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.

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

fix "." (dot) pronounced #308

Open
wants to merge 1 commit into
base: dev
Choose a base branch
from
Open

Conversation

ROBERT-MCDOWELL
Copy link

TODO: it needs to check if the "." dot is between numbers so it has to be pronounced (num2words?)

@eginhard
Copy link
Member

Thank you for the PR! I'm not sure yet if this is a good idea, I'm afraid it might cause unexpected issues. Perhaps a safer approach would be to only remove periods at the end of the input?

@ROBERT-MCDOWELL
Copy link
Author

ROBERT-MCDOWELL commented Feb 25, 2025

according to our hundreds test from more than 100 languages, and thousands users reports, I can say removing the "dot" is worse , causing change of the sentence voice tone confusing its sense and hallucinations sometimes.
For us it's the only way to get rid of unpleasant "dot" pronounced by the speaker, and it's absolutely worth to do it since there are much much more normal "dot" in a text than a "dot" representing a decimal number.
but if you have another better solution like review the entire XTTSv2 model to fix it so I'm ok with it.

@eginhard
Copy link
Member

I can say removing the "dot" is worse

Should this be not removing it is worse? On the other hand in #317 (comment) you suggested adding punctuation can help with short utterances, so removing it always might not be the best?

but if you have another better solution like review the entire XTTSv2 model to fix it so I'm ok with it.

There is probably no clean way to fix it because it's likely due to some issue in the original XTTS training, which is not reproducible.

@ROBERT-MCDOWELL
Copy link
Author

Should this be not removing it is worse? On the other hand in #317 (comment) you suggested adding punctuation can help with short utterances, so removing it always might not be the best?

no, removing it is worse, not worth! :)
the dot should stay with a space between the word and the dot. then use my patch and everyone is happy to have a TTS not pronouncing "dot" at each sentence.

now if you really want more and more report of user complaining about the "dot " be pronounced (in all languages btw). so it's up to you. on our side, we prefer for now use our patch to avoid that.

@@ -258,10 +258,11 @@ def expand_abbreviations_multilingual(text, lang="en"):
("$", " dollar "),
("£", " pound "),
("°", " degree "),
(".", ""),
Copy link
Member

@eginhard eginhard Feb 25, 2025

Choose a reason for hiding this comment

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

no, removing it is worse, not worth! :) the dot should stay with a space between the word and the dot. then use my patch and everyone is happy to have a TTS not pronouncing "dot" at each sentence.

Ok. I'm sorry, but I don't fully understand your change yet then. With these lines, you are removing the dot, no?

@UtkuBulkan
Copy link

@ROBERT-MCDOWELL , with Italian model, it is already pronouncing "." as punto. I haven't seen this behavior with other models.

@ROBERT-MCDOWELL
Copy link
Author

it's only with xttsv2

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants