4136 Commits

This Branch

This Branch

All Branches

Author	SHA1	Message	Date
WeberJulian	602ca85c74	Fix pred_avg_pitch_emb	2022-06-28 14:37:54 +02:00
WeberJulian	0a54d30023	Make style	2022-06-28 11:10:49 +02:00
WeberJulian	ea9dbd40fd	Add support form emotion labels in datasets	2022-06-28 11:10:49 +02:00
Edresson Casanova	135363a6d1	Remove Pitch conditioning on encoder	2022-06-22 17:28:25 -03:00
Edresson Casanova	25e3221daf	Remove noise scale predictor	2022-06-22 14:23:33 -03:00
Edresson Casanova	ae1f443b35	Add pitch and prosody encoder suport for the conditional module	2022-06-22 14:20:00 -03:00
Edresson Casanova	ef27039190	Add conditional module on VITS	2022-06-21 10:57:05 +00:00
Edresson Casanova	18dee1190e	Add Determinist decoder on VITS	2022-06-20 14:06:16 +00:00
Edresson Casanova	3165c55fae	Add latent discriminator over unexpanded m_p	2022-06-18 14:26:56 +00:00
Edresson Casanova	569decba64	Add Pitch Predictor conditioned on enc	2022-06-17 17:39:17 -03:00
Edresson Casanova	8f6c187848	Add Pitch Predictor conditioned on m_p	2022-06-17 17:45:10 +00:00
Edresson Casanova	6186da855f	Bug fix on pre-compute F0	2022-06-16 19:38:11 +00:00
Edresson Casanova	6a573065f4	Add pitch predictor	2022-06-16 19:34:54 +00:00
Edresson Casanova	5859e6474c	Add script for extract VITS MAS alignments	2022-06-16 19:07:10 +00:00
Edresson Casanova	92e7391a5d	Add speaker embedding on prosody encoder	2022-06-16 19:06:48 +00:00
Edresson Casanova	251e1c289d	Add support for inference using an specific reference file instead of the averaged embeddings	2022-06-13 13:47:31 +00:00
Edresson Casanova	856e185641	Add Resnet prosody encoder support	2022-06-13 13:47:22 +00:00
Edresson Casanova	0844d9225d	Fix unit tests	2022-06-08 10:18:19 -03:00
Edresson Casanova	4b59f07946	Support the use of speaker embedding as emotion embedding	2022-06-08 09:52:39 -03:00
Edresson Casanova	360b969c23	Fix rebase issues	2022-06-08 09:52:39 -03:00
Edresson Casanova	e069985f17	Add speaker and emotion squeezer layers	2022-06-08 09:52:39 -03:00
Edresson Casanova	a309edacb4	Remove VITS conditional flow module	2022-06-08 09:52:39 -03:00
Edresson Casanova	a1d0088087	Remove VITS End2End loss	2022-06-08 09:52:38 -03:00
Edresson Casanova	ae55bdae6c	Fix Lint checks	2022-06-08 09:52:38 -03:00
Edresson Casanova	fd1036f4ba	Add Noise scale predictor	2022-06-08 09:52:38 -03:00
Edresson Casanova	d6d8d0e3e1	Fix the VITS GAN loss	2022-06-08 09:52:38 -03:00
Edresson Casanova	e07fcc7a8c	Add text encoder adversarial loss on the VITS	2022-06-08 09:52:38 -03:00
Edresson Casanova	4e94b46d5e	Add end2end VITS loss	2022-06-08 09:52:38 -03:00
Edresson Casanova	ec8c8dc5a2	Recreate the prior distribution of Capacitron VAE on the right device	2022-06-08 09:52:38 -03:00
Edresson Casanova	a822f21b78	Add prosody encoder inference support	2022-06-08 09:52:38 -03:00
Edresson Casanova	010f847929	Add an option to detach the prosody encoder input	2022-06-08 09:52:38 -03:00
Edresson Casanova	2cac18c7b7	Add VAE prosody encoder	2022-06-08 09:52:37 -03:00
Edresson Casanova	f774cf0648	Condition the prosody encoder on z_p	2022-06-08 09:52:37 -03:00
Edresson Casanova	512525cc39	Support prosody conditional model on decoder input	2022-06-08 09:52:37 -03:00
Edresson Casanova	02194367d7	Add emotion classifier loss	2022-06-08 09:52:37 -03:00
Edresson Casanova	f50819a5f6	Fix compute embeddings issue	2022-06-08 09:52:37 -03:00
Edresson Casanova	a6c8fea192	Add conditional module	2022-06-08 09:52:37 -03:00
Edresson Casanova	bce4a41b9c	Fix unit tests	2022-06-08 09:52:37 -03:00
Edresson Casanova	0fb1b200c6	Fix rebase issues	2022-06-08 09:52:37 -03:00
Edresson Casanova	98c2834b17	Disable the reversal prosody encoder speaker loss	2022-06-08 09:52:37 -03:00
Edresson Casanova	ac3f98cefb	Add text encoder reversal speaker classifier loss	2022-06-08 09:52:37 -03:00
Edresson Casanova	a543d71352	Clean up old code	2022-06-08 09:52:36 -03:00
Edresson Casanova	66e3f5388e	Add prosody encoder params on config	2022-06-08 09:52:36 -03:00
Edresson Casanova	95409be0bc	Add Speech style balancer	2022-06-08 09:52:36 -03:00
Edresson Casanova	050f7707e2	Add reversal classifier loss	2022-06-08 09:52:36 -03:00
Edresson Casanova	44ec2ab387	Add prosody encoder training support	2022-06-08 09:52:36 -03:00
Edresson Casanova	6126e5e588	Add emotion embedding in the encoder	2022-06-08 09:52:36 -03:00
Edresson Casanova	1fdef1c4c9	Add formatter for the Emotional Speech Dataset	2022-06-08 09:52:36 -03:00
Edresson Casanova	61a04a7855	Remove useless encoder weights reload	2022-06-08 09:52:36 -03:00
Edresson Casanova	836c4c6801	Fix emotion unit test	2022-06-08 09:52:36 -03:00