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

VITS HiFiTTS doc #6288

Merged
merged 19 commits into from
Apr 6, 2023
Merged

VITS HiFiTTS doc #6288

merged 19 commits into from
Apr 6, 2023

Conversation

treacker
Copy link
Contributor

@treacker treacker commented Mar 24, 2023 •
edited
Loading

What does this PR do ?

Update docs and model for HiFiTTS version

Collection: [TTS]

Before your PR is "Ready for review"

Pre checks:

  • Make sure you read and followed Contributor guidelines
  • Did you write any new necessary tests?
  • Did you add or update any necessary documentation?
  • Does the PR affect components that are optional to install? (Ex: Numba, Pynini, Apex etc)
    • Reviewer: Does the PR have correct import guards for all optional libraries?

PR Type:

  • New Feature
  • Bugfix
  • Documentation

If you haven't finished some of the above items you can still open "Draft" PR.

Who can review?

Anyone in the community is free to review the PR once the checks have passed.
Contributor guidelines contains specific people who can review PRs to various areas.

Additional Information

  • Related to # (issue)

treacker and others added 13 commits December 13, 2022 03:13
@treacker
storing
591d74a
@treacker
Merge branch 'main' of https://github.com/NVIDIA/NeMo into main
1f2cd6e
@treacker
Added VITS documentation
8374ae3 
Signed-off-by: Evgeniy Shabalin <baah1999@yandex.ru>
@treacker
Added VITS documentation
178c69a 
Signed-off-by: Evgeniy Shabalin <baah1999@yandex.ru>
@treacker
Cleaned stuff
82c1563 
Signed-off-by: Evgeniy Shabalin <baah1999@yandex.ru>
@treacker
Cleaned stuff
843e74d 
Signed-off-by: Evgeniy Shabalin <baah1999@yandex.ru>
@treacker
cleaning
323e791 
Signed-off-by: Evgeniy Shabalin <baah1999@yandex.ru>
@treacker
Typos
6ff867e 
Signed-off-by: Evgeniy Shabalin <baah1999@yandex.ru>
@treacker
Added experimental note
aa65b42 
Signed-off-by: Evgeniy Shabalin <baah1999@yandex.ru>
@treacker
Merge branch 'main' of https://github.com/NVIDIA/NeMo into main
9ca84b5
Merge branch 'main' of https://github.com/NVIDIA/NeMo into main
1c70344
Merge branch 'main' into vits_doc
e402f7a
updated for 44kHz version
22b398a 
Signed-off-by: Evgeny Shabalin <eshabalin@nvidia.com>
@github-actions github-actions bot added the TTS label Mar 24, 2023
added table
75d2fd4 
Signed-off-by: Evgeny Shabalin <eshabalin@nvidia.com>
XuesongYang
XuesongYang requested changes Mar 24, 2023
View reviewed changes
Copy link
Collaborator

@XuesongYang XuesongYang left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thanks for your updates! Besides of comments above, could you please also add sections showing how to evaluate your VITS model, just like our FastPitch tutorial did?

Updated tutorial
16dd374 
Signed-off-by: Evgeny Shabalin <eshabalin@nvidia.com>
Evgeny Shabalin added 2 commits March 29, 2023 06:51
XuesongYang
XuesongYang requested changes Apr 5, 2023
View reviewed changes
Copy link
Collaborator

@XuesongYang XuesongYang left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

thanks for updates. One question, are you using ARPABET or IPA units for VITS? If use ARPABET, the phoneme dict should be cmudict-0.7b_nv22.10, otherwise, ipa_cmudict-0.7b_nv23.01.txt

@treacker
Copy link
Contributor Author

treacker commented Apr 5, 2023

I am using IPA

@XuesongYang
Copy link
Collaborator

I am using IPA

Gotcha! then please fix the version of ipa dict with ipa_cmudict-0.7b_nv23.01.txt. i still see you used ipa_cmudict-0.7b_nv22.10.txt

Evgeny Shabalin and others added 2 commits April 5, 2023 12:44
Updated ipa_cmudict version
dc05669 
Signed-off-by: Evgeny Shabalin <eshabalin@nvidia.com>
@XuesongYang
Merge branch 'main' into vits_doc
5c3f7ec
@XuesongYang XuesongYang merged commit 515d36b into main Apr 6, 2023
@XuesongYang XuesongYang deleted the vits_doc branch April 6, 2023 00:08
hsiehjackson pushed a commit to hsiehjackson/NeMo that referenced this pull request Jun 2, 2023
@treacker @XuesongYang @hsiehjackson
VITS HiFiTTS doc (NVIDIA#6288)
fa333f0 
* Added VITS documentation
* Typos
* Added experimental note
* Updated tutorial
* Added spectrogram visualization
* Updated ipa_cmudict version

---------

Signed-off-by: Evgeny Shabalin <eshabalin@nvidia.com>
Co-authored-by: Xuesong Yang <1646669+XuesongYang@users.noreply.github.com>
Signed-off-by: hsiehjackson <c2hsieh@ucsd.edu>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@XuesongYang XuesongYang XuesongYang approved these changes

Assignees
No one assigned
Labels
TTS
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
2 participants
@treacker @XuesongYang