Edresson
a3901032f4
Add H/ASP original checkpoint support
2021-12-09 13:28:16 +00:00
Edresson
fee01daa09
Add the ValueError in the restore checkpoint exception to avoid problems with the optimizer restauration when new keys are addition
2021-12-09 13:27:21 +00:00
Edresson
ecf327a118
Add VITS multispeaker train unit test
2021-12-09 13:27:21 +00:00
Edresson
2bba769e67
Active the multispeaker mode in multilingual training
2021-12-09 13:27:21 +00:00
Edresson
256197b6aa
Fix the optimizer parameters bug in multilingual and multispeaker training
2021-12-09 13:27:21 +00:00
Edresson
f4abb19515
Fix bug after merge
2021-12-09 13:26:33 +00:00
Edresson
d7042ecfd8
Fix d-vector multispeaker training bug
2021-12-09 13:26:33 +00:00
Edresson
08da902af3
Add VITS d-vector unit test
2021-12-09 13:18:36 +00:00
Edresson
859cf1bfac
Add VITS multilingual unit test
2021-12-09 13:18:36 +00:00
Edresson
82611cfcd3
Fix unit tests
2021-12-09 13:18:36 +00:00
Edresson
cfa9910f9d
Fix pylint issues
2021-12-09 13:16:32 +00:00
Edresson
9071bf326f
Implement vocoder Fine Tuning like SC-GlowTTS paper
2021-12-09 13:16:32 +00:00
Edresson
3df5d9a619
Fix the bug in M-AILABS formatter
2021-12-09 13:11:06 +00:00
Edresson
d653227e59
Add voice conversion support for the model VITS trained with external speaker embedding
2021-12-09 13:11:06 +00:00
Edresson
56b548835d
Fix bug in VITS multilingual inference
2021-12-09 13:11:06 +00:00
Edresson
240356cd53
Fix bugs in the non-multilingual VITS inference
2021-12-09 13:11:06 +00:00
Edresson
32ece5d5ad
Fix pylint issues
2021-12-09 13:11:06 +00:00
Edresson
8e83a212fa
Add multilingual inference support
2021-12-09 13:10:09 +00:00
Edresson
d0e3647db6
Add multilingual training support to the VITS model
2021-12-09 13:07:00 +00:00
Edresson
829ee55b04
Implement multilingual dataloader support
2021-12-09 12:50:03 +00:00
Edresson
c9f5838bb4
Fix pylint issues
2021-12-09 12:38:58 +00:00
Edresson
1efcccd5c9
Implement training support with d_vecs in the VITS model
2021-12-09 12:37:37 +00:00
Edresson
c9c1960040
Allow ignore speakers for all multispeaker datasets
2021-12-09 12:35:12 +00:00
Edresson
234a4aacb3
Select randomly a speaker from the speaker manager for the test setences
2021-12-09 12:32:14 +00:00
Edresson
8310d19da8
Save speakers embeddings/ids before starting training
2021-12-09 12:23:02 +00:00
Eren Gölge
7f1a23787e
Merge pull request #914 from coqui-ai/dev
...
v0.4.2
2021-12-08 16:41:44 +01:00
Jörg Thalheim
bce143c738
server: fix compatibility with tts_models/en/ljspeech/fast_pitch ( #893 )
2021-12-07 14:36:29 +01:00
Eren Gölge
babdd84f91
Fix GST inference
...
