-
Notifications
You must be signed in to change notification settings - Fork 212
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
Adding UtteranceEnd support for Deepgram #737
base: main
Are you sure you want to change the base?
Conversation
|
|
@@ -63,6 +64,7 @@ def __init__( | |||
smart_format: bool = True, | |||
no_delay: bool = True, | |||
endpointing_ms: int = 25, | |||
utterance_end_ms: int | None, |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Hey, can you default it to None?
@@ -391,6 +401,12 @@ def _process_stream_event(self, data: dict) -> None: | |||
|
|||
elif data["type"] == "Metadata": | |||
pass # metadata is too noisy | |||
elif data["type"] == "UtteranceEnd": |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Is it being sent every time we finish speaking? If so, we should remove the previous dispatch of END_OF_SPEECH to avoid duplicate events, (only when end_of_utterance_ms is enabled)
Adding support for UtteranceEnd to Deepgram agent plugin. The UtteranceEnd is another feature offered by Deepgram to detect end of speech.
The Deepgram documentation is here:
https://developers.deepgram.com/docs/utterance-end