wx44wx/pipecat
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Suppress UserStartedSpeakingFrame and UserStoppedSpeakingFrame when muted

Browse Source
This commit is contained in:
Mark Backman
2024-11-14 17:11:51 -05:00
parent 33108f5798
commit f807f233bd
2 changed files with 15 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
examples/foundational/24-stt-mute-processor.py
View File

@@ -51,7 +51,7 @@ async def main():
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY")) stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
# Configure the mute processor to mute only during first speech # Configure the mute processor to mute only during first speech
stt_mute_processor = STTMuteProcessor( stt_mute_processor = STTMuteProcessor(
stt_service=stt, config=STTMuteConfig(strategy=STTMuteStrategy.ALWAYS) stt_service=stt, config=STTMuteConfig(strategy=STTMuteStrategy.FIRST_SPEECH)
) )
tts = DeepgramTTSService(api_key=os.getenv("DEEPGRAM_API_KEY"), voice="aura-helios-en") tts = DeepgramTTSService(api_key=os.getenv("DEEPGRAM_API_KEY"), voice="aura-helios-en")

18
src/pipecat/processors/filters/stt_mute.py
View File

@@ -17,6 +17,8 @@ from pipecat.frames.frames import (
StartInterruptionFrame, StartInterruptionFrame,
StopInterruptionFrame, StopInterruptionFrame,
STTMuteFrame, STTMuteFrame,
UserStartedSpeakingFrame,
UserStoppedSpeakingFrame,
) )
from pipecat.processors.frame_processor import FrameDirection, FrameProcessor from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
from pipecat.services.ai_services import STTService from pipecat.services.ai_services import STTService
@@ -60,7 +62,7 @@ class STTMuteProcessor(FrameProcessor):
async def _handle_mute_state(self, should_mute: bool): async def _handle_mute_state(self, should_mute: bool):
"""Handles both STT muting and interruption control.""" """Handles both STT muting and interruption control."""
if should_mute != self.is_muted: if should_mute != self.is_muted:
logger.info(f"STT {'muting' if should_mute else 'unmuting'}") logger.debug(f"STT {'muting' if should_mute else 'unmuting'}")
await self.push_frame(STTMuteFrame(mute=should_mute)) await self.push_frame(STTMuteFrame(mute=should_mute))
async def _should_mute(self) -> bool: async def _should_mute(self) -> bool:
@@ -90,12 +92,20 @@ class STTMuteProcessor(FrameProcessor):
await self._handle_mute_state(await self._should_mute()) await self._handle_mute_state(await self._should_mute())
# Handle frame propagation # Handle frame propagation
if isinstance(frame, (StartInterruptionFrame, StopInterruptionFrame)): if isinstance(
# Only pass interruption frames when not muted frame,
(
StartInterruptionFrame,
StopInterruptionFrame,
UserStartedSpeakingFrame,
UserStoppedSpeakingFrame,
),
):
# Only pass VAD-related frames when not muted
if not self.is_muted: if not self.is_muted:
await self.push_frame(frame, direction) await self.push_frame(frame, direction)
else: else:
logger.debug("Interruption frame suppressed - STT currently muted") logger.debug(f"{frame.__class__.__name__} suppressed - STT currently muted")
else: else:
# Pass all other frames through # Pass all other frames through
await self.push_frame(frame, direction) await self.push_frame(frame, direction)