From b4340d01858594fd771a4888c65060c8a0a59d3d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Aleix=20Conchillo=20Flaqu=C3=A9?= Date: Thu, 6 Jun 2024 23:39:44 -0700 Subject: [PATCH] services(whisper): increase no speech probability to 0.4 --- src/pipecat/services/whisper.py | 2 +- src/pipecat/transports/base_input.py | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/src/pipecat/services/whisper.py b/src/pipecat/services/whisper.py index 6c5dd0d1f..1f3bda5b8 100644 --- a/src/pipecat/services/whisper.py +++ b/src/pipecat/services/whisper.py @@ -45,7 +45,7 @@ class WhisperSTTService(STTService): model: Model = Model.DISTIL_MEDIUM_EN, device: str = "auto", compute_type: str = "default", - no_speech_prob: float = 0.1, + no_speech_prob: float = 0.4, **kwargs): super().__init__(**kwargs) diff --git a/src/pipecat/transports/base_input.py b/src/pipecat/transports/base_input.py index 823ab5844..1162708cc 100644 --- a/src/pipecat/transports/base_input.py +++ b/src/pipecat/transports/base_input.py @@ -177,7 +177,7 @@ class BaseInputTransport(FrameProcessor): vad_state = self._handle_vad(frame.audio, vad_state) audio_passthrough = self._params.vad_audio_passthrough - # Push audio downstream if passthrough. + # Push audio downstream if passthrough. if audio_passthrough: future = asyncio.run_coroutine_threadsafe( self._internal_push_frame(frame), self._loop)