From 30cdcd8fba1a9d88a06f4f10f9326092d7be5579 Mon Sep 17 00:00:00 2001 From: "dingfeng.wong" Date: Wed, 23 Jul 2025 12:36:34 +0800 Subject: [PATCH] h --- .gitignore | 1 + pyproject.toml | 3 +- realtimesst.log | 1408 ++++++++++++++++++++++++++++++++++++++++ src/tooling/stt_cli.py | 32 +- test_realtime_stt.py | 19 + uv.lock | 2 + 6 files changed, 1451 insertions(+), 14 deletions(-) create mode 100644 realtimesst.log create mode 100755 test_realtime_stt.py diff --git a/.gitignore b/.gitignore index ad52012..91fe6a2 100644 --- a/.gitignore +++ b/.gitignore @@ -27,3 +27,4 @@ wheels/ /Users/wongdingfeng/.config/tooling/.env /Users/wongdingfeng/.config/tooling/.DS_Store /Users/wongdingfeng/.config/tooling/Thumbs.db +uv.lock diff --git a/pyproject.toml b/pyproject.toml index 4062c5d..fbd0760 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -13,8 +13,9 @@ dependencies = [ "python-doctr>=0.8.0", "typer>=0.12.0", "rich>=13.0.0", - "realtimestt>=0.3.104", "rumps>=0.4.0", + "realtimestt>=0.3.104", + "pyautogui>=0.9.54", ] [project.optional-dependencies] diff --git a/realtimesst.log b/realtimesst.log new file mode 100644 index 0000000..b04a81b --- /dev/null +++ b/realtimesst.log @@ -0,0 +1,1408 @@ +2025-07-23 11:25:44.427 - RealTimeSTT: realtimestt - INFO - Starting RealTimeSTT +2025-07-23 11:25:44.436 - RealTimeSTT: realtimestt - INFO - Initializing audio recording (creating pyAudio input stream, sample rate: 16000 buffer size: 512 +2025-07-23 11:25:44.442 - RealTimeSTT: realtimestt - INFO - Initializing faster_whisper realtime transcription model tiny, default device: cpu, compute type: default, device index: 0, download root: None +2025-07-23 11:25:45.375 - RealTimeSTT: realtimestt - DEBUG - Faster_whisper realtime speech to text transcription model initialized successfully +2025-07-23 11:25:45.448 - RealTimeSTT: realtimestt - INFO - Successfully loaded openwakeword model: alexa +2025-07-23 11:25:45.448 - RealTimeSTT: realtimestt - INFO - Successfully loaded openwakeword model: hey_mycroft +2025-07-23 11:25:45.448 - RealTimeSTT: realtimestt - INFO - Successfully loaded openwakeword model: hey_jarvis +2025-07-23 11:25:45.448 - RealTimeSTT: realtimestt - INFO - Successfully loaded openwakeword model: hey_rhasspy +2025-07-23 11:25:45.448 - RealTimeSTT: realtimestt - INFO - Successfully loaded openwakeword model: timer +2025-07-23 11:25:45.448 - RealTimeSTT: realtimestt - INFO - Successfully loaded openwakeword model: weather +2025-07-23 11:25:45.448 - RealTimeSTT: realtimestt - DEBUG - Open wake word detection engine initialized successfully +2025-07-23 11:25:45.448 - RealTimeSTT: realtimestt - INFO - Initializing WebRTC voice with Sensitivity 3 +2025-07-23 11:25:45.448 - RealTimeSTT: realtimestt - DEBUG - WebRTC VAD voice activity detection engine initialized successfully +2025-07-23 11:25:45.917 - RealTimeSTT: realtimestt - DEBUG - Silero VAD voice activity detection engine initialized successfully +2025-07-23 11:25:45.917 - RealTimeSTT: realtimestt - DEBUG - Starting realtime worker +2025-07-23 11:25:45.917 - RealTimeSTT: realtimestt - DEBUG - Waiting for main transcription model to start +2025-07-23 11:25:48.042 - RealTimeSTT: realtimestt - DEBUG - Main transcription model ready +2025-07-23 11:25:48.042 - RealTimeSTT: realtimestt - DEBUG - RealtimeSTT initialization completed successfully +2025-07-23 11:25:48.042 - RealTimeSTT: realtimestt - INFO - Setting listen time +2025-07-23 11:25:48.042 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'listening' +2025-07-23 11:25:48.043 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording start +2025-07-23 11:25:48.100 - RealTimeSTT: realtimestt - INFO - State changed from 'listening' to 'wakeword' +2025-07-23 11:26:02.947 - RealTimeSTT: realtimestt - INFO - State changed from 'wakeword' to 'listening' +2025-07-23 11:26:05.191 - RealTimeSTT: realtimestt - INFO - voice activity detected +2025-07-23 11:26:05.191 - RealTimeSTT: realtimestt - INFO - recording started +2025-07-23 11:26:05.191 - RealTimeSTT: realtimestt - INFO - State changed from 'listening' to 'recording' +2025-07-23 11:26:05.191 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording stop +2025-07-23 11:26:05.212 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 14848 +2025-07-23 11:26:05.398 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: Come on +2025-07-23 11:26:05.413 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 17920 +2025-07-23 11:26:05.591 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: Come on. +2025-07-23 11:26:05.614 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 20992 +2025-07-23 11:26:05.806 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: Come on. +2025-07-23 11:26:05.825 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 25088 +2025-07-23 11:26:06.009 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: Come on. +2025-07-23 11:26:06.026 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 28160 +2025-07-23 11:26:06.218 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: 今晚,謝謝 +2025-07-23 11:26:06.227 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 31232 +2025-07-23 11:26:06.422 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: 今晚謝謝身份 +2025-07-23 11:26:06.427 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 34304 +2025-07-23 11:26:06.614 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: 今晚謝謝你 +2025-07-23 11:26:07.170 - RealTimeSTT: realtimestt - INFO - recording stopped +2025-07-23 11:26:07.172 - RealTimeSTT: realtimestt - DEBUG - No samples removed, final audio length: 46080 +2025-07-23 11:26:07.172 - RealTimeSTT: realtimestt - INFO - State changed from 'recording' to 'inactive' +2025-07-23 11:26:07.208 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'transcribing' +2025-07-23 11:26:07.208 - RealTimeSTT: realtimestt - DEBUG - Adding transcription request, no early transcription started +2025-07-23 11:26:07.216 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 11:26:07.316 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 11:26:07.417 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 11:26:07.518 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 11:26:07.617 - RealTimeSTT: realtimestt - INFO - State changed from 'transcribing' to 'inactive' +2025-07-23 11:26:07.647 - RealTimeSTT: realtimestt - DEBUG - Model base completed transcription in 0.44 seconds +2025-07-23 11:26:07.647 - RealTimeSTT: realtimestt - INFO - Setting listen time +2025-07-23 11:26:07.647 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'listening' +2025-07-23 11:26:07.647 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording start +2025-07-23 11:26:10.628 - RealTimeSTT: realtimestt - INFO - voice activity detected +2025-07-23 11:26:10.628 - RealTimeSTT: realtimestt - INFO - recording started +2025-07-23 11:26:10.629 - RealTimeSTT: realtimestt - INFO - State changed from 'listening' to 'recording' +2025-07-23 11:26:10.629 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording stop +2025-07-23 11:26:10.633 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 16384 +2025-07-23 11:26:10.829 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: What? +2025-07-23 11:26:10.835 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 17408 +2025-07-23 11:26:11.006 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: What is +2025-07-23 11:26:11.035 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 20480 +2025-07-23 11:26:11.236 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: What did you say? +2025-07-23 11:26:11.236 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 23552 +2025-07-23 11:26:11.428 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: Why did you stop? +2025-07-23 11:26:11.969 - RealTimeSTT: realtimestt - INFO - recording stopped +2025-07-23 11:26:11.969 - RealTimeSTT: realtimestt - DEBUG - No samples removed, final audio length: 35328 +2025-07-23 11:26:11.969 - RealTimeSTT: realtimestt - INFO - State changed from 'recording' to 'inactive' +2025-07-23 11:26:12.025 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'transcribing' +2025-07-23 11:26:12.026 - RealTimeSTT: realtimestt - DEBUG - Adding transcription request, no early transcription started +2025-07-23 11:26:12.026 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 11:26:12.127 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 11:26:12.228 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 11:26:12.330 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 11:26:12.406 - RealTimeSTT: realtimestt - INFO - State changed from 'transcribing' to 'inactive' +2025-07-23 11:26:12.455 - RealTimeSTT: realtimestt - DEBUG - Model base completed transcription in 0.43 seconds +2025-07-23 11:26:12.455 - RealTimeSTT: realtimestt - INFO - Setting listen time +2025-07-23 11:26:12.455 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'listening' +2025-07-23 11:26:12.456 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording start +2025-07-23 11:29:06.457 - RealTimeSTT: realtimestt - INFO - Starting RealTimeSTT +2025-07-23 11:29:06.466 - RealTimeSTT: realtimestt - INFO - Initializing audio recording (creating pyAudio input stream, sample rate: 16000 buffer size: 512 +2025-07-23 11:29:06.471 - RealTimeSTT: realtimestt - INFO - Initializing faster_whisper realtime transcription model tiny, default device: cpu, compute type: default, device index: 0, download root: None +2025-07-23 11:29:07.272 - RealTimeSTT: realtimestt - DEBUG - Faster_whisper realtime speech to text transcription model initialized successfully +2025-07-23 11:29:18.485 - RealTimeSTT: realtimestt - INFO - Successfully loaded openwakeword model: alexa +2025-07-23 11:29:18.485 - RealTimeSTT: realtimestt - INFO - Successfully loaded openwakeword model: hey_mycroft +2025-07-23 11:29:18.485 - RealTimeSTT: realtimestt - INFO - Successfully loaded openwakeword model: hey_jarvis +2025-07-23 11:29:18.485 - RealTimeSTT: realtimestt - INFO - Successfully loaded openwakeword model: hey_rhasspy +2025-07-23 11:29:18.485 - RealTimeSTT: realtimestt - INFO - Successfully loaded openwakeword model: timer +2025-07-23 11:29:18.485 - RealTimeSTT: realtimestt - INFO - Successfully loaded openwakeword model: weather +2025-07-23 11:29:18.485 - RealTimeSTT: realtimestt - DEBUG - Open wake word detection engine initialized successfully +2025-07-23 11:29:18.485 - RealTimeSTT: realtimestt - INFO - Initializing WebRTC voice with Sensitivity 3 +2025-07-23 11:29:18.485 - RealTimeSTT: realtimestt - DEBUG - WebRTC VAD voice activity detection engine initialized successfully +2025-07-23 11:29:19.079 - RealTimeSTT: realtimestt - DEBUG - Silero VAD voice activity detection engine initialized successfully +2025-07-23 11:29:19.079 - RealTimeSTT: realtimestt - DEBUG - Starting realtime worker +2025-07-23 11:29:19.079 - RealTimeSTT: realtimestt - DEBUG - Waiting for main transcription model to start +2025-07-23 11:29:19.080 - RealTimeSTT: realtimestt - DEBUG - Main transcription model ready +2025-07-23 11:29:19.080 - RealTimeSTT: realtimestt - DEBUG - RealtimeSTT initialization completed successfully +2025-07-23 11:29:19.080 - RealTimeSTT: realtimestt - INFO - Setting listen time +2025-07-23 11:29:19.081 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'listening' +2025-07-23 11:29:19.081 - RealTimeSTT: realtimestt - INFO - State changed from 'listening' to 'wakeword' +2025-07-23 11:29:19.081 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording start +2025-07-23 11:31:59.298 - RealTimeSTT: realtimestt - INFO - Starting RealTimeSTT +2025-07-23 11:31:59.304 - RealTimeSTT: realtimestt - INFO - Initializing audio recording (creating pyAudio input stream, sample rate: 16000 buffer size: 512 +2025-07-23 11:31:59.310 - RealTimeSTT: realtimestt - INFO - Initializing WebRTC voice with Sensitivity 3 +2025-07-23 11:31:59.310 - RealTimeSTT: realtimestt - DEBUG - WebRTC VAD voice activity detection engine initialized successfully +2025-07-23 11:31:59.890 - RealTimeSTT: realtimestt - DEBUG - Silero VAD voice activity detection engine initialized successfully +2025-07-23 11:31:59.890 - RealTimeSTT: realtimestt - DEBUG - Starting realtime worker +2025-07-23 11:31:59.890 - RealTimeSTT: realtimestt - DEBUG - Waiting for main transcription model to start +2025-07-23 11:32:02.328 - RealTimeSTT: realtimestt - DEBUG - Main transcription model ready +2025-07-23 11:32:02.328 - RealTimeSTT: realtimestt - DEBUG - RealtimeSTT initialization completed successfully +2025-07-23 11:32:02.328 - RealTimeSTT: realtimestt - INFO - Setting listen time +2025-07-23 11:32:02.328 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'listening' +2025-07-23 11:32:02.328 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording start +2025-07-23 11:32:21.443 - RealTimeSTT: realtimestt - INFO - voice activity detected +2025-07-23 11:32:21.443 - RealTimeSTT: realtimestt - INFO - recording started +2025-07-23 11:32:21.443 - RealTimeSTT: realtimestt - INFO - State changed from 'listening' to 'recording' +2025-07-23 11:32:21.443 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording stop +2025-07-23 11:32:22.591 - RealTimeSTT: realtimestt - INFO - recording stopped +2025-07-23 11:32:22.591 - RealTimeSTT: realtimestt - DEBUG - No samples removed, final audio length: 34816 +2025-07-23 11:32:22.591 - RealTimeSTT: realtimestt - INFO - State changed from 'recording' to 'inactive' +2025-07-23 11:32:22.622 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'transcribing' +2025-07-23 11:32:22.623 - RealTimeSTT: realtimestt - DEBUG - Adding transcription request, no early transcription started +2025-07-23 11:32:22.629 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 11:32:22.736 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 11:32:22.838 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 11:32:22.938 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 11:32:22.952 - RealTimeSTT: realtimestt - INFO - State changed from 'transcribing' to 'inactive' +2025-07-23 11:32:22.954 - RealTimeSTT: realtimestt - DEBUG - Model tiny completed transcription in 0.33 seconds +2025-07-23 11:32:22.954 - RealTimeSTT: realtimestt - INFO - Setting listen time +2025-07-23 11:32:22.954 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'listening' +2025-07-23 11:32:22.954 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording start +2025-07-23 11:32:24.515 - RealTimeSTT: realtimestt - INFO - voice activity detected +2025-07-23 11:32:24.515 - RealTimeSTT: realtimestt - INFO - recording started +2025-07-23 11:32:24.515 - RealTimeSTT: realtimestt - INFO - State changed from 'listening' to 'recording' +2025-07-23 11:32:24.516 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording stop +2025-07-23 11:32:26.881 - RealTimeSTT: realtimestt - INFO - recording stopped +2025-07-23 11:32:26.882 - RealTimeSTT: realtimestt - DEBUG - No samples removed, final audio length: 54272 +2025-07-23 11:32:26.882 - RealTimeSTT: realtimestt - INFO - State changed from 'recording' to 'inactive' +2025-07-23 11:32:26.952 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'transcribing' +2025-07-23 11:32:26.953 - RealTimeSTT: realtimestt - DEBUG - Adding transcription request, no early transcription started +2025-07-23 11:32:26.954 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 11:32:27.056 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 11:32:27.157 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 11:32:27.258 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 11:32:27.313 - RealTimeSTT: realtimestt - INFO - State changed from 'transcribing' to 'inactive' +2025-07-23 11:32:27.362 - RealTimeSTT: realtimestt - DEBUG - Model tiny completed transcription in 0.41 seconds +2025-07-23 11:32:27.362 - RealTimeSTT: realtimestt - INFO - Setting listen time +2025-07-23 11:32:27.362 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'listening' +2025-07-23 11:32:27.362 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording start +2025-07-23 11:32:29.377 - RealTimeSTT: realtimestt - INFO - voice activity detected +2025-07-23 11:32:29.377 - RealTimeSTT: realtimestt - INFO - recording started +2025-07-23 11:32:29.377 - RealTimeSTT: realtimestt - INFO - State changed from 'listening' to 'recording' +2025-07-23 11:32:29.378 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording stop +2025-07-23 11:32:30.530 - RealTimeSTT: realtimestt - INFO - recording stopped +2025-07-23 11:32:30.613 - RealTimeSTT: realtimestt - DEBUG - No samples removed, final audio length: 34816 +2025-07-23 11:32:30.613 - RealTimeSTT: realtimestt - INFO - State changed from 'recording' to 'inactive' +2025-07-23 11:32:30.714 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'transcribing' +2025-07-23 11:32:30.714 - RealTimeSTT: realtimestt - DEBUG - Adding transcription request, no early transcription started +2025-07-23 11:32:30.720 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 11:32:30.821 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 11:32:30.824 - RealTimeSTT: realtimestt - INFO - State changed from 'transcribing' to 'inactive' +2025-07-23 11:32:30.878 - RealTimeSTT: realtimestt - DEBUG - Model tiny completed transcription in 0.16 seconds +2025-07-23 11:32:30.878 - RealTimeSTT: realtimestt - INFO - Setting listen time +2025-07-23 11:32:30.878 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'listening' +2025-07-23 11:32:30.879 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording start +2025-07-23 11:35:58.498 - RealTimeSTT: realtimestt - INFO - KeyboardInterrupt in wait_audio, shutting down +2025-07-23 11:35:58.498 - RealTimeSTT: realtimestt - DEBUG - Finishing recording thread +2025-07-23 11:35:58.506 - RealTimeSTT: realtimestt - DEBUG - Terminating reader process +2025-07-23 11:35:58.963 - RealTimeSTT: realtimestt - DEBUG - Terminating transcription process +2025-07-23 11:35:58.963 - RealTimeSTT: realtimestt - DEBUG - Finishing realtime thread +2025-07-23 11:35:59.017 - RealTimeSTT: realtimestt - INFO - KeyboardInterrupt in text() method +2025-07-23 11:36:04.436 - RealTimeSTT: realtimestt - INFO - Starting RealTimeSTT +2025-07-23 11:36:04.445 - RealTimeSTT: realtimestt - INFO - Initializing audio recording (creating pyAudio input stream, sample rate: 16000 buffer size: 512 +2025-07-23 11:36:04.452 - RealTimeSTT: realtimestt - INFO - Initializing WebRTC voice with Sensitivity 3 +2025-07-23 11:36:04.452 - RealTimeSTT: realtimestt - DEBUG - WebRTC VAD voice activity detection engine initialized successfully +2025-07-23 11:36:04.943 - RealTimeSTT: realtimestt - DEBUG - Silero VAD voice activity detection engine initialized successfully +2025-07-23 11:36:04.943 - RealTimeSTT: realtimestt - DEBUG - Starting realtime worker +2025-07-23 11:36:04.943 - RealTimeSTT: realtimestt - DEBUG - Waiting for main transcription model to start +2025-07-23 11:36:07.565 - RealTimeSTT: realtimestt - DEBUG - Main transcription model ready +2025-07-23 11:36:07.565 - RealTimeSTT: realtimestt - DEBUG - RealtimeSTT initialization completed successfully +2025-07-23 11:36:07.565 - RealTimeSTT: realtimestt - INFO - Setting listen time +2025-07-23 11:36:07.565 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'listening' +2025-07-23 11:36:07.566 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording start +2025-07-23 11:36:12.261 - RealTimeSTT: realtimestt - INFO - voice activity detected +2025-07-23 11:36:12.261 - RealTimeSTT: realtimestt - INFO - recording started +2025-07-23 11:36:12.261 - RealTimeSTT: realtimestt - INFO - State changed from 'listening' to 'recording' +2025-07-23 11:36:12.261 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording stop +2025-07-23 11:36:13.415 - RealTimeSTT: realtimestt - INFO - recording stopped +2025-07-23 11:36:13.416 - RealTimeSTT: realtimestt - DEBUG - No samples removed, final audio length: 34816 +2025-07-23 11:36:13.416 - RealTimeSTT: realtimestt - INFO - State changed from 'recording' to 'inactive' +2025-07-23 11:36:13.509 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'transcribing' +2025-07-23 11:36:13.509 - RealTimeSTT: realtimestt - DEBUG - Adding transcription request, no early transcription started +2025-07-23 11:36:13.533 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 11:36:13.640 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 11:36:13.749 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 11:36:13.850 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 11:36:13.854 - RealTimeSTT: realtimestt - INFO - State changed from 'transcribing' to 'inactive' +2025-07-23 11:36:13.883 - RealTimeSTT: realtimestt - DEBUG - Model tiny completed transcription in 0.37 seconds +2025-07-23 11:36:13.883 - RealTimeSTT: realtimestt - INFO - Setting listen time +2025-07-23 11:36:13.883 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'listening' +2025-07-23 11:36:13.883 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording start +2025-07-23 11:36:31.549 - RealTimeSTT: realtimestt - INFO - KeyboardInterrupt in wait_audio, shutting down +2025-07-23 11:36:31.549 - RealTimeSTT: realtimestt - DEBUG - Finishing recording thread +2025-07-23 11:36:31.549 - RealTimeSTT: realtimestt - DEBUG - Receive from stdout pipe +2025-07-23 11:36:31.550 - RealTimeSTT: realtimestt - INFO - None +2025-07-23 11:36:31.550 - RealTimeSTT: realtimestt - DEBUG - Terminating reader process +2025-07-23 11:36:31.963 - RealTimeSTT: realtimestt - DEBUG - Terminating transcription process +2025-07-23 11:36:31.963 - RealTimeSTT: realtimestt - DEBUG - Finishing realtime thread +2025-07-23 11:36:32.011 - RealTimeSTT: realtimestt - INFO - KeyboardInterrupt in text() method +2025-07-23 11:36:43.916 - RealTimeSTT: realtimestt - INFO - recording stopped +2025-07-23 11:36:43.916 - RealTimeSTT: realtimestt - DEBUG - Finishing recording thread +2025-07-23 11:36:43.916 - RealTimeSTT: realtimestt - DEBUG - No samples removed, final audio length: 0 +2025-07-23 11:36:43.916 - RealTimeSTT: realtimestt - INFO - State changed from 'listening' to 'inactive' +2025-07-23 11:36:43.924 - RealTimeSTT: realtimestt - DEBUG - Terminating reader process +2025-07-23 11:36:44.563 - RealTimeSTT: realtimestt - DEBUG - Terminating transcription process +2025-07-23 11:36:44.563 - RealTimeSTT: realtimestt - DEBUG - Finishing realtime thread +2025-07-23 11:36:56.167 - RealTimeSTT: realtimestt - INFO - Starting RealTimeSTT +2025-07-23 11:36:56.177 - RealTimeSTT: realtimestt - INFO - Initializing audio recording (creating pyAudio input stream, sample rate: 16000 buffer size: 512 +2025-07-23 11:36:56.182 - RealTimeSTT: realtimestt - INFO - Initializing faster_whisper realtime transcription model tiny, default device: cpu, compute type: default, device index: 0, download root: None +2025-07-23 11:36:56.662 - RealTimeSTT: realtimestt - DEBUG - Faster_whisper realtime speech to text transcription model initialized successfully +2025-07-23 11:36:56.729 - RealTimeSTT: realtimestt - INFO - Successfully loaded openwakeword model: alexa +2025-07-23 11:36:56.729 - RealTimeSTT: realtimestt - INFO - Successfully loaded openwakeword model: hey_mycroft +2025-07-23 11:36:56.730 - RealTimeSTT: realtimestt - INFO - Successfully loaded openwakeword model: hey_jarvis +2025-07-23 11:36:56.730 - RealTimeSTT: realtimestt - INFO - Successfully loaded openwakeword model: hey_rhasspy +2025-07-23 11:36:56.730 - RealTimeSTT: realtimestt - INFO - Successfully loaded openwakeword model: timer +2025-07-23 11:36:56.730 - RealTimeSTT: realtimestt - INFO - Successfully loaded openwakeword model: weather +2025-07-23 11:36:56.730 - RealTimeSTT: realtimestt - DEBUG - Open wake word detection engine initialized successfully +2025-07-23 11:36:56.730 - RealTimeSTT: realtimestt - INFO - Initializing WebRTC voice with Sensitivity 3 +2025-07-23 11:36:56.730 - RealTimeSTT: realtimestt - DEBUG - WebRTC VAD voice activity detection engine initialized successfully +2025-07-23 11:36:57.189 - RealTimeSTT: realtimestt - DEBUG - Silero VAD voice activity detection engine initialized successfully +2025-07-23 11:36:57.190 - RealTimeSTT: realtimestt - DEBUG - Starting realtime worker +2025-07-23 11:36:57.190 - RealTimeSTT: realtimestt - DEBUG - Waiting for main transcription model to start +2025-07-23 11:36:59.393 - RealTimeSTT: realtimestt - DEBUG - Main transcription model ready +2025-07-23 11:36:59.393 - RealTimeSTT: realtimestt - DEBUG - RealtimeSTT initialization completed successfully +2025-07-23 11:36:59.394 - RealTimeSTT: realtimestt - INFO - Setting listen time +2025-07-23 11:36:59.394 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'listening' +2025-07-23 11:36:59.394 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording start +2025-07-23 11:36:59.444 - RealTimeSTT: realtimestt - INFO - State changed from 'listening' to 'wakeword' +2025-07-23 11:37:19.543 - RealTimeSTT: realtimestt - INFO - State changed from 'wakeword' to 'listening' +2025-07-23 11:37:21.340 - RealTimeSTT: realtimestt - INFO - voice activity detected +2025-07-23 11:37:21.340 - RealTimeSTT: realtimestt - INFO - recording started +2025-07-23 11:37:21.340 - RealTimeSTT: realtimestt - INFO - State changed from 'listening' to 'recording' +2025-07-23 11:37:21.340 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording stop +2025-07-23 11:37:21.352 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 14848 +2025-07-23 11:37:21.545 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: You +2025-07-23 11:37:21.552 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 17920 +2025-07-23 11:37:21.743 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: What are you doing? +2025-07-23 11:37:21.753 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 20992 +2025-07-23 11:37:21.939 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: Are you there? +2025-07-23 11:37:22.552 - RealTimeSTT: realtimestt - INFO - recording stopped +2025-07-23 11:37:22.552 - RealTimeSTT: realtimestt - DEBUG - No samples removed, final audio length: 33792 +2025-07-23 11:37:22.552 - RealTimeSTT: realtimestt - INFO - State changed from 'recording' to 'inactive' +2025-07-23 11:37:22.620 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'transcribing' +2025-07-23 11:37:22.621 - RealTimeSTT: realtimestt - DEBUG - Adding transcription request, no early transcription started +2025-07-23 