Merge pull request #1680 from pipecat-ai/aleix/local-input-select-stt-update

examples: update local-input-select-stt

.gitignore

@@ -7,7 +7,7 @@ venv
 /.idea
 #*#
 
-# Distribution / packaging
+# Distribution / Packaging
 .Python
 build/
 develop-eggs/
@@ -30,24 +30,24 @@ MANIFEST
 .env
 fly.toml
 
-# Example files
+# Examples
-pipecat/examples/twilio-chatbot/templates/streams.xml
+examples/telnyx-chatbot/templates/streams.xml
-pipecat/examples/bot-ready-signalling/client/react-native/node_modules/
+examples/twilio-chatbot/templates/streams.xml
-pipecat/examples/bot-ready-signalling/client/react-native/.expo/
+examples/**/node_modules/
-pipecat/examples/bot-ready-signalling/client/react-native/dist/
+examples/**/.expo/
-pipecat/examples/bot-ready-signalling/client/react-native/npm-debug.*
+examples/**/dist/
-pipecat/examples/bot-ready-signalling/client/react-native/*.jks
+examples/**/npm-debug.*
-pipecat/examples/bot-ready-signalling/client/react-native/*.p8
+examples/**/*.jks
-pipecat/examples/bot-ready-signalling/client/react-native/*.p12
+examples/**/*.p8
-pipecat/examples/bot-ready-signalling/client/react-native/*.key
+examples/**/*.p12
-pipecat/examples/bot-ready-signalling/client/react-native/*.mobileprovision
+examples/**/*.key
-pipecat/examples/bot-ready-signalling/client/react-native/*.orig.*
+examples/**/*.mobileprovision
-pipecat/examples/bot-ready-signalling/client/react-native/web-build/
+examples/**/*.orig.*
+examples/**/web-build/
 
 # macOS
 .DS_Store
 
-
 # Documentation
 docs/api/_build/
 docs/api/api

examples/local-input-select-stt/bot.py

@@ -12,11 +12,10 @@ from dotenv import load_dotenv
 from loguru import logger
 from select_audio_device import AudioDevice, run_device_selector
 
-from pipecat.frames.frames import Frame, TranscriptionFrame
+from pipecat.observers.loggers.transcription_log_observer import TranscriptionLogObserver
 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.whisper.stt import Model, WhisperSTTService
 from pipecat.transports.local.audio import LocalAudioTransport, LocalAudioTransportParams
 
@@ -26,14 +25,6 @@ logger.remove(0)
 logger.add(sys.stderr, level="DEBUG")
 
 
-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}")
-
-
 async def main(input_device: int, output_device: int):
     transport = LocalAudioTransport(
         LocalAudioTransportParams(
@@ -46,11 +37,9 @@ async def main(input_device: int, output_device: int):
 
     stt = WhisperSTTService(device="cuda", model=Model.LARGE, no_speech_prob=0.3)
 
-    tl = TranscriptionLogger()
+    pipeline = Pipeline([transport.input(), stt])
 
-    pipeline = Pipeline([transport.input(), stt, tl])
+    task = PipelineTask(pipeline, observers=[TranscriptionLogObserver()])
-
-    task = PipelineTask(pipeline)
 
     runner = PipelineRunner(handle_sigint=False if sys.platform == "win32" else True)
 

examples/local-input-select-stt/requirements.txt

@@ -1,8 +1,4 @@
---extra-index-url https://download.pytorch.org/whl/cu124
+pipecat-ai[whisper, openai]
-torch==2.5.0+cu124
-torchvision 
-torchaudio
-pipecat[whisper, openai]
 textual==1.0.0
 pydantic-settings==2.7.1
 pyaudio==0.2.14

examples/local-input-select-stt/select_audio_device.py

@@ -1,3 +1,9 @@
+#
+# Copyright (c) 2024–2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
 from typing import List, Optional, Tuple
 
 import pyaudio