Commit Graph

  • 09eda31a3f Fix tests WeberJulian 2021-11-23 16:00:38 +01:00
  • 78a23e19df Fix pylint checks Edresson 2021-11-23 11:43:08 -03:00
  • 4cd0e4eb0d Remove self.audio_config from VITS WeberJulian 2021-11-23 15:40:03 +01:00
  • d39200e69b Remove torchaudio requeriment Edresson 2021-11-23 11:24:36 -03:00
  • 2e516869a1 Fix trailing whitespace WeberJulian 2021-11-23 15:24:03 +01:00
  • ffc269eaf4 Update docstring WeberJulian 2021-11-23 14:50:19 +01:00
  • 06d89f93a8 Add VITS multilingual d-vectors unit test Edresson 2021-11-22 20:19:37 -03:00
  • 12968532fe Add the language embedding dim in the duration predictor class Edresson 2021-11-22 20:02:05 -03:00
  • 4196a42de7 Get the number speaker from the Speaker Manager property Edresson 2021-11-22 18:52:59 -03:00
  • f394d60695 Fix the bug in multispeaker vits Edresson 2021-11-22 18:43:56 -03:00
  • 90eac13bb2 Rename ununsed_speakers to ignored_speakers Edresson 2021-11-22 18:42:54 -03:00
  • 9ca3af900f remove inference notebook WeberJulian 2021-11-22 22:42:12 +01:00
  • f34596d957 Fix function name Edresson 2021-11-22 16:41:46 -03:00
  • 45d0b04179 Lint fixs Edresson 2021-11-22 15:55:00 -03:00
  • 85418ffeaa Fix the bug in extract tts spectrograms Edresson 2021-11-22 13:43:44 -03:00
  • 2b2cecaea2 Set the new_fields in copy_model_files as None by default Edresson 2021-11-22 09:25:32 -03:00
  • 34749f8727 Remove the call to get_speaker_manager Edresson 2021-11-22 09:18:29 -03:00
  • b769b49e34 Remove the data from the set_d_vectors_from_file function Edresson 2021-11-22 09:05:28 -03:00
  • 9daa33d1fd Remove unusable speaker manager function Edresson 2021-11-22 08:57:13 -03:00
  • 8c22d5ac49 Turn more clear the VITS loss function Edresson 2021-11-22 08:48:56 -03:00
  • 6fc3b9e679 Remove the unusable fine-tuning model Edresson 2021-11-22 08:19:36 -03:00
  • 352aa69eca Create a module for the VAD script Edresson 2021-11-21 12:20:35 -03:00
  • 631addf33b fix d-vector WeberJulian 2021-11-18 00:17:42 +01:00
  • da6c1e858c Fix small issues WeberJulian 2021-11-15 22:09:59 +01:00
  • e8af6a9f08 Fix use_speaker_embedding logic WeberJulian 2021-11-09 12:20:43 +01:00
  • 23d789c072 Fix continue path WeberJulian 2021-11-09 12:20:11 +01:00
  • 120332d53f Fix phonemes WeberJulian 2021-11-06 00:27:58 +01:00
  • 846bf16f02 fix imports for load_meta_data WeberJulian 2021-11-04 16:36:40 +01:00
  • 1340938159 fix phonemes per language WeberJulian 2021-11-04 16:36:11 +01:00
  • e995a63bd6 fix linter WeberJulian 2021-11-02 19:10:18 +01:00
  • 1472b6df49 make style WeberJulian 2021-11-02 17:31:14 +01:00
  • e22f7a2aca Add torchaudio in requirements.txt WeberJulian 2021-11-02 17:30:20 +01:00
  • 4d721bcabd fix test sentence synthesis WeberJulian 2021-11-02 16:33:40 +01:00
  • 0804806727 fix f0_cache_path in dataset WeberJulian 2021-10-29 19:05:26 +02:00
  • 3b5592abcf fix test vits WeberJulian 2021-10-29 17:09:10 +02:00
  • 2a2b5767c2 fix collate_fn WeberJulian 2021-10-27 13:45:49 +02:00
