4034 Commits

This Branch

This Branch

All Branches

Author	SHA1	Message	Date
WeberJulian	da6c1e858c	Fix small issues	2021-12-20 11:54:10 +00:00
WeberJulian	e8af6a9f08	Fix use_speaker_embedding logic	2021-12-20 11:54:10 +00:00
WeberJulian	23d789c072	Fix continue path	2021-12-20 11:54:10 +00:00
WeberJulian	120332d53f	Fix phonemes	2021-12-20 11:54:10 +00:00
WeberJulian	846bf16f02	fix imports for load_meta_data	2021-12-20 11:54:10 +00:00
WeberJulian	1340938159	fix phonemes per language	2021-12-20 11:54:10 +00:00
WeberJulian	e995a63bd6	fix linter	2021-12-20 11:54:10 +00:00
WeberJulian	1472b6df49	make style	2021-12-20 11:54:10 +00:00
WeberJulian	e22f7a2aca	Add torchaudio in requirements.txt	2021-12-20 11:54:10 +00:00
WeberJulian	4d721bcabd	fix test sentence synthesis	2021-12-20 11:54:10 +00:00
WeberJulian	0804806727	fix f0_cache_path in dataset	2021-12-20 11:54:10 +00:00
WeberJulian	3b5592abcf	fix test vits	2021-12-20 11:54:10 +00:00
WeberJulian	2a2b5767c2	fix collate_fn	2021-12-20 11:54:10 +00:00
Julian WEBER	78c2d12a91	PitchExtractor	2021-12-20 11:54:10 +00:00
Julian WEBER	9a2f91327c	get_aux_input	2021-12-20 11:54:10 +00:00
Julian WEBER	b3abd01793	Merge dataset	2021-12-20 11:54:10 +00:00
Edresson	10ff90d6d2	Add remove silence VAD script	2021-12-20 11:54:10 +00:00
Edresson	1bd1a0546b	Add audio resample in the speaker consistency loss	2021-12-20 11:54:10 +00:00
Edresson	1c6bcda950	Add freeze vocoder generator and flow-based decoder option	2021-12-20 11:54:10 +00:00
WeberJulian	2b952d8b97	freeze vits parts	2021-12-20 11:54:10 +00:00
WeberJulian	005bba60b0	get_speaker_weighted_sampler	2021-12-20 11:54:10 +00:00
Edresson	9de4539422	Update the VITS model docs	2021-12-20 11:54:10 +00:00
Edresson	eeb8ac07d9	Add voice conversion fine tuning mode	2021-12-20 11:54:10 +00:00
WeberJulian	6ac31e4152	Added a notbook for d-vector multilingual VITS	2021-12-20 11:54:09 +00:00
Edresson	690b37d0ab	Add support to use the speaker encoder as loss function in VITS model	2021-12-20 11:54:09 +00:00
Edresson	9b011b1cb3	Add H/ASP original checkpoint support	2021-12-20 11:54:09 +00:00
Edresson	0bdfd3cb50	Add the ValueError in the restore checkpoint exception to avoid problems with the optimizer restauration when new keys are addition	2021-12-20 11:54:09 +00:00
Edresson	bbdb5c38e6	Add VITS multispeaker train unit test	2021-12-20 11:54:09 +00:00
Edresson	92f7f4f400	Active the multispeaker mode in multilingual training	2021-12-20 11:54:09 +00:00
Edresson	de78556655	Fix the optimizer parameters bug in multilingual and multispeaker training	2021-12-20 11:54:09 +00:00
Edresson	9be5b75da3	Fix bug after merge	2021-12-20 11:54:09 +00:00
Edresson	76251b619a	Fix d-vector multispeaker training bug	2021-12-20 11:54:09 +00:00
Edresson	e68b042493	Add VITS d-vector unit test	2021-12-20 11:54:09 +00:00
Edresson	959cc8f03c	Add VITS multilingual unit test	2021-12-20 11:54:09 +00:00
Edresson	7ef3ddc6ff	Fix unit tests	2021-12-20 11:54:09 +00:00
Edresson	36dcd11453	Fix pylint issues	2021-12-20 11:54:09 +00:00
Edresson	c53693c155	Implement vocoder Fine Tuning like SC-GlowTTS paper	2021-12-20 11:54:09 +00:00
Edresson	f1f016314e	Fix the bug in M-AILABS formatter	2021-12-20 11:54:09 +00:00
Edresson	c334d39acc	Add voice conversion support for the model VITS trained with external speaker embedding	2021-12-20 11:54:09 +00:00
Edresson	e997889ba8	Fix bug in VITS multilingual inference	2021-12-20 11:54:09 +00:00
Edresson	7c0b8ec572	Fix bugs in the non-multilingual VITS inference	2021-12-20 11:54:09 +00:00
Edresson	3fbbebd74d	Fix pylint issues	2021-12-20 11:54:09 +00:00
Edresson	ac9416fb86	Add multilingual inference support	2021-12-20 11:54:09 +00:00
Edresson	dcb2374bc9	Add multilingual training support to the VITS model	2021-12-20 11:54:09 +00:00
Edresson	f996afedb0	Implement multilingual dataloader support	2021-12-20 11:54:09 +00:00
Edresson	5f1c18187f	Fix pylint issues	2021-12-20 11:54:09 +00:00
Edresson	d91c595c5a	Implement training support with d_vecs in the VITS model	2021-12-20 11:54:09 +00:00
Edresson	6a7db67a91	Allow ignore speakers for all multispeaker datasets	2021-12-20 11:54:09 +00:00
Edresson	e0ad838066	Select randomly a speaker from the speaker manager for the test setences	2021-12-20 11:54:09 +00:00
Edresson	eb3e8affe1	Save speakers embeddings/ids before starting training	2021-12-20 11:54:09 +00:00