Commit Graph

  • 5c821d9fa1 Fix the --model_name and --vocoder_name arguments need a <model_type> element (#1469) camillem 2022-06-27 10:32:43 +02:00
  • 3339626afc Remove conditions WeberJulian 2022-06-24 17:45:14 +02:00
  • 1bc1559f58 Add PR trigger WeberJulian 2022-06-24 17:16:41 +02:00
  • fd3b0e6f4f Add back other actions WeberJulian 2022-06-24 16:54:50 +02:00
  • 0aa71c41ca Add install requirements WeberJulian 2022-06-24 16:27:06 +02:00
  • 924dbbad50 Try --plat-name WeberJulian 2022-06-24 16:19:26 +02:00
  • 2e3743308a remove check and use only manylinux WeberJulian 2022-06-24 15:16:35 +02:00
  • c7018f19c4 temporary removal of useless pipeline WeberJulian 2022-05-25 17:31:31 +02:00
  • 1cf5bc6725 Try out manylinux WeberJulian 2022-05-25 15:30:09 +02:00
  • 85ce5aee34 Remove Pitch conditioning on encoder vits-pitch-pred-new Edresson Casanova 2022-06-23 13:34:39 -03:00
  • dca929cea4 Added d-vector pool selection implementation attribute-extraction Aya Jafari 2022-06-23 11:52:23 +00:00
  • 135363a6d1 Remove Pitch conditioning on encoder Edresson Casanova 2022-06-22 17:28:25 -03:00
  • 25e3221daf Remove noise scale predictor Edresson Casanova 2022-06-22 14:23:33 -03:00
  • ae1f443b35 Add pitch and prosody encoder suport for the conditional module Edresson Casanova 2022-06-22 14:20:00 -03:00
  • 577ec406f4 Fix checkpointing GAN models (#1641) manmay nakhashi 2022-06-22 15:37:46 +05:30
  • c8a1f8921d Merge branch 'dev' into main Eren G??lge 2022-06-21 14:13:23 +02:00
  • 00e67092d8 Bump up to v0.7.1 Eren G??lge 2022-06-21 14:12:55 +02:00
  • 829e2c24f9 v0.7.1 (#1676) v0.7.1 Eren Gölge 2022-06-21 14:11:39 +02:00
  • ef27039190 Add conditional module on VITS Edresson Casanova 2022-06-21 10:57:05 +00:00
  • 3328be7a8e Remove GL message Eren G??lge 2022-06-21 12:39:31 +02:00
  • 30c72e0d05 Add Thorsten VITS model (#1675) WeberJulian 2022-06-21 11:39:49 +02:00
  • c7cca4135d Merge pull request #1537 from coqui-ai/dev v0.7.0 Eren Gölge 2022-06-20 23:55:22 +02:00
  • 71281ff1e4 Add support for model_info in CLI (#1623) p0p4k 2022-06-21 06:28:17 +09:00
  • 18dee1190e Add Determinist decoder on VITS Edresson Casanova 2022-06-20 14:06:16 +00:00
  • 8b75e8be9c Bump up to v0.7.0 Eren G??lge 2022-06-20 13:50:09 +02:00
  • 6126c23498 Add synpaflex formatter (#1616) WeberJulian 2022-06-20 13:36:26 +02:00
  • 3165c55fae Add latent discriminator over unexpanded m_p Edresson Casanova 2022-06-18 14:26:56 +00:00
  • a969a11c04 Fix condition_dp_on_speaker fix_condition_dp_on_speaker Eren G??lge 2022-06-18 14:03:46 +02:00
  • 18dbf22195 Fix test Eren G??lge 2022-06-18 14:01:28 +02:00
  • 00a75dde29 Update recipes Eren G??lge 2022-06-18 12:21:15 +02:00
  • cd0a55df9a Make style Eren G??lge 2022-05-06 15:56:06 +02:00
  • 6939242c00 Add missing param Eren G??lge 2022-05-06 15:53:42 +02:00
  • 3ab7afbc1a Add missing decorator Eren Gölge 2022-05-03 14:09:56 +02:00
  • d832d6b08a Make style Eren Gölge 2022-05-03 13:53:06 +02:00
  • b73b445278 Update VITS VCTK recipe Eren Gölge 2022-05-03 13:44:32 +02:00
