Skip to content

Conversation

ZZDoog
Copy link

@ZZDoog ZZDoog commented Jul 31, 2024

The abnormal noise at the end of the generated audio is likely caused by the Duration Predictor predicting an excessively long duration for the last punctuation mark in the input text. During inference, if the input text ends with a non-alphabetic character, the duration should be manually set to the minimum value.

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.

1 participant