commit d3e477875a7e46a101fcf95a1794442823750fe2
Author: George Rousssos <25833833+george-roussos@users.noreply.github.com >
Date: Wed Nov 3 10:16:12 2021 +0000
Read .wav for GST conditioning from CL
commit 074e6d0874d3b34fb6a4991fc17d66dccd413fbb
Author: George Rousssos <25833833+george-roussos@users.noreply.github.com >
Date: Fri Oct 29 14:43:47 2021 +0100
Fix GST during inference in Tacotron2
commit fdece14585ab5a36eed1061a9a838d8e48aa6882
Author: George Rousssos <25833833+george-roussos@users.noreply.github.com >
Date: Wed Nov 3 10:16:12 2021 +0000
Read .wav for GST conditioning from CL
commit cd29e21b8d0a541ee298d2bf5f67223ad60be38f
Author: George Rousssos <25833833+george-roussos@users.noreply.github.com >
Date: Fri Oct 29 14:43:47 2021 +0100
Fix GST during inference in Tacotron2
commit 908ce39370eadcc9fa8510cdb26c9ead87305427
Author: George Rousssos <25833833+george-roussos@users.noreply.github.com >
Date: Fri Oct 29 12:49:37 2021 +0100
Make trim_db value negative
commit 1008a2e0f72fa7ca7f0307424f570386f2f16d42
Author: George Rousssos <25833833+george-roussos@users.noreply.github.com >
Date: Fri Oct 29 12:22:24 2021 +0100
Set find_endpoint db threshold in config.json
2021-12-07 13:28:49 +00:00
Eren Gölge
ce45d9e1af
Make style and lint
2021-12-01 10:42:52 +00:00
Eren Gölge
40cb8ac966
Fix #958
2021-12-01 10:33:34 +00:00
Eren Gölge
512ada7548
Fix callbacks against multi-gpu training
2021-12-01 10:32:14 +00:00
Baybars Külebi
9a145c9b88
Documentation corrections for finetuning and data preparation ( #931 )
...
* arctic recipe added
* config correction
* arctic config update
* directory name fix
* ugly prints added
* config and data corrections
* training instructions added
* documentation updates for finetuning and data prep
Revert "arctic recipe added"
This reverts commit 77b4df1f43a00af642f43655abf817e0551d0147.
doc updates for finetuning and data prep
2021-11-15 18:14:55 +01:00
Eren Gölge
2ed9e3c241
Fix constant use of noise augment
2021-11-08 09:20:34 +01:00
Eren Gölge
b6b14a76af
Fix VITS stochastic duration predictor
2021-11-08 09:20:11 +01:00
Eren Gölge
3a77899775
Update issue and feature request templates
2021-11-08 09:19:37 +01:00
Eren Gölge
dc3dd55dd9
Add collect_env_info.py
2021-11-08 08:59:08 +01:00
Eren Gölge
faafea4cf2
Fix style
2021-11-04 17:04:40 +01:00
Eren Gölge
d227aaebcc
Print when using Griffin-Lim in Synthesizer
2021-11-01 16:52:26 +01:00
Eren Gölge
c5077c6c3f
Merge branch 'dev' of https://github.com/coqui-ai/TTS into dev
2021-11-01 16:42:27 +01:00
Eren Gölge
20cebde1c9
Add docstring to MAI labs formatter
2021-11-01 16:41:55 +01:00
Eren Gölge
608f437545
Add a function to find unique chars
2021-11-01 16:41:33 +01:00
Eren Gölge
d6d780e758
Fix FastSpeech config
2021-11-01 16:41:15 +01:00
Eren Gölge
5ba47081ee
Use GL for VCTK FastPitch models
2021-11-01 16:39:03 +01:00
Michael Hansen
3bc043faeb
Upgrade to gruut 2.0 ( #882 )
2021-10-31 11:41:55 +01:00
Eren Gölge
f38c5ee6c1
Merge branch 'dev' of https://github.com/coqui-ai/TTS into dev
2021-10-30 14:50:25 +02:00
Eren Gölge
505e2db6aa
Fix VCTK Tacotron2-DDC recipe
2021-10-30 14:47:49 +02:00
Eren Gölge
9e2befb55c
Add vctk tacotron2 recipe
2021-10-30 14:47:35 +02:00
George
37eaefc085
Optional silence trimming during inference and find_endpoint() fix ( #898 )
...
* Set find_endpoint db threshold in config.json
* Optional silence trimming during inference
* Make trim_db value negative
2021-10-29 18:28:55 +02:00
Eren Gölge
33aa27e2d6
Merge pull request #901 from coqui-ai/dev
...
v0.4.2
2021-10-29 18:20:51 +02:00
Eren Gölge
7293abada2
Bump up to v0.4.2
2021-10-29 17:57:30 +02:00
