From 5100a7599b88605df88ab6afa402b10a5e62c93f Mon Sep 17 00:00:00 2001 From: Chad Bailey Date: Thu, 22 Feb 2024 16:14:36 -0600 Subject: [PATCH] 0.5s VAD is interesting --- src/dailyai/services/base_transport_service.py | 2 +- src/dailyai/services/open_ai_services.py | 2 +- .../foundational/06c-listen-respond-interruptible-refactor.py | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) diff --git a/src/dailyai/services/base_transport_service.py b/src/dailyai/services/base_transport_service.py index c155425be..f3dab7132 100644 --- a/src/dailyai/services/base_transport_service.py +++ b/src/dailyai/services/base_transport_service.py @@ -94,7 +94,7 @@ class BaseTransportService(): self._speaker_sample_rate = kwargs.get("speaker_sample_rate") or 16000 self._fps = kwargs.get("fps") or 8 self._vad_start_s = kwargs.get("vad_start_s") or 0.2 - self._vad_stop_s = kwargs.get("vad_stop_s") or 1.2 + self._vad_stop_s = kwargs.get("vad_stop_s") or 0.5 self._context = kwargs.get("context") or [] self._vad_samples = 1536 diff --git a/src/dailyai/services/open_ai_services.py b/src/dailyai/services/open_ai_services.py index 7cb89c91c..9a6a7cf2c 100644 --- a/src/dailyai/services/open_ai_services.py +++ b/src/dailyai/services/open_ai_services.py @@ -10,7 +10,7 @@ from dailyai.services.ai_services import LLMService, ImageGenService class OpenAILLMService(LLMService): - def __init__(self, *, api_key, model="gpt-4", context): + def __init__(self, *, api_key, model="gpt-4-turbo-preview", context): super().__init__(context) self._model = model self._client = AsyncOpenAI(api_key=api_key) diff --git a/src/examples/foundational/06c-listen-respond-interruptible-refactor.py b/src/examples/foundational/06c-listen-respond-interruptible-refactor.py index 22d0e783e..db6c38c31 100644 --- a/src/examples/foundational/06c-listen-respond-interruptible-refactor.py +++ b/src/examples/foundational/06c-listen-respond-interruptible-refactor.py @@ -43,7 +43,7 @@ async def main(room_url: str, token): # context=context) llm = OpenAILLMService( context=context, api_key=os.getenv("OPENAI_CHATGPT_API_KEY")) - llm = GroqLLMService(api_key=os.getenv("GROQ_API_KEY"), context=context) + # llm = GroqLLMService(api_key=os.getenv("GROQ_API_KEY"), context=context) tts = AzureTTSService( api_key=os.getenv("AZURE_SPEECH_API_KEY"), region=os.getenv("AZURE_SPEECH_REGION"))