  • 463d6f1b22 Update VITS LJSpeech recipe Eren Gölge 2022-05-03 13:43:40 +02:00
  • 0ef6bf2c28 Implement VitsAudioConfig Eren Gölge 2022-05-03 13:41:51 +02:00
  • 569decba64 Add Pitch Predictor conditioned on enc Edresson Casanova 2022-06-17 17:39:17 -03:00
  • 8f6c187848 Add Pitch Predictor conditioned on m_p Edresson Casanova 2022-06-17 17:45:10 +00:00
  • 9c3473860b deleted older version Aya Jafari 2022-06-17 15:04:01 +00:00
  • 134ed5ece6 fixed bugs, added model in torch Aya Jafari 2022-06-17 15:01:02 +00:00
  • 6186da855f Bug fix on pre-compute F0 Edresson Casanova 2022-05-19 13:48:02 +00:00
  • 6a573065f4 Add pitch predictor Edresson Casanova 2022-05-16 21:53:49 +00:00
  • 5859e6474c Add script for extract VITS MAS alignments Edresson Casanova 2022-06-16 19:07:10 +00:00
  • 92e7391a5d Add speaker embedding on prosody encoder Edresson Casanova 2022-06-16 19:06:48 +00:00
  • 1187d4df5f Speaker attribute extraction - WIP Aya Jafari 2022-06-15 16:58:20 +00:00
  • 251e1c289d Add support for inference using an specific reference file instead of the averaged embeddings Edresson Casanova 2022-06-13 13:47:31 +00:00
  • 856e185641 Add Resnet prosody encoder support Edresson Casanova 2022-06-13 13:47:22 +00:00
  • c44e39d9d6 Update training_a_model.md (#1620) klotlabs 2022-06-09 00:40:05 +03:00
  • 0844d9225d Fix unit tests Edresson Casanova 2022-06-08 10:18:19 -03:00
  • 4b59f07946 Support the use of speaker embedding as emotion embedding Edresson Casanova 2022-06-07 13:29:22 -03:00
  • 360b969c23 Fix rebase issues Edresson Casanova 2022-06-07 11:26:44 -03:00
  • e069985f17 Add speaker and emotion squeezer layers Edresson Casanova 2022-06-07 09:27:08 -03:00
  • a309edacb4 Remove VITS conditional flow module Edresson Casanova 2022-06-06 19:48:56 -03:00
  • a1d0088087 Remove VITS End2End loss Edresson Casanova 2022-06-06 15:10:00 -03:00
  • ae55bdae6c Fix Lint checks Edresson Casanova 2022-06-06 14:59:21 -03:00
  • fd1036f4ba Add Noise scale predictor Edresson Casanova 2022-06-06 13:22:26 -03:00
  • d6d8d0e3e1 Fix the VITS GAN loss Edresson Casanova 2022-06-03 13:05:40 +00:00
  • e07fcc7a8c Add text encoder adversarial loss on the VITS Edresson Casanova 2022-06-02 18:40:57 -03:00
  • 4e94b46d5e Add end2end VITS loss Edresson Casanova 2022-06-02 13:50:08 -03:00
  • ec8c8dc5a2 Recreate the prior distribution of Capacitron VAE on the right device Edresson Casanova 2022-05-27 16:41:13 -03:00
  • a822f21b78 Add prosody encoder inference support Edresson Casanova 2022-05-27 16:00:41 -03:00
  • 010f847929 Add an option to detach the prosody encoder input Edresson Casanova 2022-05-27 13:19:06 -03:00
  • 2cac18c7b7 Add VAE prosody encoder Edresson Casanova 2022-05-27 12:53:56 -03:00
  • f774cf0648 Condition the prosody encoder on z_p Edresson Casanova 2022-05-26 15:41:24 -03:00
  • 512525cc39 Support prosody conditional model on decoder input Edresson Casanova 2022-05-25 17:03:38 -03:00
  • 02194367d7 Add emotion classifier loss Edresson Casanova 2022-05-25 10:05:52 -03:00
