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

Add param to push empty transcripts

Browse Source
This commit is contained in:
Daksh Dua
2026-03-05 14:25:31 -08:00
parent 671ef5b6cc
commit 789ce2fd5e
2 changed files with 13 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
changelog/3930.added.md Normal file
View File

@@ -0,0 +1 @@
- Added `push_empty_transcripts` parameter to `BaseWhisperSTTService` and `OpenAISTTService` to allow empty transcripts to be pushed downstream as `TranscriptionFrame` instead of discarding them (the default behavior). This is intended for situations where VAD fires even though the user did not speak. In these cases, it is useful to know that nothing was transcribed so that the agent can resume speaking, instead of waiting longer for a transcription.

15
src/pipecat/services/whisper/base_stt.py
View File

@@ -136,6 +136,7 @@ class BaseWhisperSTTService(SegmentedSTTService):
prompt: Optional[str] = None, prompt: Optional[str] = None,
temperature: Optional[float] = None, temperature: Optional[float] = None,
include_prob_metrics: bool = False, include_prob_metrics: bool = False,
push_empty_transcripts: bool = False,
ttfs_p99_latency: Optional[float] = WHISPER_TTFS_P99, ttfs_p99_latency: Optional[float] = WHISPER_TTFS_P99,
**kwargs, **kwargs,
): ):
@@ -151,6 +152,12 @@ class BaseWhisperSTTService(SegmentedSTTService):
include_prob_metrics: If True, enables probability metrics in API response. include_prob_metrics: If True, enables probability metrics in API response.
Each service implements this differently (see child classes). Each service implements this differently (see child classes).
Defaults to False. Defaults to False.
push_empty_transcripts: - If true, allow empty `TranscriptionFrame` frames to be
pushed downstream instead of discarding them. This is intended for situations
where VAD fires even though the user did not speak. In these cases, it is
useful to know that nothing was transcribed so that the agent can resume
speaking, instead of waiting longer for a transcription.
Defaults to False.
ttfs_p99_latency: P99 latency from speech end to final transcript in seconds. ttfs_p99_latency: P99 latency from speech end to final transcript in seconds.
Override for your deployment. See https://github.com/pipecat-ai/stt-benchmark Override for your deployment. See https://github.com/pipecat-ai/stt-benchmark
**kwargs: Additional arguments passed to SegmentedSTTService. **kwargs: Additional arguments passed to SegmentedSTTService.
@@ -171,6 +178,7 @@ class BaseWhisperSTTService(SegmentedSTTService):
self._prompt = prompt self._prompt = prompt
self._temperature = temperature self._temperature = temperature
self._include_prob_metrics = include_prob_metrics self._include_prob_metrics = include_prob_metrics
self._push_empty_transcripts = push_empty_transcripts
def _create_client(self, api_key: Optional[str], base_url: Optional[str]): def _create_client(self, api_key: Optional[str], base_url: Optional[str]):
return AsyncOpenAI(api_key=api_key, base_url=base_url) return AsyncOpenAI(api_key=api_key, base_url=base_url)
@@ -237,7 +245,10 @@ class BaseWhisperSTTService(SegmentedSTTService):
text = response.text.strip() text = response.text.strip()
if text: if not text:
logger.warning("Received empty transcription from API")
if text or self._push_empty_transcripts:
await self._handle_transcription(text, True, self._language) await self._handle_transcription(text, True, self._language)
logger.debug(f"Transcription: [{text}]") logger.debug(f"Transcription: [{text}]")
yield TranscriptionFrame( yield TranscriptionFrame(
@@ -246,8 +257,6 @@ class BaseWhisperSTTService(SegmentedSTTService):
time_now_iso8601(), time_now_iso8601(),
result=response, result=response,
) )
else:
logger.warning("Received empty transcription from API")
except Exception as e: except Exception as e:
yield ErrorFrame(error=f"Unknown error occurred: {e}") yield ErrorFrame(error=f"Unknown error occurred: {e}")