11:37:22.622 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 11:37:22.724 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 11:37:22.825 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 11:37:22.926 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 11:37:23.020 - RealTimeSTT: realtimestt - INFO - State changed from 'transcribing' to 'inactive' +2025-07-23 11:37:23.052 - RealTimeSTT: realtimestt - DEBUG - Model base completed transcription in 0.43 seconds +2025-07-23 11:37:23.053 - RealTimeSTT: realtimestt - INFO - Setting listen time +2025-07-23 11:37:23.053 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'listening' +2025-07-23 11:37:23.053 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording start +2025-07-23 11:39:19.715 - RealTimeSTT: realtimestt - DEBUG - No samples removed, final audio length: 0 +2025-07-23 11:39:19.721 - RealTimeSTT: realtimestt - INFO - State changed from 'listening' to 'inactive' +2025-07-23 11:39:19.905 - RealTimeSTT: realtimestt - INFO - Setting listen time +2025-07-23 11:39:19.905 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'listening' +2025-07-23 11:39:19.905 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording start +2025-07-23 11:39:29.102 - RealTimeSTT: realtimestt - INFO - Starting RealTimeSTT +2025-07-23 11:39:29.111 - RealTimeSTT: realtimestt - INFO - Initializing audio recording (creating pyAudio input stream, sample rate: 16000 buffer size: 512 +2025-07-23 11:39:29.115 - RealTimeSTT: realtimestt - INFO - Initializing WebRTC voice with Sensitivity 3 +2025-07-23 11:39:29.116 - RealTimeSTT: realtimestt - DEBUG - WebRTC VAD voice activity detection engine initialized successfully +2025-07-23 11:39:29.590 - RealTimeSTT: realtimestt - DEBUG - Silero VAD voice activity detection engine initialized successfully +2025-07-23 11:39:29.590 - RealTimeSTT: realtimestt - DEBUG - Starting realtime worker +2025-07-23 11:39:29.590 - RealTimeSTT: realtimestt - DEBUG - Waiting for main transcription model to start +2025-07-23 11:39:32.080 - RealTimeSTT: realtimestt - DEBUG - Main transcription model ready +2025-07-23 11:39:32.080 - RealTimeSTT: realtimestt - DEBUG - RealtimeSTT initialization completed successfully +2025-07-23 11:39:32.080 - RealTimeSTT: realtimestt - INFO - Setting listen time +2025-07-23 11:39:32.080 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'listening' +2025-07-23 11:39:32.081 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording start +2025-07-23 11:39:32.547 - RealTimeSTT: realtimestt - INFO - voice activity detected +2025-07-23 11:39:32.547 - RealTimeSTT: realtimestt - INFO - recording started +2025-07-23 11:39:32.547 - RealTimeSTT: realtimestt - INFO - State changed from 'listening' to 'recording' +2025-07-23 11:39:32.547 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording stop +2025-07-23 11:39:34.468 - RealTimeSTT: realtimestt - INFO - recording stopped +2025-07-23 11:39:34.468 - RealTimeSTT: realtimestt - DEBUG - No samples removed, final audio length: 39424 +2025-07-23 11:39:34.468 - RealTimeSTT: realtimestt - INFO - State changed from 'recording' to 'inactive' +2025-07-23 11:39:34.564 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'transcribing' +2025-07-23 11:39:34.564 - RealTimeSTT: realtimestt - DEBUG - Adding transcription request, no early transcription started +2025-07-23 11:39:34.565 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 11:39:34.665 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 11:39:34.745 - RealTimeSTT: realtimestt - INFO - State changed from 'transcribing' to 'inactive' +2025-07-23 11:39:34.759 - RealTimeSTT: realtimestt - DEBUG - Model tiny completed transcription in 0.19 seconds +2025-07-23 11:39:34.759 - RealTimeSTT: realtimestt - INFO - Setting listen time +2025-07-23 11:39:34.759 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'listening' +2025-07-23 11:39:34.759 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording start +2025-07-23 11:39:35.877 - RealTimeSTT: realtimestt - INFO - voice activity detected +2025-07-23 11:39:35.877 - RealTimeSTT: realtimestt - INFO - recording started +2025-07-23 11:39:35.877 - RealTimeSTT: realtimestt - INFO - State changed from 'listening' to 'recording' +2025-07-23 11:39:35.877 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording stop +2025-07-23 11:39:37.474 - RealTimeSTT: realtimestt - INFO - recording stopped +2025-07-23 11:39:37.475 - RealTimeSTT: realtimestt - DEBUG - No samples removed, final audio length: 41984 +2025-07-23 11:39:37.475 - RealTimeSTT: realtimestt - INFO - State changed from 'recording' to 'inactive' +2025-07-23 11:39:37.572 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'transcribing' +2025-07-23 11:39:37.573 - RealTimeSTT: realtimestt - DEBUG - Adding transcription request, no early transcription started +2025-07-23 11:39:37.579 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 11:39:37.680 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 11:39:37.778 - RealTimeSTT: realtimestt - INFO - State changed from 'transcribing' to 'inactive' +2025-07-23 11:39:37.820 - RealTimeSTT: realtimestt - DEBUG - Model tiny completed transcription in 0.25 seconds +2025-07-23 11:39:37.820 - RealTimeSTT: realtimestt - INFO - Setting listen time +2025-07-23 11:39:37.820 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'listening' +2025-07-23 11:39:37.820 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording start +2025-07-23 11:39:38.245 - RealTimeSTT: realtimestt - INFO - voice activity detected +2025-07-23 11:39:38.245 - RealTimeSTT: realtimestt - INFO - recording started +2025-07-23 11:39:38.245 - RealTimeSTT: realtimestt - INFO - State changed from 'listening' to 'recording' +2025-07-23 11:39:38.245 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording stop +2025-07-23 11:39:39.522 - RealTimeSTT: realtimestt - INFO - recording stopped +2025-07-23 11:39:39.523 - RealTimeSTT: realtimestt - DEBUG - No samples removed, final audio length: 36864 +2025-07-23 11:39:39.523 - RealTimeSTT: realtimestt - INFO - State changed from 'recording' to 'inactive' +2025-07-23 11:39:39.566 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'transcribing' +2025-07-23 11:39:39.567 - RealTimeSTT: realtimestt - DEBUG - Adding transcription request, no early transcription started +2025-07-23 11:39:39.571 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 11:39:39.672 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 11:39:39.773 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 11:39:39.786 - RealTimeSTT: realtimestt - INFO - State changed from 'transcribing' to 'inactive' +2025-07-23 11:39:39.815 - RealTimeSTT: realtimestt - DEBUG - Model tiny completed transcription in 0.25 seconds +2025-07-23 11:39:39.815 - RealTimeSTT: realtimestt - INFO - Setting listen time +2025-07-23 11:39:39.815 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'listening' +2025-07-23 11:39:39.816 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording start +2025-07-23 11:39:40.230 - RealTimeSTT: realtimestt - INFO - voice activity detected +2025-07-23 11:39:40.230 - RealTimeSTT: realtimestt - INFO - recording started +2025-07-23 11:39:40.230 - RealTimeSTT: realtimestt - INFO - State changed from 'listening' to 'recording' +2025-07-23 11:39:40.230 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording stop +2025-07-23 11:39:44.773 - RealTimeSTT: realtimestt - INFO - recording stopped +2025-07-23 11:39:44.773 - RealTimeSTT: realtimestt - DEBUG - No samples removed, final audio length: 89088 +2025-07-23 11:39:44.774 - RealTimeSTT: realtimestt - INFO - State changed from 'recording' to 'inactive' +2025-07-23 11:39:44.874 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'transcribing' +2025-07-23 11:39:44.874 - RealTimeSTT: realtimestt - DEBUG - Adding transcription request, no early transcription started +2025-07-23 11:39:44.882 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 11:39:44.983 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 11:39:45.084 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 11:39:45.161 - RealTimeSTT: realtimestt - INFO - State changed from 'transcribing' to 'inactive' +2025-07-23 11:39:45.196 - RealTimeSTT: realtimestt - DEBUG - Model tiny completed transcription in 0.32 seconds +2025-07-23 11:39:45.197 - RealTimeSTT: realtimestt - INFO - Setting listen time +2025-07-23 11:39:45.197 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'listening' +2025-07-23 11:39:45.197 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording start +2025-07-23 11:39:45.479 - RealTimeSTT: realtimestt - INFO - voice activity detected +2025-07-23 11:39:45.479 - RealTimeSTT: realtimestt - INFO - recording started +2025-07-23 11:39:45.479 - RealTimeSTT: realtimestt - INFO - State changed from 'listening' to 'recording' +2025-07-23 11:39:45.479 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording stop +2025-07-23 11:39:46.695 - RealTimeSTT: realtimestt - INFO - recording stopped +2025-07-23 11:39:46.695 - RealTimeSTT: realtimestt - DEBUG - No samples removed, final audio length: 35840 +2025-07-23 11:39:46.695 - RealTimeSTT: realtimestt - INFO - State changed from 'recording' to 'inactive' +2025-07-23 11:39:46.747 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'transcribing' +2025-07-23 11:39:46.748 - RealTimeSTT: realtimestt - DEBUG - Adding transcription request, no early transcription started +2025-07-23 11:39:46.748 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 11:39:46.849 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 11:39:46.946 - RealTimeSTT: realtimestt - INFO - State changed from 'transcribing' to 'inactive' +2025-07-23 11:39:46.961 - RealTimeSTT: realtimestt - DEBUG - Model tiny completed transcription in 0.21 seconds +2025-07-23 11:39:46.962 - RealTimeSTT: realtimestt - INFO - Setting listen time +2025-07-23 11:39:46.962 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'listening' +2025-07-23 11:39:46.962 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording start +2025-07-23 11:39:47.394 - RealTimeSTT: realtimestt - INFO - voice activity detected +2025-07-23 11:39:47.394 - RealTimeSTT: realtimestt - INFO - recording started +2025-07-23 11:39:47.394 - RealTimeSTT: realtimestt - INFO - State changed from 'listening' to 'recording' +2025-07-23 11:39:47.394 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording stop +2025-07-23 11:39:48.552 - RealTimeSTT: realtimestt - INFO - recording stopped +2025-07-23 11:39:48.552 - RealTimeSTT: realtimestt - DEBUG - No samples removed, final audio length: 34816 +2025-07-23 11:39:48.552 - RealTimeSTT: realtimestt - INFO - State changed from 'recording' to 'inactive' +2025-07-23 11:39:48.606 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'transcribing' +2025-07-23 11:39:48.607 - RealTimeSTT: realtimestt - DEBUG - Adding transcription request, no early transcription started +2025-07-23 11:39:48.614 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 11:39:48.715 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 11:39:48.730 - RealTimeSTT: realtimestt - INFO - State changed from 'transcribing' to 'inactive' +2025-07-23 11:39:48.765 - RealTimeSTT: realtimestt - DEBUG - Model tiny completed transcription in 0.16 seconds +2025-07-23 11:39:48.765 - RealTimeSTT: realtimestt - INFO - Setting listen time +2025-07-23 11:39:48.765 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'listening' +2025-07-23 11:39:48.765 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording start +2025-07-23 11:41:00.229 - RealTimeSTT: realtimestt - INFO - voice activity detected +2025-07-23 11:41:00.230 - RealTimeSTT: realtimestt - INFO - recording started +2025-07-23 11:41:00.230 - RealTimeSTT: realtimestt - INFO - State changed from 'listening' to 'recording' +2025-07-23 11:41:00.231 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording stop +2025-07-23 11:41:01.381 - RealTimeSTT: realtimestt - INFO - recording stopped +2025-07-23 11:41:01.382 - RealTimeSTT: realtimestt - DEBUG - No samples removed, final audio length: 34816 +2025-07-23 11:41:01.382 - RealTimeSTT: realtimestt - INFO - State changed from 'recording' to 'inactive' +2025-07-23 11:41:01.463 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'transcribing' +2025-07-23 11:41:01.465 - RealTimeSTT: realtimestt - DEBUG - Adding transcription request, no early transcription started +2025-07-23 11:41:01.467 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 11:41:01.568 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 11:41:01.687 - RealTimeSTT: realtimestt - INFO - State changed from 'transcribing' to 'inactive' +2025-07-23 11:41:01.738 - RealTimeSTT: realtimestt - DEBUG - Model tiny completed transcription in 0.27 seconds +2025-07-23 11:41:01.739 - RealTimeSTT: realtimestt - INFO - Setting listen time +2025-07-23 11:41:01.739 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'listening' +2025-07-23 11:41:01.741 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording start +2025-07-23 11:41:02.211 - RealTimeSTT: realtimestt - INFO - voice activity detected +2025-07-23 11:41:02.212 - RealTimeSTT: realtimestt - INFO - recording started +2025-07-23 11:41:02.212 - RealTimeSTT: realtimestt - INFO - State changed from 'listening' to 'recording' +2025-07-23 11:41:02.212 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording stop +2025-07-23 11:41:03.364 - RealTimeSTT: realtimestt - INFO - recording stopped +2025-07-23 11:41:03.365 - RealTimeSTT: realtimestt - DEBUG - No samples removed, final audio length: 34816 +2025-07-23 11:41:03.365 - RealTimeSTT: realtimestt - INFO - State changed from 'recording' to 'inactive' +2025-07-23 11:41:03.444 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'transcribing' +2025-07-23 11:41:03.446 - RealTimeSTT: realtimestt - DEBUG - Adding transcription request, no early transcription started +2025-07-23 11:41:03.454 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 11:41:03.546 - RealTimeSTT: realtimestt - INFO - State changed from 'transcribing' to 'inactive' +2025-07-23 11:41:03.550 - RealTimeSTT: realtimestt - DEBUG - Model tiny completed transcription in 0.10 seconds +2025-07-23 11:41:03.551 - RealTimeSTT: realtimestt - INFO - Setting listen time +2025-07-23 11:41:03.551 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'listening' +2025-07-23 11:41:03.552 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording start +2025-07-23 11:41:10.918 - RealTimeSTT: realtimestt - INFO - voice activity detected +2025-07-23 11:41:10.918 - RealTimeSTT: realtimestt - INFO - recording started +2025-07-23 11:41:10.918 - RealTimeSTT: realtimestt - INFO - State changed from 'listening' to 'recording' +2025-07-23 11:41:10.919 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording stop +2025-07-23 11:41:13.156 - RealTimeSTT: realtimestt - INFO - recording stopped +2025-07-23 11:41:13.159 - RealTimeSTT: realtimestt - DEBUG - No samples removed, final audio length: 52224 +2025-07-23 11:41:13.160 - RealTimeSTT: realtimestt - INFO - State changed from 'recording' to 'inactive' +2025-07-23 11:41:13.165 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'transcribing' +2025-07-23 11:41:13.167 - RealTimeSTT: realtimestt - DEBUG - Adding transcription request, no early transcription started +2025-07-23 11:41:13.179 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 11:41:13.281 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 11:41:13.382 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 11:41:13.421 - RealTimeSTT: realtimestt - INFO - State changed from 'transcribing' to 'inactive' +2025-07-23 11:41:13.423 - RealTimeSTT: realtimestt - DEBUG - Model tiny completed transcription in 0.26 seconds +2025-07-23 11:41:13.424 - RealTimeSTT: realtimestt - INFO - Setting listen time +2025-07-23 11:41:13.424 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'listening' +2025-07-23 11:41:13.425 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording start +2025-07-23 11:41:13.988 - RealTimeSTT: realtimestt - INFO - voice activity detected +2025-07-23 11:41:13.988 - RealTimeSTT: realtimestt - INFO - recording started +2025-07-23 11:41:13.988 - RealTimeSTT: realtimestt - INFO - State changed from 'listening' to 'recording' +2025-07-23 11:41:13.988 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording stop +2025-07-23 11:41:15.144 - RealTimeSTT: realtimestt - INFO - recording stopped +2025-07-23 11:41:15.154 - RealTimeSTT: realtimestt - DEBUG - No samples removed, final audio length: 34816 +2025-07-23 11:41:15.154 - RealTimeSTT: realtimestt - INFO - State changed from 'recording' to 'inactive' +2025-07-23 11:41:15.227 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'transcribing' +2025-07-23 11:41:15.229 - RealTimeSTT: realtimestt - DEBUG - Adding transcription request, no early transcription started +2025-07-23 11:41:15.232 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 11:41:15.334 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 11:41:15.357 - RealTimeSTT: realtimestt - INFO - State changed from 'transcribing' to 'inactive' +2025-07-23 11:41:15.385 - RealTimeSTT: realtimestt - DEBUG - Model tiny completed transcription in 0.16 seconds +2025-07-23 11:41:15.385 - RealTimeSTT: realtimestt - INFO - Setting listen time +2025-07-23 11:41:15.385 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'listening' +2025-07-23 11:41:15.386 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording start +2025-07-23 11:41:26.824 - RealTimeSTT: realtimestt - DEBUG - Receive from