Skip to content

Add end_silence_timeout_ms parameter to azure.STT() #3577

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.

Sign up for GitHub

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

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
+9 −0
Open

Add end_silence_timeout_ms parameter to azure.STT() #3577

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
9 changes: 9 additions & 0 deletions livekit-plugins/livekit-plugins-azure/livekit/plugins/azure/stt.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -54,6 +54,7 @@ class STTOptions:
language: list[
str
] # see https://learn.microsoft.com/en-us/azure/ai-services/speech-service/language-support?tabs=stt
end_silence_timeout_ms: NotGivenOr[int]
speech_endpoint: NotGivenOr[str] = NOT_GIVEN
profanity: NotGivenOr[speechsdk.enums.ProfanityOption] = NOT_GIVEN
phrase_list: NotGivenOr[list[str] | None] = NOT_GIVEN
Expand All @@ -79,6 +80,7 @@ def __init__(
speech_endpoint: NotGivenOr[str] = NOT_GIVEN,
phrase_list: NotGivenOr[list[str] | None] = NOT_GIVEN,
explicit_punctuation: bool = False,
end_silence_timeout_ms: NotGivenOr[int] = NOT_GIVEN,
):
"""
Create a new instance of Azure STT.
Expand Down Expand Up @@ -144,6 +146,7 @@ def __init__(
speech_endpoint=speech_endpoint,
phrase_list=phrase_list,
explicit_punctuation=explicit_punctuation,
end_silence_timeout_ms=end_silence_timeout_ms,
)
self._streams = weakref.WeakSet[SpeechStream]()

Expand Down Expand Up @@ -387,6 +390,12 @@ def _create_speech_recognizer(
"punctuation", "explicit", speechsdk.ServicePropertyChannel.UriQueryParameter
)

if config.end_silence_timeout_ms:
speech_config.set_property(
speechsdk.enums.PropertyId.SpeechServiceConnection_EndSilenceTimeoutMs,
str(config.end_silence_timeout_ms),
)

kwargs: dict[str, Any] = {}
if config.language and len(config.language) > 1:
kwargs["auto_detect_source_language_config"] = (
Expand Down