Skip to content

feat(google): add denoiser configuration parameter to Google STT class #3823

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 3 commits into
base: main
Choose a base branch
from
Open

feat(google): add denoiser configuration parameter to Google STT class #3823

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
a1a2c40
Update STT configuration to include denoiser settings and increment v…
LastMonopoly Nov 7, 2025
0cdf803
feat(stt): add denoiser configuration parameter to STT class
LastMonopoly Nov 7, 2025
dd157ef
feat(stt): add denoiser configuration parameter to STT class
LastMonopoly Nov 7, 2025
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
6 changes: 6 additions & 0 deletions livekit-plugins/livekit-plugins-google/livekit/plugins/google/stt.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -75,6 +75,7 @@ class STTOptions:
sample_rate: int
min_confidence_threshold: float
keywords: NotGivenOr[list[tuple[str, float]]] = NOT_GIVEN
denoiser_config: NotGivenOr[cloud_speech.DenoiserConfig] = NOT_GIVEN

def build_adaptation(self) -> cloud_speech.SpeechAdaptation | None:
if is_given(self.keywords):
Expand Down Expand Up @@ -113,6 +114,7 @@ def __init__(
credentials_file: NotGivenOr[str] = NOT_GIVEN,
keywords: NotGivenOr[list[tuple[str, float]]] = NOT_GIVEN,
use_streaming: NotGivenOr[bool] = NOT_GIVEN,
denoiser_config: NotGivenOr[cloud_speech.DenoiserConfig] = NOT_GIVEN,
):
"""
Create a new instance of Google STT.
Expand All @@ -139,6 +141,7 @@ def __init__(
credentials_file(str): the credentials file to use for recognition (default: None)
keywords(List[tuple[str, float]]): list of keywords to recognize (default: None)
use_streaming(bool): whether to use streaming for recognition (default: True)
denoiser_config(DenoiserConfig): configuration for audio denoising (default: None)
"""
if not is_given(use_streaming):
use_streaming = True
Expand Down Expand Up @@ -176,6 +179,7 @@ def __init__(
sample_rate=sample_rate,
min_confidence_threshold=min_confidence_threshold,
keywords=keywords,
denoiser_config=denoiser_config,
)
self._streams = weakref.WeakSet[SpeechStream]()
self._pool = utils.ConnectionPool[SpeechAsyncClient](
Expand Down Expand Up @@ -265,6 +269,7 @@ async def _recognize_impl(
),
model=config.model,
language_codes=config.languages,
denoiser_config=config.denoiser_config,
)

try:
Expand Down Expand Up @@ -516,6 +521,7 @@ async def process_stream(
enable_word_time_offsets=self._config.enable_word_time_offsets,
enable_spoken_punctuation=self._config.spoken_punctuation,
),
denoiser_config=self._config.denoiser_config,
),
streaming_features=cloud_speech.StreamingRecognitionFeatures(
interim_results=self._config.interim_results,
Expand Down
Loading