  • f50819a5f6 Fix compute embeddings issue Edresson Casanova 2022-05-25 10:05:28 -03:00
  • a6c8fea192 Add conditional module Edresson Casanova 2022-05-23 14:05:17 -03:00
  • bce4a41b9c Fix unit tests Edresson Casanova 2022-05-23 10:26:45 -03:00
  • 0fb1b200c6 Fix rebase issues Edresson Casanova 2022-05-20 18:29:39 -03:00
  • 98c2834b17 Disable the reversal prosody encoder speaker loss Edresson Casanova 2022-05-19 13:55:14 +00:00
  • ac3f98cefb Add text encoder reversal speaker classifier loss Edresson Casanova 2022-05-17 13:14:15 +00:00
  • a543d71352 Clean up old code Edresson Casanova 2022-05-16 13:09:12 +00:00
  • 66e3f5388e Add prosody encoder params on config Edresson Casanova 2022-05-16 09:45:28 -03:00
  • 95409be0bc Add Speech style balancer Edresson Casanova 2022-04-19 15:51:15 -03:00
  • 050f7707e2 Add reversal classifier loss Edresson Casanova 2022-04-18 21:09:59 -03:00
  • 44ec2ab387 Add prosody encoder training support Edresson Casanova 2022-04-18 17:01:44 -03:00
  • 6126e5e588 Add emotion embedding in the encoder Edresson Casanova 2022-03-31 19:14:41 -03:00
  • 1fdef1c4c9 Add formatter for the Emotional Speech Dataset Edresson Casanova 2022-03-31 17:27:30 +00:00
  • 61a04a7855 Remove useless encoder weights reload Edresson Casanova 2022-03-31 11:05:58 -03:00
  • 836c4c6801 Fix emotion unit test Edresson Casanova 2022-03-31 08:34:08 -03:00
  • e8c4417f07 Fix Style tests Edresson Casanova 2022-03-30 16:51:39 -03:00
  • 730befebcc Fix style tests Edresson Casanova 2022-03-23 15:31:33 -03:00
  • a8292c7c03 Fix the Bug in Synthesizer Edresson Casanova 2022-03-30 15:32:35 -03:00
  • e409f3588b Bug fix in single speaker emotion embedding training Edresson Casanova 2022-03-16 20:57:14 +00:00
  • 6f33506d89 Fix unit tests Edresson Casanova 2022-03-15 19:40:07 +00:00
  • 7a0eba517f Add emotion external embeddings training unit test Edresson Casanova 2022-03-15 13:09:58 +00:00
  • 5a10ef27b3 Add emotion consistency loss Edresson Casanova 2022-03-15 12:35:00 +00:00
  • c54e6ae1e4 Fix the bug in sythesizer Edresson Casanova 2022-03-15 12:33:36 +00:00
  • bd99548016 Add Emotion Support for the VITS model Edresson Casanova 2022-03-15 01:16:48 +00:00
  • ad7ce05ac9 Add emotion manager Edresson Casanova 2022-03-14 14:26:40 +00:00
  • f09ea11c71 Internal formatter (#1629) WeberJulian 2022-06-08 14:31:03 +02:00
  • bf45319f64 Add speaker and emotion squeezer layers emotion_cond_module Edresson Casanova 2022-06-07 09:27:08 -03:00
  • 0f1dde642f Remove VITS conditional flow module Edresson Casanova 2022-06-06 19:48:56 -03:00
  • 5bd59a6023 Remove VITS End2End loss Edresson Casanova 2022-06-06 15:10:00 -03:00
  • 8ea72356a2 Fix Lint checks Edresson Casanova 2022-06-06 14:59:21 -03:00
  • 0d7f8e24b2 Add Noise scale predictor Edresson Casanova 2022-06-06 13:22:26 -03:00
  • cbc81b55cb Fix the VITS GAN loss Edresson Casanova 2022-06-03 13:05:40 +00:00
  • 7f8c12888c Add text encoder adversarial loss on the VITS Edresson Casanova 2022-06-02 18:40:57 -03:00