stdout pipe +2025-07-23 11:41:26.824 - RealTimeSTT: realtimestt - INFO - None +2025-07-23 11:41:26.828 - RealTimeSTT: realtimestt - DEBUG - No samples removed, final audio length: 0 +2025-07-23 11:41:26.828 - RealTimeSTT: realtimestt - INFO - State changed from 'listening' to 'inactive' +2025-07-23 11:41:26.976 - RealTimeSTT: realtimestt - INFO - Setting listen time +2025-07-23 11:41:26.977 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'listening' +2025-07-23 11:41:26.978 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording start +2025-07-23 11:41:53.044 - RealTimeSTT: realtimestt - INFO - Starting RealTimeSTT +2025-07-23 11:41:53.053 - RealTimeSTT: realtimestt - INFO - Initializing audio recording (creating pyAudio input stream, sample rate: 16000 buffer size: 512 +2025-07-23 11:41:53.059 - RealTimeSTT: realtimestt - INFO - Initializing WebRTC voice with Sensitivity 3 +2025-07-23 11:41:53.059 - RealTimeSTT: realtimestt - DEBUG - WebRTC VAD voice activity detection engine initialized successfully +2025-07-23 11:41:53.215 - RealTimeSTT: realtimestt - DEBUG - Silero VAD voice activity detection engine initialized successfully +2025-07-23 11:41:53.215 - RealTimeSTT: realtimestt - DEBUG - Starting realtime worker +2025-07-23 11:41:53.215 - RealTimeSTT: realtimestt - DEBUG - Waiting for main transcription model to start +2025-07-23 11:41:56.007 - RealTimeSTT: realtimestt - DEBUG - Main transcription model ready +2025-07-23 11:41:56.008 - RealTimeSTT: realtimestt - DEBUG - RealtimeSTT initialization completed successfully +2025-07-23 11:41:56.008 - RealTimeSTT: realtimestt - INFO - Setting listen time +2025-07-23 11:41:56.008 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'listening' +2025-07-23 11:41:56.008 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording start +2025-07-23 11:41:56.480 - RealTimeSTT: realtimestt - INFO - voice activity detected +2025-07-23 11:41:56.480 - RealTimeSTT: realtimestt - INFO - recording started +2025-07-23 11:41:56.480 - RealTimeSTT: realtimestt - INFO - State changed from 'listening' to 'recording' +2025-07-23 11:41:56.480 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording stop +2025-07-23 11:41:58.975 - RealTimeSTT: realtimestt - INFO - recording stopped +2025-07-23 11:41:58.976 - RealTimeSTT: realtimestt - DEBUG - No samples removed, final audio length: 48640 +2025-07-23 11:41:58.976 - RealTimeSTT: realtimestt - INFO - State changed from 'recording' to 'inactive' +2025-07-23 11:41:58.988 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'transcribing' +2025-07-23 11:41:58.988 - RealTimeSTT: realtimestt - DEBUG - Adding transcription request, no early transcription started +2025-07-23 11:41:58.989 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 11:41:59.090 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 11:41:59.191 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 11:41:59.206 - RealTimeSTT: realtimestt - INFO - State changed from 'transcribing' to 'inactive' +2025-07-23 11:41:59.235 - RealTimeSTT: realtimestt - DEBUG - Model tiny completed transcription in 0.25 seconds +2025-07-23 11:41:59.235 - RealTimeSTT: realtimestt - INFO - Setting listen time +2025-07-23 11:41:59.235 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'listening' +2025-07-23 11:41:59.236 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording start +2025-07-23 11:41:59.742 - RealTimeSTT: realtimestt - INFO - voice activity detected +2025-07-23 11:41:59.742 - RealTimeSTT: realtimestt - INFO - recording started +2025-07-23 11:41:59.742 - RealTimeSTT: realtimestt - INFO - State changed from 'listening' to 'recording' +2025-07-23 11:41:59.742 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording stop +2025-07-23 11:42:05.056 - RealTimeSTT: realtimestt - INFO - recording stopped +2025-07-23 11:42:05.056 - RealTimeSTT: realtimestt - DEBUG - No samples removed, final audio length: 101376 +2025-07-23 11:42:05.057 - RealTimeSTT: realtimestt - INFO - State changed from 'recording' to 'inactive' +2025-07-23 11:42:05.134 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'transcribing' +2025-07-23 11:42:05.135 - RealTimeSTT: realtimestt - DEBUG - Adding transcription request, no early transcription started +2025-07-23 11:42:05.136 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 11:42:05.234 - RealTimeSTT: realtimestt - INFO - State changed from 'transcribing' to 'inactive' +2025-07-23 11:42:05.244 - RealTimeSTT: realtimestt - DEBUG - Model tiny completed transcription in 0.11 seconds +2025-07-23 11:42:05.244 - RealTimeSTT: realtimestt - INFO - Setting listen time +2025-07-23 11:42:05.244 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'listening' +2025-07-23 11:42:05.245 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording start +2025-07-23 11:42:06.005 - RealTimeSTT: realtimestt - DEBUG - No samples removed, final audio length: 0 +2025-07-23 11:42:06.005 - RealTimeSTT: realtimestt - INFO - State changed from 'listening' to 'inactive' +2025-07-23 11:42:06.009 - RealTimeSTT: realtimestt - INFO - Setting listen time +2025-07-23 11:42:06.010 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'listening' +2025-07-23 11:42:06.010 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording start +2025-07-23 11:42:06.033 - RealTimeSTT: realtimestt - DEBUG - No samples removed, final audio length: 0 +2025-07-23 11:42:06.033 - RealTimeSTT: realtimestt - INFO - State changed from 'listening' to 'inactive' +2025-07-23 11:42:17.930 - RealTimeSTT: realtimestt - INFO - Starting RealTimeSTT +2025-07-23 11:42:17.936 - RealTimeSTT: realtimestt - INFO - Initializing audio recording (creating pyAudio input stream, sample rate: 16000 buffer size: 512 +2025-07-23 11:42:18.012 - RealTimeSTT: realtimestt - INFO - Successfully loaded openwakeword model: alexa +2025-07-23 11:42:18.012 - RealTimeSTT: realtimestt - INFO - Successfully loaded openwakeword model: hey_mycroft +2025-07-23 11:42:18.012 - RealTimeSTT: realtimestt - INFO - Successfully loaded openwakeword model: hey_jarvis +2025-07-23 11:42:18.012 - RealTimeSTT: realtimestt - INFO - Successfully loaded openwakeword model: hey_rhasspy +2025-07-23 11:42:18.012 - RealTimeSTT: realtimestt - INFO - Successfully loaded openwakeword model: timer +2025-07-23 11:42:18.012 - RealTimeSTT: realtimestt - INFO - Successfully loaded openwakeword model: weather +2025-07-23 11:42:18.012 - RealTimeSTT: realtimestt - DEBUG - Open wake word detection engine initialized successfully +2025-07-23 11:42:18.012 - RealTimeSTT: realtimestt - INFO - Initializing WebRTC voice with Sensitivity 3 +2025-07-23 11:42:18.012 - RealTimeSTT: realtimestt - DEBUG - WebRTC VAD voice activity detection engine initialized successfully +2025-07-23 11:42:18.533 - RealTimeSTT: realtimestt - DEBUG - Silero VAD voice activity detection engine initialized successfully +2025-07-23 11:42:18.534 - RealTimeSTT: realtimestt - DEBUG - Starting realtime worker +2025-07-23 11:42:18.534 - RealTimeSTT: realtimestt - DEBUG - Waiting for main transcription model to start +2025-07-23 11:42:21.149 - RealTimeSTT: realtimestt - DEBUG - Main transcription model ready +2025-07-23 11:42:21.150 - RealTimeSTT: realtimestt - DEBUG - RealtimeSTT initialization completed successfully +2025-07-23 11:42:21.150 - RealTimeSTT: realtimestt - INFO - Setting listen time +2025-07-23 11:42:21.150 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'listening' +2025-07-23 11:42:21.151 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording start +2025-07-23 11:42:21.155 - RealTimeSTT: realtimestt - INFO - State changed from 'listening' to 'wakeword' +2025-07-23 11:43:05.705 - RealTimeSTT: realtimestt - DEBUG - No samples removed, final audio length: 0 +2025-07-23 11:43:05.706 - RealTimeSTT: realtimestt - INFO - State changed from 'wakeword' to 'inactive' +2025-07-23 11:43:30.243 - RealTimeSTT: realtimestt - INFO - Starting RealTimeSTT +2025-07-23 11:43:30.252 - RealTimeSTT: realtimestt - INFO - Initializing audio recording (creating pyAudio input stream, sample rate: 16000 buffer size: 512 +2025-07-23 11:43:30.331 - RealTimeSTT: realtimestt - INFO - Successfully loaded openwakeword model: alexa +2025-07-23 11:43:30.331 - RealTimeSTT: realtimestt - INFO - Successfully loaded openwakeword model: hey_mycroft +2025-07-23 11:43:30.331 - RealTimeSTT: realtimestt - INFO - Successfully loaded openwakeword model: hey_jarvis +2025-07-23 11:43:30.331 - RealTimeSTT: realtimestt - INFO - Successfully loaded openwakeword model: hey_rhasspy +2025-07-23 11:43:30.331 - RealTimeSTT: realtimestt - INFO - Successfully loaded openwakeword model: timer +2025-07-23 11:43:30.331 - RealTimeSTT: realtimestt - INFO - Successfully loaded openwakeword model: weather +2025-07-23 11:43:30.331 - RealTimeSTT: realtimestt - DEBUG - Open wake word detection engine initialized successfully +2025-07-23 11:43:30.331 - RealTimeSTT: realtimestt - INFO - Initializing WebRTC voice with Sensitivity 3 +2025-07-23 11:43:30.331 - RealTimeSTT: realtimestt - DEBUG - WebRTC VAD voice activity detection engine initialized successfully +2025-07-23 11:43:30.814 - RealTimeSTT: realtimestt - DEBUG - Silero VAD voice activity detection engine initialized successfully +2025-07-23 11:43:30.814 - RealTimeSTT: realtimestt - DEBUG - Starting realtime worker +2025-07-23 11:43:30.814 - RealTimeSTT: realtimestt - DEBUG - Waiting for main transcription model to start +2025-07-23 11:43:33.762 - RealTimeSTT: realtimestt - DEBUG - Main transcription model ready +2025-07-23 11:43:33.763 - RealTimeSTT: realtimestt - DEBUG - RealtimeSTT initialization completed successfully +2025-07-23 11:43:33.763 - RealTimeSTT: realtimestt - INFO - Setting listen time +2025-07-23 11:43:33.763 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'listening' +2025-07-23 11:43:33.763 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording start +2025-07-23 11:43:33.777 - RealTimeSTT: realtimestt - INFO - State changed from 'listening' to 'wakeword' +2025-07-23 11:44:13.142 - RealTimeSTT: realtimestt - DEBUG - Receive from stdout pipe +2025-07-23 11:44:13.142 - RealTimeSTT: realtimestt - INFO - None +2025-07-23 11:44:13.154 - RealTimeSTT: realtimestt - DEBUG - No samples removed, final audio length: 0 +2025-07-23 11:44:13.154 - RealTimeSTT: realtimestt - INFO - State changed from 'wakeword' to 'inactive' +2025-07-23 11:44:25.807 - RealTimeSTT: realtimestt - INFO - Starting RealTimeSTT +2025-07-23 11:44:25.815 - RealTimeSTT: realtimestt - INFO - Initializing audio recording (creating pyAudio input stream, sample rate: 16000 buffer size: 512 +2025-07-23 11:44:25.819 - RealTimeSTT: realtimestt - INFO - Initializing faster_whisper realtime transcription model tiny, default device: cpu, compute type: default, device index: 0, download root: None +2025-07-23 11:44:26.314 - RealTimeSTT: realtimestt - DEBUG - Faster_whisper realtime speech to text transcription model initialized successfully +2025-07-23 11:44:26.382 - RealTimeSTT: realtimestt - INFO - Successfully loaded openwakeword model: alexa +2025-07-23 11:44:26.382 - RealTimeSTT: realtimestt - INFO - Successfully loaded openwakeword model: hey_mycroft +2025-07-23 11:44:26.382 - RealTimeSTT: realtimestt - INFO - Successfully loaded openwakeword model: hey_jarvis +2025-07-23 11:44:26.382 - RealTimeSTT: realtimestt - INFO - Successfully loaded openwakeword model: hey_rhasspy +2025-07-23 11:44:26.382 - RealTimeSTT: realtimestt - INFO - Successfully loaded openwakeword model: timer +2025-07-23 11:44:26.382 - RealTimeSTT: realtimestt - INFO - Successfully loaded openwakeword model: weather +2025-07-23 11:44:26.382 - RealTimeSTT: realtimestt - DEBUG - Open wake word detection engine initialized successfully +2025-07-23 11:44:26.382 - RealTimeSTT: realtimestt - INFO - Initializing WebRTC voice with Sensitivity 3 +2025-07-23 11:44:26.382 - RealTimeSTT: realtimestt - DEBUG - WebRTC VAD voice activity detection engine initialized successfully +2025-07-23 11:44:26.843 - RealTimeSTT: realtimestt - DEBUG - Silero VAD voice activity detection engine initialized successfully +2025-07-23 11:44:26.843 - RealTimeSTT: realtimestt - DEBUG - Starting realtime worker +2025-07-23 11:44:26.843 - RealTimeSTT: realtimestt - DEBUG - Waiting for main transcription model to start +2025-07-23 11:44:28.942 - RealTimeSTT: realtimestt - DEBUG - Main transcription model ready +2025-07-23 11:44:28.943 - RealTimeSTT: realtimestt - DEBUG - RealtimeSTT initialization completed successfully +2025-07-23 11:44:28.943 - RealTimeSTT: realtimestt - INFO - Setting listen time +2025-07-23 11:44:28.943 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'listening' +2025-07-23 11:44:28.943 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording start +2025-07-23 11:44:29.000 - RealTimeSTT: realtimestt - INFO - State changed from 'listening' to 'wakeword' +2025-07-23 11:44:37.386 - RealTimeSTT: realtimestt - INFO - State changed from 'wakeword' to 'listening' +2025-07-23 11:44:42.435 - RealTimeSTT: realtimestt - INFO - State changed from 'listening' to 'wakeword' +2025-07-23 11:45:45.662 - RealTimeSTT: realtimestt - DEBUG - Receive from stdout pipe +2025-07-23 11:45:45.662 - RealTimeSTT: realtimestt - INFO - None +2025-07-23 11:45:45.663 - RealTimeSTT: realtimestt - DEBUG - No samples removed, final audio length: 0 +2025-07-23 11:45:45.663 - RealTimeSTT: realtimestt - INFO - State changed from 'wakeword' to 'inactive' +2025-07-23 11:45:53.207 - RealTimeSTT: realtimestt - INFO - Starting RealTimeSTT +2025-07-23 11:45:53.218 - RealTimeSTT: realtimestt - INFO - Initializing audio recording (creating pyAudio input stream, sample rate: 16000 buffer size: 512 +2025-07-23 11:45:53.223 - RealTimeSTT: realtimestt - INFO - Initializing faster_whisper realtime transcription model tiny, default device: cpu, compute type: default, device index: 0, download root: None +2025-07-23 11:45:53.787 - RealTimeSTT: realtimestt - DEBUG - Faster_whisper realtime speech to text transcription model initialized successfully +2025-07-23 11:45:53.855 - RealTimeSTT: realtimestt - INFO - Successfully loaded openwakeword model: alexa +2025-07-23 11:45:53.856 - RealTimeSTT: realtimestt - INFO - Successfully loaded openwakeword model: hey_mycroft +2025-07-23 11:45:53.856 - RealTimeSTT: realtimestt - INFO - Successfully loaded openwakeword model: hey_jarvis +2025-07-23 11:45:53.856 - RealTimeSTT: realtimestt - INFO - Successfully loaded openwakeword model: hey_rhasspy +2025-07-23 11:45:53.856 - RealTimeSTT: realtimestt - INFO - Successfully loaded openwakeword model: timer +2025-07-23 11:45:53.856 - RealTimeSTT: realtimestt - INFO - Successfully loaded openwakeword model: weather +2025-07-23 11:45:53.856 - RealTimeSTT: realtimestt - DEBUG - Open wake word detection engine initialized successfully +2025-07-23 11:45:53.856 - RealTimeSTT: realtimestt - INFO - Initializing WebRTC voice with Sensitivity 3 +2025-07-23 11:45:53.856 - RealTimeSTT: realtimestt - DEBUG - WebRTC VAD voice activity detection engine initialized successfully +2025-07-23 11:45:54.321 - RealTimeSTT: realtimestt - DEBUG - Silero VAD voice activity detection engine initialized successfully +2025-07-23 11:45:54.321 - RealTimeSTT: realtimestt - DEBUG - Starting realtime worker +2025-07-23 11:45:54.321 - RealTimeSTT: realtimestt - DEBUG - Waiting for main transcription model to start +2025-07-23 11:45:56.738 - RealTimeSTT: realtimestt - DEBUG - Main transcription model ready +2025-07-23 11:45:56.738 - RealTimeSTT: realtimestt - DEBUG - RealtimeSTT initialization completed successfully +2025-07-23 11:45:56.738 - RealTimeSTT: realtimestt - INFO - Setting listen time +2025-07-23 11:45:56.738 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'listening' +2025-07-23 11:45:56.739 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording start +2025-07-23 11:45:56.764 - RealTimeSTT: realtimestt - INFO - State changed from 'listening' to 'wakeword' +2025-07-23 11:46:05.017 - RealTimeSTT: realtimestt - INFO - State changed from 'wakeword' to 'listening' +2025-07-23 11:46:06.359 - RealTimeSTT: realtimestt - INFO - voice activity detected +2025-07-23 11:46:06.359 - RealTimeSTT: realtimestt - INFO - recording started +2025-07-23 11:46:06.359 - RealTimeSTT: realtimestt - INFO - State changed from 'listening' to 'recording' +2025-07-23 11:46:06.359 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording stop +2025-07-23 11:46:06.378 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 14848 +2025-07-23 11:46:06.568 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: Jump. +2025-07-23 11:46:06.578 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 17920 +2025-07-23 11:46:06.754 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: job as +2025-07-23 11:46:06.779 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 20992 +2025-07-23 11:46:06.963 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: Javas. +2025-07-23 11:46:07.512 - RealTimeSTT: realtimestt - INFO - recording stopped +2025-07-23 11:46:07.513 - RealTimeSTT: realtimestt - DEBUG - No samples removed, final audio length: 32768 +2025-07-23 11:46:07.513 - RealTimeSTT: realtimestt - INFO - State changed from 'recording' to 'inactive' +2025-07-23 11:46:07.513 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'transcribing' +2025-07-23 11:46:07.514 - RealTimeSTT: realtimestt - DEBUG - Adding transcription request, no early transcription started +2025-07-23 11:46:07.524 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 11:46:07.625 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 