Speechmatics STT + multi-speaker conversations (#2036)
* initial config * skeleton * Added a README (to be added to). * Payloads coming from the ASR. * doc update * handle the partials and finals * enable diarization in the example * support sending messages to pipecat pipeline * requirements fix in README * updated example (with amusement) * updated example to match master * updated docs * support for diarization tags * logic fix for wrapper * Use an internal SpeechFrame for speaker_id (not user_id). * only include speaker tags on finalised transcript (as this may skew end of utterance detection) * updated docs * correction to docs and updated example * updated requirement * Fix for using default EU server. * Updates from PR comments. * Refactor based on comments in the original PR. Primary focus on documentation, naming conventions and how `user_id` is used. * Check for SMX installed when importing. * Variable name change * Comment correction. * Support for Esporanto and Uyghur * Impoved language support * function name change * Locale fix * intercept * interim changes * pass the pipeline task to the module for adding events to the top of the pipeline * logging for the pipeline * Reduce timeout for content aggregator. * staged update * testing with Azure * Updated context (Azure was dropping punctuation) and using better ElevenLabs model. * Updated to RT 0.3.0 and use OpenAI (not Azure). * Missing OpenAI import; parameter name change for output locale validation. * Revert to `0.2.0` of RT SDK. * fix for assignment of `output_locale_code`. * update Speechmatics library to 0.3.1 * new transcription example * updated asyncio task handling * Updated doc strings * enable OpenTelemetry logging * removed import from stt for __init__ * updated examples and default values * updated examples * prevent lock up when closing the STT connection
This commit is contained in:
Sam Sykes
153
examples/foundational/07a-interruptible-speechmatics.py
Normal file
153
examples/foundational/07a-interruptible-speechmatics.py
Normal file
@@ -0,0 +1,153 @@
|
||||
#
|
||||
# Copyright (c) 2024–2025, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
import argparse
|
||||
import os
|
||||
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.llm_response import (
|
||||
LLMUserAggregatorParams,
|
||||
)
|
||||
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
|
||||
from pipecat.services.elevenlabs.tts import ElevenLabsTTSService
|
||||
from pipecat.services.openai.base_llm import BaseOpenAILLMService
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.services.speechmatics.stt import SpeechmaticsSTTService
|
||||
from pipecat.transcriptions.language import Language
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
|
||||
from pipecat.transports.services.daily import DailyParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
# We store functions so objects (e.g. SileroVADAnalyzer) don't get
|
||||
# instantiated. The function will be called when the desired transport gets
|
||||
# selected.
|
||||
transport_params = {
|
||||
"daily": lambda: DailyParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_sigint: bool):
|
||||
"""Run example using Speechmatics STT.
|
||||
|
||||
This example will use diarization within our STT service and output the words spoken by
|
||||
each individual speaker and wrap them with XML tags for the LLM to process. Note the
|
||||
instructions in the system context for the LLM. This greatly improves the conversation
|
||||
experience by allowing the LLM to understand who is speaking in a multi-party call.
|
||||
|
||||
If you do not wish to use diarization, then set the `enable_speaker_diarization` parameter
|
||||
to `False` or omit it altogether. The `text_format` will only be used if diarization is enabled.
|
||||
|
||||
By default, this example will use our ENHANCED operating point, which is optimized for
|
||||
high accuracy. You can change this by setting the `operating_point` parameter to a different
|
||||
value.
|
||||
|
||||
For more information on operating points, see the Speechmatics documentation:
|
||||
https://docs.speechmatics.com/rt-api-ref
|
||||
"""
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
stt = SpeechmaticsSTTService(
|
||||
api_key=os.getenv("SPEECHMATICS_API_KEY"),
|
||||
language=Language.EN,
|
||||
enable_speaker_diarization=True,
|
||||
text_format="<{speaker_id}>{text}</{speaker_id}>",
|
||||
)
|
||||
|
||||
tts = ElevenLabsTTSService(
|
||||
api_key=os.getenv("ELEVENLABS_API_KEY", ""),
|
||||
voice_id=os.getenv("ELEVENLABS_VOICE_ID", ""),
|
||||
model="eleven_turbo_v2_5",
|
||||
)
|
||||
|
||||
llm = OpenAILLMService(
|
||||
api_key=os.getenv("OPENAI_API_KEY"),
|
||||
params=BaseOpenAILLMService.InputParams(temperature=0.75),
|
||||
)
|
||||
|
||||
messages = [
|
||||
{
|
||||
"role": "system",
|
||||
"content": (
|
||||
"You are a helpful British assistant called Alfred. "
|
||||
"Your goal is to demonstrate your capabilities in a succinct way. "
|
||||
"Your output will be converted to audio so don't include special characters in your answers. "
|
||||
"Always include punctuation in your responses. "
|
||||
"Give very short replies - do not give longer replies unless strictly necessary. "
|
||||
"Respond to what the user said in a concise, funny, creative and helpful way. "
|
||||
"Use `<Sn/>` tags to identify different speakers - do not use tags in your replies."