  • 78c2d12a91 PitchExtractor Julian WEBER 2021-10-27 13:40:11 +02:00
  • 9a2f91327c get_aux_input Julian WEBER 2021-10-27 12:02:02 +02:00
  • b3abd01793 Merge dataset Julian WEBER 2021-10-27 11:54:05 +02:00
  • 10ff90d6d2 Add remove silence VAD script Edresson 2021-10-26 11:35:18 -03:00
  • 1bd1a0546b Add audio resample in the speaker consistency loss Edresson 2021-10-19 08:07:48 -03:00
  • 1c6bcda950 Add freeze vocoder generator and flow-based decoder option Edresson 2021-09-19 21:06:58 -03:00
  • 2b952d8b97 freeze vits parts WeberJulian 2021-09-19 23:35:31 +02:00
  • 005bba60b0 get_speaker_weighted_sampler WeberJulian 2021-09-19 23:34:38 +02:00
  • 9de4539422 Update the VITS model docs Edresson 2021-09-19 13:29:09 -03:00
  • eeb8ac07d9 Add voice conversion fine tuning mode Edresson 2021-09-14 17:27:00 -03:00
  • 6ac31e4152 Added a notbook for d-vector multilingual VITS WeberJulian 2021-07-21 16:49:12 +02:00
  • 690b37d0ab Add support to use the speaker encoder as loss function in VITS model Edresson 2021-09-03 07:37:43 -03:00
  • 9b011b1cb3 Add H/ASP original checkpoint support Edresson 2021-09-01 09:23:45 -03:00
  • 0bdfd3cb50 Add the ValueError in the restore checkpoint exception to avoid problems with the optimizer restauration when new keys are addition Edresson 2021-08-28 10:11:33 -03:00
  • bbdb5c38e6 Add VITS multispeaker train unit test Edresson 2021-08-28 09:59:48 -03:00
  • 92f7f4f400 Active the multispeaker mode in multilingual training Edresson 2021-08-28 09:59:09 -03:00
  • de78556655 Fix the optimizer parameters bug in multilingual and multispeaker training Edresson 2021-08-28 09:57:52 -03:00
  • 9be5b75da3 Fix bug after merge Edresson 2021-08-26 16:01:07 -03:00
  • 76251b619a Fix d-vector multispeaker training bug Edresson 2021-08-26 14:47:53 -03:00
  • e68b042493 Add VITS d-vector unit test Edresson 2021-08-26 12:19:01 -03:00
  • 959cc8f03c Add VITS multilingual unit test Edresson 2021-08-26 12:18:05 -03:00
  • 7ef3ddc6ff Fix unit tests Edresson 2021-08-26 11:36:11 -03:00
  • 36dcd11453 Fix pylint issues Edresson 2021-08-26 07:55:41 -03:00
  • c53693c155 Implement vocoder Fine Tuning like SC-GlowTTS paper Edresson 2021-08-25 16:52:02 -03:00
  • f1f016314e Fix the bug in M-AILABS formatter Edresson 2021-08-23 16:12:31 -03:00
  • c334d39acc Add voice conversion support for the model VITS trained with external speaker embedding Edresson 2021-08-19 14:05:42 -03:00
  • e997889ba8 Fix bug in VITS multilingual inference Edresson 2021-08-19 09:59:41 -03:00
  • 7c0b8ec572 Fix bugs in the non-multilingual VITS inference Edresson 2021-08-17 07:41:21 -03:00
  • 3fbbebd74d Fix pylint issues Edresson 2021-08-15 13:44:58 -03:00
  • ac9416fb86 Add multilingual inference support Edresson 2021-08-14 17:52:00 -03:00
  • dcb2374bc9 Add multilingual training support to the VITS model Edresson 2021-08-13 21:40:34 -03:00
  • f996afedb0 Implement multilingual dataloader support Edresson 2021-08-13 19:58:56 -03:00
