Commit Graph

2899 Commits

Author SHA1 Message Date
Eren Gölge d0ab0382fc linter fixes 2021-06-01 09:15:32 +02:00
Eren Gölge 406c4d0577 bump pylint version to 2.8.3 2021-06-01 09:15:15 +02:00
Eren Gölge 4726ae393d pylint disable `not-callable` checks due to the warnings on torch layers 2021-06-01 09:14:16 +02:00
Eren Gölge bec85ac58d make style 2021-05-31 16:37:15 +02:00
Eren Gölge 975531b3f2 update `pylintrc` for torch and numpy functions 2021-05-31 16:11:22 +02:00
Eren Gölge d9f1268f99 init tb_logger None for rank > 0 processes 2021-05-31 15:47:07 +02:00
Eren Gölge 301c516abd Merge branch 'dev' of https://github.com/coqui-ai/TTS into dev 2021-05-31 15:46:25 +02:00
Eren Gölge 92e26b4216
Merge pull request #508 from Edresson/dev
Implement/Train a better speaker encoder
2021-05-31 11:45:36 +02:00
Edresson cc192b6843 add resnet speaker encoder train unit test 2021-05-29 22:43:41 -03:00
Edresson 7448177b72 use SpeakerManager on compute embeddings script 2021-05-29 21:11:53 -03:00
Edresson 099142d4dd bug fix 2021-05-27 21:50:56 -03:00
Edresson 208bb0f0ee add batched speaker encoder inference 2021-05-27 20:01:00 -03:00
Edresson 825734a3a9 remove unused embeddings export 2021-05-27 19:10:24 -03:00
Eren Gölge 925c08cf95 replace unidecode with anyascii 2021-05-27 14:02:44 +02:00
Eren Gölge e08c58db3b bump up version to v0.14.1 2021-05-27 13:11:01 +02:00
Eren Gölge c6f22aaa67 fix #509 2021-05-27 13:09:15 +02:00
Edresson 1496f271dc update Compute embeddings script 2021-05-27 00:45:18 -03:00
Edresson 5af505ff33 remove unused notebooks 2021-05-26 21:43:51 -03:00
Edresson bc5307caa0 add unit tests for SoftmaxAngleProtoLoss and ResnetSpeakerEncoder and bugfix 2021-05-26 20:35:58 -03:00
Edresson 7a9a27282a fix unit tests 2021-05-26 18:14:06 -03:00
Edresson c90037c2e9 solve merge problems 2021-05-26 16:01:30 -03:00
Edresson Casanova f89cb6aec2
Merge branch 'dev' into dev 2021-05-25 17:30:25 -03:00
Edresson d570c2d790 pylint fix and data loader bug fix 2021-05-26 01:11:37 -03:00
Eren Gölge 5482a0f62d type def for gradual_training 2021-05-19 14:03:26 +02:00
Eren Gölge df6a98d0c3 type def for gradual_training 2021-05-19 14:00:44 +02:00
Eren Gölge 1ca10c3232
Merge pull request #487 from coqui-ai/dev
v0.0.14
2021-05-19 12:53:08 +02:00
Eren Gölge 16576d6408 bump version number 2021-05-19 12:35:10 +02:00
Eren Gölge e6985a5bbc Merge branch 'coqpit-refactor' into dev 2021-05-19 11:34:04 +02:00
Eren Gölge f5a9950a2e phoneme files for testing 2021-05-19 03:16:57 +02:00
Eren Gölge 9b706c5583 enable phonemes in test to match the attention masks 2021-05-19 03:15:54 +02:00
Eren Gölge 8a7c40736c set use_phonemes false 2021-05-19 01:27:26 +02:00
Eren Gölge faedea4b60 set use_phonemes False in configs 2021-05-19 00:08:07 +02:00
Eren Gölge ccfaa6b1d5 add `needs_phonemizer` field to models.json. If set true these models
are only compatible with v0.0.13 or below.
2021-05-18 17:57:28 +02:00
Eren Gölge a14fcf2a13 remove text_processing test 2021-05-18 17:57:28 +02:00
Eren Gölge d7fae3f515 remove all espeaker and phonemizer deps 2021-05-18 17:57:28 +02:00
Eren Gölge ced05e812a move chinese phonemizer 2021-05-18 17:57:28 +02:00
Eren Gölge 218af1d9a2 change `list` to `List` in config 2021-05-18 17:30:27 +02:00
Eren Gölge 8142291b36 change `list` to `List` in config 2021-05-18 16:09:32 +02:00
Eren Gölge 4df31f7fbd unused_speakers argument for ignoring speaker ids in multi-speaker
training
2021-05-18 14:50:03 +02:00
Eren Gölge c2c7dff805 use relaxted coqpit parser 2021-05-18 14:49:47 +02:00
Edresson 856ea19758 bug fix in dataloader and update inference 2021-05-18 03:43:16 -03:00
Eren Gölge d1b469935d tacotron DDC LJSpeech recipe 2021-05-17 11:42:14 +02:00
Eren Gölge 34a42d379f update tacotron_config.py for checking `r` and the docstring 2021-05-17 11:35:30 +02:00
Eren Gölge 12722501bb styling 2021-05-15 23:48:31 +02:00
Eren Gölge 8b1014d188 add docstrings with default value fixes 2021-05-15 23:45:10 +02:00
Eren Gölge 7e02cff924 reduce pwgan test batch size 2021-05-12 16:10:08 +02:00
Eren Gölge da49089a72 update melgan training test batch size 2021-05-12 10:12:11 +02:00
Edresson 3433c2f348 add compute embedding for the new speaker encoder 2021-05-12 03:06:46 -03:00
Eren Gölge 0213e1cbf4 update configs for tts models to match the field typed with the expected
values
2021-05-12 00:57:38 +02:00
Eren Gölge 8058aaa304 pin numba==0.52 2021-05-12 00:57:38 +02:00