doc: fix error message 2021-04-07 11:58:47 +02:00
Hervé Bredin f7047bae78 Merge branch 'develop' of https://github.com/pyannote/pyannote-audio into develop 2021-03-29 22:24:32 +02:00
Hervé Bredin b4fee9856f fix: add missing "uri" attribute 2021-03-29 22:23:08 +02:00
Hervé Bredin 041231fca9 Merge branch 'develop' of https://github.com/pyannote/pyannote-audio into develop 2021-03-24 10:35:52 +01:00
Hervé Bredin 25d34e3088 Merge branch 'develop' of https://github.com/pyannote/pyannote-audio into develop 2021-03-19 10:38:20 +01:00
Hervé Bredin 3069c52fbe Merge branch 'develop' of https://github.com/pyannote/pyannote-audio into develop 2021-03-18 16:23:41 +01:00
Hervé Bredin 482b43da63 git: merge 2021-03-10 16:48:28 +01:00
Hervé Bredin 11f146d069 fix: fix bug introduced by PR #632 2021-03-10 16:34:59 +01:00
Hervé BREDIN daa35e9b72 fix: fix support for previewing chunks not starting at t=0. 2021-02-19 08:44:49 +01:00
Hervé Bredin 74f1349a8c fix: fix validation bug 2021-02-18 18:02:48 +01:00
Hervé BREDIN 79804315a0 fix: move layers added by build() to same device as the rest of the model 2021-02-17 10:49:27 +01:00
Hervé Bredin 2d06c1a0e1 chore: silence "interpolate" warning 2021-02-16 21:47:57 +01:00
Hervé Bredin 1919f15748 feat: add returns_cost option to permutate 2021-02-12 16:18:23 +01:00
Hervé Bredin 9c3fec0152 improve: use "linear" interpolation instead of "nearest" 2021-02-09 13:18:16 +01:00
Hervé Bredin 87fef20187 feat(cli): make patience configurable 2021-02-04 15:42:01 +01:00
Hervé Bredin 40fb905da8 doc: improve various comments 2021-02-03 22:05:51 +01:00
Hervé Bredin 727ff00dc5 fix(cli): fix model=pretrained config 2021-01-28 14:47:25 +01:00
Hervé Bredin d466c03542 fix: capitalize Adam 2021-01-28 14:40:29 +01:00
Hervé Bredin 7675d4fa35 doc: update changelog 2021-01-28 11:10:12 +01:00
Hervé Bredin d1a20eb814 fix: switch back to (4x faster) soundfile 2021-01-18 21:44:32 +01:00
Hervé Bredin 54ddc0b076 doc: mention streamlit demo in README 2021-01-15 13:24:35 +01:00
Hervé Bredin 7cbaa6cdbb Merge branch 'develop' of github.com:pyannote/pyannote-audio into develop 2021-01-15 13:19:47 +01:00
Hervé Bredin 8696421140 doc: update README with 2.0 highlights 2021-01-15 13:19:10 +01:00
Hervé Bredin 4860be9700 fix: convert y to float before NaNing it 2021-01-08 12:03:24 +01:00
Hervé Bredin c22b94ad9a fix: move tensors to CPU before visualizing them 2021-01-08 11:59:44 +01:00
Hervé Bredin fcd5635eb4 Merge branch 'develop' of github.com:pyannote/pyannote-audio into develop 2021-01-08 11:48:45 +01:00
Hervé Bredin b2a1621a89 fix: move metric to correct device 2021-01-08 11:48:24 +01:00
Hervé Bredin ce59ff27e8 git: add back check-added-large-files pre-commit check 2020-11-09 12:53:27 +01:00
Hervé Bredin 51cb44d04a fix: add test data 2020-11-09 12:52:44 +01:00
Hervé Bredin c2c9618f61 git: merge 2020-11-08 22:46:56 +01:00
Hervé Bredin 4097af53d4 feat: initial import 2020-11-08 22:42:37 +01:00
Hervé Bredin 7960dd01ce Merge tag '1.1' into develop
Version 1.1
2020-11-08 21:19:47 +01:00
Hervé Bredin ffe9b0b5d3 Merge branch 'release/1.1' 2020-11-08 21:19:38 +01:00
Hervé Bredin 547f062d54 doc: update changelog and installation instruction 2020-11-08 21:19:25 +01:00
Hervé Bredin 15f05f7099 Merge branch 'v2' of github.com:pyannote/pyannote-audio into v2 2020-11-08 17:40:09 +01:00
Hervé Bredin ba04e96070 feat: initial import 2020-10-12 16:20:50 +02:00
Hervé Bredin b8d623596e fix: add support for when "annotation" key exists but is None 2020-10-02 12:23:40 +02:00
Hervé Bredin 80b002a664 fix: take subset value into account 2020-06-09 16:34:37 +02:00
Hervé Bredin f159288c72 Merge branch 'develop' of github.com:pyannote/pyannote-audio into develop 2020-06-09 14:52:12 +02:00
Hervé Bredin 2d830b6b33 git: ignore .vscode 2020-06-09 14:49:04 +02:00
Hervé Bredin 3900f749dd git: ignore .mypy_cache 2020-06-09 14:48:36 +02:00
Hervé Bredin dc65dee596 setup: remove typing_extensions for Python 3.8+ 2020-06-09 14:47:49 +02:00
Hervé Bredin f886996cc2 fix: fixes #381 2020-05-20 09:17:58 +02:00
Hervé Bredin 93328fe35d fix: make Wrapper pickable 2020-05-15 11:41:41 +02:00
Hervé Bredin 48ccb41752 test: pin flake8 version 2020-05-14 17:49:47 +02:00
Hervé Bredin 94dbd602d1 test: add sad_mfcc CLI test 2020-05-14 17:33:28 +02:00
Hervé Bredin c0125c7c06 Merge branch 'develop' of github.com:pyannote/pyannote-audio into develop 2020-05-02 14:12:34 +02:00
Hervé Bredin 071b70ff5b doc: stop promising things :) 2020-05-02 14:12:29 +02:00
Hervé Bredin 2f0e902ace chore: return half of previous AutoLR result 2020-04-15 11:43:28 +02:00
Hervé Bredin cdd430e84f fix: add missing norm1ds 2020-04-09 09:44:43 +02:00
Hervé Bredin 412bc29def feat: add support for instance normalization 2020-04-09 09:36:19 +02:00
Hervé Bredin 633b30907d feat: add support for partial checkpoint loading 2020-04-08 17:02:10 +02:00
Hervé Bredin 671386ea12 feat: add optional scaling to ACRoPoLiS model 2020-04-08 17:01:34 +02:00
Hervé Bredin 7db8721ee9 feat: add more CLI tests 2020-04-08 13:42:05 +02:00
Hervé Bredin 4f1bac0d45 doc: add typing to Model.foward 2020-04-08 10:17:28 +02:00
Hervé Bredin cd8ab0558f test: add dummy test 2020-04-03 22:38:36 +02:00
Hervé Bredin 87f4a726ab chore: remove scripts/ directory 2020-04-03 22:36:21 +02:00
Hervé Bredin a073aff5b4 fix: fix flake8 2020-04-03 22:31:50 +02:00
Hervé Bredin 02c6038370 setup: switch to pyannote.pipeline 1.5 2020-04-03 14:22:56 +02:00