Merge pull request #1011 from Vaibhav159/vl_deepgram_metrics_without_vad

adding metric generation without deepgram VAD

CHANGELOG.md

@@ -89,6 +89,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
   `UserStoppedSpeakingFrame`. This helps in faster transcriptions and clearing
   the `Deepgram` audio buffer.
 
+- Changed `DeepgramSTTService` to generate metrics using pipeline VAD.
+
 ### Fixed
 
 - Fixed `UserIdleProcessor` not properly propagating `EndFrame`s through the

src/pipecat/services/deepgram.py

@@ -20,6 +20,7 @@ from pipecat.frames.frames import (
     TTSAudioRawFrame,
     TTSStartedFrame,
     TTSStoppedFrame,
+    UserStartedSpeakingFrame,
     UserStoppedSpeakingFrame,
 )
 from pipecat.processors.frame_processor import FrameDirection
@@ -169,7 +170,7 @@ class DeepgramSTTService(STTService):
         return self._settings["vad_events"]
 
     def can_generate_metrics(self) -> bool:
-        return self.vad_enabled
+        return True
 
     async def set_model(self, model: str):
         await super().set_model(model)
@@ -210,9 +211,12 @@ class DeepgramSTTService(STTService):
             logger.debug("Disconnecting from Deepgram")
             await self._connection.finish()
 
-    async def _on_speech_started(self, *args, **kwargs):
+    async def start_metrics(self):
         await self.start_ttfb_metrics()
         await self.start_processing_metrics()
+
+    async def _on_speech_started(self, *args, **kwargs):
+        await self.start_metrics()
         await self._call_event_handler("on_speech_started", *args, **kwargs)
 
     async def _on_utterance_end(self, *args, **kwargs):
@@ -243,7 +247,10 @@ class DeepgramSTTService(STTService):
     async def process_frame(self, frame: Frame, direction: FrameDirection):
         await super().process_frame(frame, direction)
 
-        if isinstance(frame, UserStoppedSpeakingFrame):
+        if isinstance(frame, UserStartedSpeakingFrame) and not self.vad_enabled:
+            # Start metrics if Deepgram VAD is disabled & pipeline VAD has detected speech
+            await self.start_metrics()
+        elif isinstance(frame, UserStoppedSpeakingFrame):
             # https://developers.deepgram.com/docs/finalize
             await self._connection.finalize()
-            logger.debug(f"Triggering finalize event on: {frame.name=}, {direction=}")
+            logger.trace(f"Triggered finalize event on: {frame.name=}, {direction=}")