Skip to content

Update TTS pronunciation dictionaries#15857

Open
quapham wants to merge 2 commits into
NVIDIA-NeMo:mainfrom
quapham:tts/update-hi-ipa-pron-dicts
Open

Update TTS pronunciation dictionaries#15857
quapham wants to merge 2 commits into
NVIDIA-NeMo:mainfrom
quapham:tts/update-hi-ipa-pron-dicts

Conversation

@quapham

@quapham quapham commented Jun 30, 2026

Copy link
Copy Markdown
Contributor

What changed

  • Add scripts/tts_dataset_files/hi_IN/hi_prondict-v0.3_nostress_fixed.dict.
  • Update scripts/tts_dataset_files/ipa_cmudict-0.7b_nv26.07.txt A/A(1) pronunciation ordering.

Scope

Dictionary-only change. No code changes.

Validation

  • Verified copied dictionary file hashes match the source files.
  • Verified git diff contains only the two dictionary files.

@copy-pr-bot

copy-pr-bot Bot commented Jun 30, 2026

Copy link
Copy Markdown

This pull request requires additional validation before any workflows can run on NVIDIA's runners.

Pull request vetters can view their responsibilities here.

Contributors can view more details about this message here.

@github-actions github-actions Bot added the TTS label Jun 30, 2026
@quapham quapham force-pushed the tts/update-hi-ipa-pron-dicts branch 2 times, most recently from 8f37766 to 5e117a7 Compare June 30, 2026 07:08
@blisc

blisc commented Jun 30, 2026

Copy link
Copy Markdown
Collaborator

Can you bump the version of scripts/tts_dataset_files/ipa_cmudict-0.7b_nv23.01.txt to nv26.07? Can update references from 23.01 to 26.07?

@quapham

quapham commented Jul 9, 2026

Copy link
Copy Markdown
Contributor Author

Updated the IPA CMU dictionary filename/references from nv23.01 to nv26.07 and pushed commit ca999d9

@quapham

quapham commented Jul 10, 2026

Copy link
Copy Markdown
Contributor Author

/ok to test ca999d9

@quapham

quapham commented Jul 10, 2026

Copy link
Copy Markdown
Contributor Author

/ok to test ca999d9

@blisc blisc enabled auto-merge (squash) July 10, 2026 15:19
@NVIDIA-NeMo NVIDIA-NeMo deleted a comment from copy-pr-bot Bot Jul 14, 2026
@NVIDIA-NeMo NVIDIA-NeMo deleted a comment from copy-pr-bot Bot Jul 14, 2026
@quapham

quapham commented Jul 14, 2026

Copy link
Copy Markdown
Contributor Author

/ok to test 4dfe3a5

Comment on lines +134772 to +134773
A ˈʌ
A(1) ˈeɪ

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

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

what happened to this dictionary?

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

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

We trained the model with the updated dictionary, where the pronunciation was changed from /'eɪ/ to /'ʌ/.

@XuesongYang

Copy link
Copy Markdown
Collaborator

/ok to test 4dfe3a5

quapham added 2 commits July 16, 2026 10:54
Add the fixed Hindi pronunciation dictionary, remove the old Hindi dictionary, and update the IPA CMU dictionary entry ordering for A/A(1).

Signed-off-by: quanpham <youngkwan199@gmail.com>
Signed-off-by: quanpham <youngkwan199@gmail.com>
@XuesongYang XuesongYang force-pushed the tts/update-hi-ipa-pron-dicts branch from 4dfe3a5 to 8ebea33 Compare July 16, 2026 17:54
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants