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

examples: use SileroVADAnalyzer instead of SileroVAD

Browse Source
This commit is contained in:
Aleix Conchillo Flaqué
2024-05-17 14:16:05 -07:00
parent 34762bf604
commit d66a795413
5 changed files with 20 additions and 25 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
examples/foundational/06-listen-and-respond.py
View File

@@ -21,7 +21,7 @@ from pipecat.processors.logger import FrameLogger
from pipecat.services.elevenlabs import ElevenLabsTTSService
from pipecat.services.openai import OpenAILLMService
from pipecat.transports.services.daily import DailyParams, DailyTransport
from pipecat.vad.silero import SileroVAD
from pipecat.vad.silero import SileroVADAnalyzer
from runner import configure
@@ -41,14 +41,13 @@ async def main(room_url: str, token):
token,
"Respond bot",
DailyParams(
audio_in_enabled=True, # This is so Silero VAD can get audio data
audio_out_enabled=True,
transcription_enabled=True
transcription_enabled=True,
vad_enabled=True,
vad_analyzer=SileroVADAnalyzer()
)
)
vad = SileroVAD()
tts = ElevenLabsTTSService(
aiohttp_session=session,
api_key=os.getenv("ELEVENLABS_API_KEY"),
@@ -71,7 +70,7 @@ async def main(room_url: str, token):
tma_in = LLMUserResponseAggregator(messages)
tma_out = LLMAssistantResponseAggregator(messages)
pipeline = Pipeline([fl_in, transport.input(), vad, tma_in, llm,
pipeline = Pipeline([fl_in, transport.input(), tma_in, llm,
fl_out, tts, tma_out, transport.output()])
task = PipelineTask(pipeline)

1
examples/foundational/07-interruptible.py
View File

@@ -38,7 +38,6 @@ async def main(room_url: str, token):
token,
"Respond bot",
DailyParams(
audio_in_enabled=True,
audio_out_enabled=True,
transcription_enabled=True,
vad_enabled=True,

11
examples/foundational/12-describe-video.py
View File

@@ -19,7 +19,7 @@ from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
from pipecat.services.elevenlabs import ElevenLabsTTSService
from pipecat.services.moondream import MoondreamService
from pipecat.transports.services.daily import DailyParams, DailyTransport
from pipecat.vad.silero import SileroVAD
from pipecat.vad.silero import SileroVADAnalyzer
from runner import configure
@@ -54,14 +54,13 @@ async def main(room_url: str, token):
token,
"Describe participant video",
DailyParams(
audio_in_enabled=True, # This is so Silero VAD can get audio data
audio_out_enabled=True,
transcription_enabled=True
transcription_enabled=True,
vad_enabled=True,
vad_analyzer=SileroVADAnalyzer()
)
)
vad = SileroVAD()
tts = ElevenLabsTTSService(
aiohttp_session=session,
api_key=os.getenv("ELEVENLABS_API_KEY"),
@@ -90,7 +89,7 @@ async def main(room_url: str, token):
transport.capture_participant_transcription(participant["id"])
image_requester.set_participant_id(participant["id"])
pipeline = Pipeline([transport.input(), vad, user_response, image_requester,
pipeline = Pipeline([transport.input(), user_response, image_requester,
vision_aggregator, moondream, tts, transport.output()])
task = PipelineTask(pipeline)

11
examples/moondream-chatbot/bot.py
View File

@@ -29,7 +29,7 @@ from pipecat.services.elevenlabs import ElevenLabsTTSService
from pipecat.services.moondream import MoondreamService
from pipecat.services.openai import OpenAILLMService
from pipecat.transports.services.daily import DailyParams, DailyTransport
from pipecat.vad.silero import SileroVAD
from pipecat.vad.silero import SileroVADAnalyzer
from runner import configure
@@ -127,17 +127,16 @@ async def main(room_url: str, token):
token,
"Chatbot",
DailyParams(
audio_in_enabled=True,
audio_out_enabled=True,
camera_out_enabled=True,
camera_out_width=1024,
camera_out_height=576,
transcription_enabled=True
transcription_enabled=True,
vad_enabled=True,
vad_analyzer=SileroVADAnalyzer()
)
)
vad = SileroVAD()
tts = ElevenLabsTTSService(
aiohttp_session=session,
api_key=os.getenv("ELEVENLABS_API_KEY"),
@@ -169,7 +168,7 @@ async def main(room_url: str, token):
ura = LLMUserResponseAggregator(messages)
pipeline = Pipeline([transport.input(), vad, ura, llm,
pipeline = Pipeline([transport.input(), ura, llm,
ParallelPipeline(
[sa, ir, va, moondream],
[tf, imgf]),

11
examples/simple-chatbot/bot.py
View File

@@ -21,7 +21,7 @@ from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
from pipecat.services.elevenlabs import ElevenLabsTTSService
from pipecat.services.openai import OpenAILLMService
from pipecat.transports.services.daily import DailyParams, DailyTranscriptionSettings, DailyTransport
from pipecat.vad.silero import SileroVAD
from pipecat.vad.silero import SileroVADAnalyzer
from runner import configure
@@ -82,11 +82,12 @@ async def main(room_url: str, token):
token,
"Chatbot",
DailyParams(
audio_in_enabled=True,
audio_out_enabled=True,
camera_out_enabled=True,
camera_out_width=1024,
camera_out_height=576,
vad_enabled=True,
vad_analyzer=SileroVADAnalyzer(),
transcription_enabled=True,
#
# Spanish
@@ -99,8 +100,6 @@ async def main(room_url: str, token):
)
)
vad = SileroVAD()
tts = ElevenLabsTTSService(
aiohttp_session=session,
api_key=os.getenv("ELEVENLABS_API_KEY"),
@@ -139,10 +138,10 @@ async def main(room_url: str, token):
ta = TalkingAnimation()
pipeline = Pipeline([transport.input(), vad, user_response,
pipeline = Pipeline([transport.input(), user_response,
llm, tts, ta, transport.output()])
task = PipelineTask(pipeline)
task = PipelineTask(pipeline, allow_interruptions=True)
await task.queue_frame(quiet_frame)
@transport.event_handler("on_first_participant_joined")