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

Revert "Add new GPT-4o transcription option to OpenAIRealtimeBetaLLMService"

Browse Source
This commit is contained in:
kompfner
2025-03-17 12:36:31 -04:00
committed by Paul Kompfner
parent be2cf6d556
commit fe5fc30211
5 changed files with 9 additions and 20 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
examples/foundational/19-openai-realtime-beta.py
View File

@@ -21,7 +21,7 @@ from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineParams, PipelineTask
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
from pipecat.services.openai_realtime_beta import (
InputAudioTranscriptionModels,
InputAudioTranscription,
OpenAIRealtimeBetaLLMService,
SessionProperties,
TurnDetection,
@@ -89,7 +89,7 @@ async def main():
)
session_properties = SessionProperties(
input_audio_transcription=InputAudioTranscriptionModels.Whisper1(),
input_audio_transcription=InputAudioTranscription(),
# Set openai TurnDetection parameters. Not setting this at all will turn it
# on by default
turn_detection=TurnDetection(silence_duration_ms=1000),

4
examples/foundational/19a-azure-realtime-beta.py
View File

@@ -23,7 +23,7 @@ from pipecat.pipeline.task import PipelineParams, PipelineTask
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
from pipecat.services.openai_realtime_beta import (
AzureRealtimeBetaLLMService,
InputAudioTranscriptionModels,
InputAudioTranscription,
SessionProperties,
TurnDetection,
)
@@ -90,7 +90,7 @@ async def main():
)
session_properties = SessionProperties(
input_audio_transcription=InputAudioTranscriptionModels.Whisper1(),
input_audio_transcription=InputAudioTranscription(),
# Set openai TurnDetection parameters. Not setting this at all will turn it
# on by default
# turn_detection=TurnDetection(silence_duration_ms=1000),

4
examples/foundational/20b-persistent-context-openai-realtime.py
View File

@@ -25,7 +25,7 @@ from pipecat.processors.aggregators.openai_llm_context import (
OpenAILLMContext,
)
from pipecat.services.openai_realtime_beta import (
InputAudioTranscriptionModels,
InputAudioTranscription,
OpenAIRealtimeBetaLLMService,
SessionProperties,
TurnDetection,
@@ -186,7 +186,7 @@ async def main():
)
session_properties = SessionProperties(
input_audio_transcription=InputAudioTranscriptionModels.Whisper1(),
input_audio_transcription=InputAudioTranscription(),
# Set openai TurnDetection parameters. Not setting this at all will turn it
# on by default
turn_detection=TurnDetection(silence_duration_ms=1000),

2
src/pipecat/services/openai_realtime_beta/__init__.py
View File

@@ -1,3 +1,3 @@
from .azure import AzureRealtimeBetaLLMService
from .events import InputAudioTranscriptionModels, SessionProperties, TurnDetection
from .events import InputAudioTranscription, SessionProperties, TurnDetection
from .openai import OpenAIRealtimeBetaLLMService

15
src/pipecat/services/openai_realtime_beta/events.py
View File

@@ -16,19 +16,8 @@ from pydantic import BaseModel, Field
#
class InputAudioTranscriptionModels:
class Whisper1(BaseModel):
model: Optional[Literal["whisper-1"]] = "whisper-1"
class GPT4o(BaseModel):
model: Optional[Literal["gpt-4o-transcribe-latest"]] = "gpt-4o-transcribe-latest"
language: Optional[str] = None
prompt: Optional[str] = None
InputAudioTranscription = Union[
InputAudioTranscriptionModels.Whisper1, InputAudioTranscriptionModels.GPT4o
]
class InputAudioTranscription(BaseModel):
model: Optional[str] = "whisper-1"
class TurnDetection(BaseModel):