  • 5f1c18187f Fix pylint issues Edresson 2021-08-13 03:38:54 -03:00
  • d91c595c5a Implement training support with d_vecs in the VITS model Edresson 2021-08-13 00:49:38 -03:00
  • 6a7db67a91 Allow ignore speakers for all multispeaker datasets Edresson 2021-08-12 22:48:30 -03:00
  • e0ad838066 Select randomly a speaker from the speaker manager for the test setences Edresson 2021-08-12 21:52:12 -03:00
  • eb3e8affe1 Save speakers embeddings/ids before starting training Edresson 2021-08-12 07:52:44 -03:00
  • 37803467aa Merge pull request #1021 from loganhart420/dataset_downloaders Eren Gölge 2021-12-20 10:42:20 +01:00
  • 6b8ed18dcc Merge pull request #1022 from coqui-ai/papercuts Eren Gölge 2021-12-20 10:40:57 +01:00
  • 0635e8b931 Try to speed up CI install times Reuben Morais 2021-12-17 11:49:45 +01:00
  • 0057494a2a Remove broken link Reuben Morais 2021-12-17 11:03:03 +01:00
  • 859ac1a54c Include usage instructions in README Reuben Morais 2021-12-17 11:02:34 +01:00
  • 78100851f2 Upload sdist and wheel to PyPI Reuben Morais 2021-12-17 10:44:06 +01:00
  • 223ffe2954 Add torchaudio to requirements.txt Eren Gölge 2021-12-16 14:57:54 +00:00
  • 95ca2ef773 Implement init_speaker_encoder and change arg names Eren Gölge 2021-12-16 14:57:24 +00:00
  • 1ddf245b08 Use speaker_encoder from speaker manager in Vits Eren Gölge 2021-12-16 14:56:34 +00:00
  • 08a1cf3dcb Change speaker_idx to speaker_name Eren Gölge 2021-12-16 14:55:43 +00:00
  • abedfd586d Add functions to get and check and argument in config and config.model_args Eren Gölge 2021-12-16 14:53:57 +00:00
  • 103c010eca Add addtional datasets loganhart420 2021-12-16 07:21:27 -05:00
  • 9ec6238f4a Fixup Eren Gölge 2021-12-13 16:30:15 +00:00
  • 6274d5e438 Fixup Eren Gölge 2021-12-13 16:29:19 +00:00
  • 6d7199d559 Rename setup_model to setup_speaker_encoder_model Eren Gölge 2021-12-13 16:28:54 +00:00
  • f73573c215 Fix synthesizer reading use_language_embedding Eren Gölge 2021-12-13 16:27:36 +00:00
  • 4b06e3e232 Use torchaudio for ResNet speaker encoder Eren Gölge 2021-12-13 16:23:57 +00:00
  • 84bbe02839 Add 👑YourTTS docs Eren Gölge 2021-12-10 09:12:03 +00:00
  • bbea9b3f9f Remove redundant code Eren Gölge 2021-12-10 07:53:19 +00:00
  • 66b6e9bc99 Make style Eren Gölge 2021-12-10 07:53:10 +00:00
  • b4bb0ace70 Fix zoo tests WeberJulian 2021-12-09 12:42:38 +01:00
  • 846b4a14c6 Add recipe for multi-lingual VITS WeberJulian 2021-12-08 19:42:45 +01:00
  • 4706583452 Add support for multi-lingual models in CLI WeberJulian 2021-12-08 19:34:36 +01:00
  • 7b81c16434 Fix seed in test_samplers to avoid random fails WeberJulian 2021-12-01 23:48:38 +01:00
  • 22c7be5f44 Add test for language_weighted_sampler WeberJulian 2021-12-01 23:36:29 +01:00
  • 3f3505c1ca Prevent weighted sampler use when num_gpus > 1 WeberJulian 2021-11-28 00:48:53 +01:00
  • 0f64d45e04 Revert init multispeaker change WeberJulian 2021-11-28 00:23:55 +01:00