Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

v0.5.0 #1027

Merged
merged 248 commits into from
Jan 3, 2022
Merged

v0.5.0 #1027

merged 248 commits into from
Jan 3, 2022

Conversation

erogol
Copy link
Member

@erogol erogol commented Dec 20, 2021

No description provided.

Edresson and others added 30 commits December 9, 2021 12:23
@Edresson @erogol
Save speakers embeddings/ids before starting training
8310d19
@Edresson @erogol
Select randomly a speaker from the speaker manager for the test setences
234a4aa
@Edresson @erogol
Allow ignore speakers for all multispeaker datasets
c9c1960
@Edresson @erogol
Implement training support with d_vecs in the VITS model
1efcccd
@Edresson @erogol
Fix pylint issues
c9f5838
@Edresson @erogol
Implement multilingual dataloader support
829ee55
@Edresson @erogol
Add multilingual training support to the VITS model
d0e3647
@Edresson @erogol
Add multilingual inference support
8e83a21
@Edresson @erogol
Fix pylint issues
32ece5d
@Edresson @erogol
Fix bugs in the non-multilingual VITS inference
240356c
@Edresson @erogol
Fix bug in VITS multilingual inference
56b5488
@Edresson @erogol
Add voice conversion support for the model VITS trained with external…
d653227 
… speaker embedding
@Edresson @erogol
Fix the bug in M-AILABS formatter
3df5d9a
@Edresson @erogol
Implement vocoder Fine Tuning like SC-GlowTTS paper
9071bf3
@Edresson @erogol
Fix pylint issues
cfa9910
@Edresson @erogol
Fix unit tests
82611cf
@Edresson @erogol
Add VITS multilingual unit test
859cf1b
@Edresson @erogol
Add VITS d-vector unit test
08da902
@Edresson @erogol
Fix d-vector multispeaker training bug
d7042ec
@Edresson @erogol
Fix bug after merge
f4abb19
@Edresson @erogol
Fix the optimizer parameters bug in multilingual and multispeaker tra…
256197b 
…ining
@Edresson @erogol
Active the multispeaker mode in multilingual training
2bba769
@Edresson @erogol
Add VITS multispeaker train unit test
ecf327a
@Edresson @erogol
Add the ValueError in the restore checkpoint exception to avoid probl…
fee01da 
…ems with the optimizer restauration when new keys are addition
@Edresson @erogol
Add H/ASP original checkpoint support
a390103
@Edresson @erogol
Add support to use the speaker encoder as loss function in VITS model
3cd889a
@WeberJulian @erogol
Added a notbook for d-vector multilingual VITS
2be38aa
@Edresson @erogol
Add voice conversion fine tuning mode
cd7639c
@Edresson @erogol
Update the VITS model docs
5648036
@WeberJulian @erogol
get_speaker_weighted_sampler
9d2c445
erogol and others added 28 commits December 29, 2021 16:51
@erogol
Add VITS model tests
2033e17
@erogol
Fix Training HiFiGan -- avg loss not decreasing #1003
6189fdf
@erogol
Update Speaker Encoder models
638091f
@erogol
Update VITS model
7129b04
@erogol
Add custom asserts to tests
497332b
@erogol
Fix speaker encoder test
348b5c9
@erogol
Fix resnet speaker encoder
36cef59
@erogol
Add the YourTTS entry to the models
8100135
@erogol
Fix your_tts inference from the listed models
61874bc
@erogol
Print testing model
254c110
@erogol
Print urls when BadZipError
8fd1ee1
@erogol
Update yourTTS url
33711af
@erogol
Merge branch 'pr/Edresson/731-rebased' into dev
d37cfe4
@erogol
Update uk vocoder url
c5512af
@erogol
Merge branch 'dev' of https://github.com/coqui-ai/TTS into dev
38f5a11
@erogol
Make linter
e55f5ee
@erogol
Updake default vocoder for uk model
7ef458a
@WeberJulian
Fix phoneme language
a63998c
@WeberJulian
Fix VITS multispeaker recipe
9d0a732
@erogol
Merge pull request #1044 from WeberJulian/dev
d82fa05 
Fixes before YourTTS merge
@erogol
Fix language assignment
d724984
@erogol
Merge pull request #1047 from coqui-ai/fix_lang_assign
b0d6883 
Fix language assignment
@erogol
Fix if else statement
7fad969
@erogol
Prioritize the given encoder path over config
fc09e31
@erogol
Merge pull request #1050 from coqui-ai/fix_synthesizer_init
03bcae1 
Fix if else statement
@erogol
Keep proj_dim in speaker encoder models
5840d89
@erogol
Bump up to v0.5.0
58c38de
@WeberJulian
Fix train_tts.py and uncomment code (#1051)
e1accb6 
* Fix SE loading and language embedding logic

* remove trailing white space

* Uncomment resmapling code for SCL
@erogol erogol merged commit c63bb48 into main Jan 3, 2022
undefdev pushed a commit to undefdev/TTS that referenced this pull request Jan 4, 2022
@erogol @undefdev
Merge pull request coqui-ai#1027 from coqui-ai/dev
b680e24 
v0.5.0
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers
No reviews
Assignees
No one assigned
Labels
🚀 new version
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
6 participants
@erogol @vince62s @Edresson @WeberJulian @loganhart02 @reuben