|
||||
),
|
||||
},
|
||||
]
|
||||
|
||||
context = OpenAILLMContext(messages)
|
||||
context_aggregator = llm.create_context_aggregator(
|
||||
context,
|
||||
user_params=LLMUserAggregatorParams(aggregation_timeout=0.005),
|
||||
)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(), # Transport user input
|
||||
stt, # STT
|
||||
context_aggregator.user(), # User responses
|
||||
llm, # LLM
|
||||
tts, # TTS
|
||||
transport.output(), # Transport bot output
|
||||
context_aggregator.assistant(), # Assistant spoken responses
|
||||
]
|
||||
)
|
||||
|
||||
task = PipelineTask(
|
||||
pipeline,
|
||||
params=PipelineParams(
|
||||
enable_metrics=True,
|
||||
enable_usage_metrics=True,
|
||||
),
|
||||
)
|
||||
|
||||
@transport.event_handler("on_client_connected")
|
||||
async def on_client_connected(transport, client):
|
||||
logger.info(f"Client connected")
|
||||
# Kick off the conversation.
|
||||
messages.append({"role": "system", "content": "Say a short hello to the user."})
|
||||
await task.queue_frames([context_aggregator.user().get_context_frame()])
|
||||
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
logger.info(f"Client disconnected")
|
||||
await task.cancel()
|
||||
|
||||
runner = PipelineRunner(handle_sigint=handle_sigint)
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
from pipecat.examples.run import main
|
||||
|
||||
main(run_example, transport_params=transport_params)
|
||||
89
examples/foundational/13h-speechmatics-transcription.py
Normal file
89
examples/foundational/13h-speechmatics-transcription.py
Normal file
@@ -0,0 +1,89 @@
|
||||
#
|
||||
# Copyright (c) 2024–2025, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
import argparse
|
||||
import os
|
||||
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.frames.frames import Frame, TranscriptionFrame
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineTask
|
||||
from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
|
||||
from pipecat.services.speechmatics.stt import SpeechmaticsSTTService
|
||||
from pipecat.transcriptions.language import Language
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
|
||||
from pipecat.transports.services.daily import DailyParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
|
||||
class TranscriptionLogger(FrameProcessor):
|
||||
async def process_frame(self, frame: Frame, direction: FrameDirection):
|
||||
await super().process_frame(frame, direction)
|
||||
|
||||
if isinstance(frame, TranscriptionFrame):
|
||||
print(f"Transcription: {frame.text}")
|
||||
|
||||
|
||||
# We store functions so objects (e.g. SileroVADAnalyzer) don't get
|
||||
# instantiated. The function will be called when the desired transport gets
|
||||
# selected.
|
||||
transport_params = {
|
||||
"daily": lambda: DailyParams(audio_in_enabled=True),
|
||||
"twilio": lambda: FastAPIWebsocketParams(audio_in_enabled=True),
|
||||
"webrtc": lambda: TransportParams(audio_in_enabled=True),
|
||||
}
|
||||
|
||||
|
||||
async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_sigint: bool):
|
||||
"""Run example using Speechmatics STT.
|
||||
|
||||
This example will use diarization within our STT service and output the words spoken by
|
||||
each individual speaker and wrap them with XML tags.
|
||||
|
||||
If you do not wish to use diarization, then set the `enable_speaker_diarization` parameter
|
||||
to `False` or omit it altogether. The `text_format` will only be used if diarization is enabled.
|
||||
|
||||
By default, this example will use our ENHANCED operating point, which is optimized for
|
||||
high accuracy. You can change this by setting the `operating_point` parameter to a different
|
||||
value.
|
||||
|
||||
For more information on operating points, see the Speechmatics documentation:
|
||||
https://docs.speechmatics.com/rt-api-ref
|
||||
"""
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
stt = SpeechmaticsSTTService(
|
||||
api_key=os.getenv("SPEECHMATICS_API_KEY"),
|
||||
language=Language.EN,
|
||||
enable_speaker_diarization=True,
|
||||
text_format="<{speaker_id}>{text}</{speaker_id}>",
|
||||
)
|
||||
|
||||
tl = TranscriptionLogger()
|
||||
|
||||
pipeline = Pipeline([transport.input(), stt, tl])
|
||||
|
||||
task = PipelineTask(pipeline)
|
||||
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
logger.info(f"Client disconnected")
|
||||
await task.cancel()
|
||||
|
||||
runner = PipelineRunner(handle_sigint=handle_sigint)
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
from pipecat.examples.run import main
|
||||
|
||||
main(run_example, transport_params=transport_params)
|
||||
Reference in New Issue
Block a user