Fix for short utterances when using ForceEndOfUtterance #78
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Contributor
|
What testing did you do for this fix? |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Under certain circumstances, when there is a short utterance and the VAD triggers a
ForceEndOfUtterancemessage, then this can result in the STT engine emitting the utterance as finals, bypassing the partial payloads. The turn detection uses partials to detect speaker start / stop events and for end of turn messages, and the absence of the partial utterance resulted in these messages not being emitted.The fix checks final payloads to determine if there was a previous valid partial payload and will then determine whether to trigger a start of turn so that the remaining end of turn logic follows as expected.