11:46:07.726 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 11:46:07.828 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 11:46:07.858 - RealTimeSTT: realtimestt - INFO - State changed from 'transcribing' to 'inactive' +2025-07-23 11:46:07.896 - RealTimeSTT: realtimestt - DEBUG - Model base completed transcription in 0.38 seconds +2025-07-23 11:46:07.896 - RealTimeSTT: realtimestt - INFO - Setting listen time +2025-07-23 11:46:07.896 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'listening' +2025-07-23 11:46:07.896 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording start +2025-07-23 11:46:36.837 - RealTimeSTT: realtimestt - DEBUG - No samples removed, final audio length: 0 +2025-07-23 11:46:36.838 - RealTimeSTT: realtimestt - INFO - State changed from 'listening' to 'inactive' +2025-07-23 11:46:49.571 - RealTimeSTT: realtimestt - INFO - Starting RealTimeSTT +2025-07-23 11:46:49.583 - RealTimeSTT: realtimestt - INFO - Initializing audio recording (creating pyAudio input stream, sample rate: 16000 buffer size: 512 +2025-07-23 11:46:49.675 - RealTimeSTT: realtimestt - INFO - Successfully loaded openwakeword model: alexa +2025-07-23 11:46:49.676 - RealTimeSTT: realtimestt - INFO - Successfully loaded openwakeword model: hey_mycroft +2025-07-23 11:46:49.676 - RealTimeSTT: realtimestt - INFO - Successfully loaded openwakeword model: hey_jarvis +2025-07-23 11:46:49.676 - RealTimeSTT: realtimestt - INFO - Successfully loaded openwakeword model: hey_rhasspy +2025-07-23 11:46:49.676 - RealTimeSTT: realtimestt - INFO - Successfully loaded openwakeword model: timer +2025-07-23 11:46:49.676 - RealTimeSTT: realtimestt - INFO - Successfully loaded openwakeword model: weather +2025-07-23 11:46:49.676 - RealTimeSTT: realtimestt - DEBUG - Open wake word detection engine initialized successfully +2025-07-23 11:46:49.676 - RealTimeSTT: realtimestt - INFO - Initializing WebRTC voice with Sensitivity 3 +2025-07-23 11:46:49.676 - RealTimeSTT: realtimestt - DEBUG - WebRTC VAD voice activity detection engine initialized successfully +2025-07-23 11:46:50.182 - RealTimeSTT: realtimestt - DEBUG - Silero VAD voice activity detection engine initialized successfully +2025-07-23 11:46:50.183 - RealTimeSTT: realtimestt - DEBUG - Starting realtime worker +2025-07-23 11:46:50.183 - RealTimeSTT: realtimestt - DEBUG - Waiting for main transcription model to start +2025-07-23 11:46:52.860 - RealTimeSTT: realtimestt - DEBUG - Main transcription model ready +2025-07-23 11:46:52.860 - RealTimeSTT: realtimestt - DEBUG - RealtimeSTT initialization completed successfully +2025-07-23 11:46:52.861 - RealTimeSTT: realtimestt - INFO - Setting listen time +2025-07-23 11:46:52.861 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'listening' +2025-07-23 11:46:52.861 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording start +2025-07-23 11:46:52.910 - RealTimeSTT: realtimestt - INFO - State changed from 'listening' to 'wakeword' +2025-07-23 11:47:14.355 - RealTimeSTT: realtimestt - INFO - State changed from 'wakeword' to 'listening' +2025-07-23 11:47:19.667 - RealTimeSTT: realtimestt - INFO - State changed from 'listening' to 'wakeword' +2025-07-23 11:47:33.547 - RealTimeSTT: realtimestt - DEBUG - Receive from stdout pipe +2025-07-23 11:47:33.548 - RealTimeSTT: realtimestt - INFO - None +2025-07-23 11:47:33.569 - RealTimeSTT: realtimestt - DEBUG - No samples removed, final audio length: 0 +2025-07-23 11:47:33.569 - RealTimeSTT: realtimestt - INFO - State changed from 'wakeword' to 'inactive' +2025-07-23 11:47:43.956 - RealTimeSTT: realtimestt - INFO - Starting RealTimeSTT +2025-07-23 11:47:43.969 - RealTimeSTT: realtimestt - INFO - Initializing audio recording (creating pyAudio input stream, sample rate: 16000 buffer size: 512 +2025-07-23 11:47:44.062 - RealTimeSTT: realtimestt - INFO - Successfully loaded openwakeword model: alexa +2025-07-23 11:47:44.062 - RealTimeSTT: realtimestt - INFO - Successfully loaded openwakeword model: hey_mycroft +2025-07-23 11:47:44.062 - RealTimeSTT: realtimestt - INFO - Successfully loaded openwakeword model: hey_jarvis +2025-07-23 11:47:44.062 - RealTimeSTT: realtimestt - INFO - Successfully loaded openwakeword model: hey_rhasspy +2025-07-23 11:47:44.062 - RealTimeSTT: realtimestt - INFO - Successfully loaded openwakeword model: timer +2025-07-23 11:47:44.062 - RealTimeSTT: realtimestt - INFO - Successfully loaded openwakeword model: weather +2025-07-23 11:47:44.062 - RealTimeSTT: realtimestt - DEBUG - Open wake word detection engine initialized successfully +2025-07-23 11:47:44.062 - RealTimeSTT: realtimestt - INFO - Initializing WebRTC voice with Sensitivity 3 +2025-07-23 11:47:44.062 - RealTimeSTT: realtimestt - DEBUG - WebRTC VAD voice activity detection engine initialized successfully +2025-07-23 11:47:44.542 - RealTimeSTT: realtimestt - DEBUG - Silero VAD voice activity detection engine initialized successfully +2025-07-23 11:47:44.543 - RealTimeSTT: realtimestt - DEBUG - Starting realtime worker +2025-07-23 11:47:44.543 - RealTimeSTT: realtimestt - DEBUG - Waiting for main transcription model to start +2025-07-23 11:47:47.097 - RealTimeSTT: realtimestt - DEBUG - Main transcription model ready +2025-07-23 11:47:47.097 - RealTimeSTT: realtimestt - DEBUG - RealtimeSTT initialization completed successfully +2025-07-23 11:47:47.098 - RealTimeSTT: realtimestt - INFO - Setting listen time +2025-07-23 11:47:47.098 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'listening' +2025-07-23 11:47:47.098 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording start +2025-07-23 11:47:47.103 - RealTimeSTT: realtimestt - INFO - State changed from 'listening' to 'wakeword' +2025-07-23 11:48:12.255 - RealTimeSTT: realtimestt - DEBUG - Finishing recording thread +2025-07-23 11:48:12.255 - RealTimeSTT: realtimestt - DEBUG - No samples removed, final audio length: 0 +2025-07-23 11:48:12.255 - RealTimeSTT: realtimestt - INFO - State changed from 'wakeword' to 'inactive' +2025-07-23 11:48:12.256 - RealTimeSTT: realtimestt - DEBUG - Terminating reader process +2025-07-23 11:48:12.843 - RealTimeSTT: realtimestt - DEBUG - Terminating transcription process +2025-07-23 11:48:12.844 - RealTimeSTT: realtimestt - DEBUG - Finishing realtime thread +2025-07-23 11:48:23.902 - RealTimeSTT: realtimestt - INFO - Starting RealTimeSTT +2025-07-23 11:48:23.910 - RealTimeSTT: realtimestt - INFO - Initializing audio recording (creating pyAudio input stream, sample rate: 16000 buffer size: 512 +2025-07-23 11:48:23.987 - RealTimeSTT: realtimestt - INFO - Successfully loaded openwakeword model: alexa +2025-07-23 11:48:23.987 - RealTimeSTT: realtimestt - INFO - Successfully loaded openwakeword model: hey_mycroft +2025-07-23 11:48:23.987 - RealTimeSTT: realtimestt - INFO - Successfully loaded openwakeword model: hey_jarvis +2025-07-23 11:48:23.987 - RealTimeSTT: realtimestt - INFO - Successfully loaded openwakeword model: hey_rhasspy +2025-07-23 11:48:23.987 - RealTimeSTT: realtimestt - INFO - Successfully loaded openwakeword model: timer +2025-07-23 11:48:23.987 - RealTimeSTT: realtimestt - INFO - Successfully loaded openwakeword model: weather +2025-07-23 11:48:23.987 - RealTimeSTT: realtimestt - DEBUG - Open wake word detection engine initialized successfully +2025-07-23 11:48:23.987 - RealTimeSTT: realtimestt - INFO - Initializing WebRTC voice with Sensitivity 3 +2025-07-23 11:48:23.987 - RealTimeSTT: realtimestt - DEBUG - WebRTC VAD voice activity detection engine initialized successfully +2025-07-23 11:48:24.500 - RealTimeSTT: realtimestt - DEBUG - Silero VAD voice activity detection engine initialized successfully +2025-07-23 11:48:24.500 - RealTimeSTT: realtimestt - DEBUG - Starting realtime worker +2025-07-23 11:48:24.500 - RealTimeSTT: realtimestt - DEBUG - Waiting for main transcription model to start +2025-07-23 11:48:26.876 - RealTimeSTT: realtimestt - DEBUG - Main transcription model ready +2025-07-23 11:48:26.876 - RealTimeSTT: realtimestt - DEBUG - RealtimeSTT initialization completed successfully +2025-07-23 11:48:26.876 - RealTimeSTT: realtimestt - INFO - Setting listen time +2025-07-23 11:48:26.876 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'listening' +2025-07-23 11:48:26.876 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording start +2025-07-23 11:48:26.917 - RealTimeSTT: realtimestt - INFO - State changed from 'listening' to 'wakeword' +2025-07-23 11:49:21.806 - RealTimeSTT: realtimestt - DEBUG - Receive from stdout pipe +2025-07-23 11:49:21.806 - RealTimeSTT: realtimestt - INFO - None +2025-07-23 11:49:21.811 - RealTimeSTT: realtimestt - DEBUG - No samples removed, final audio length: 0 +2025-07-23 11:49:21.811 - RealTimeSTT: realtimestt - INFO - State changed from 'wakeword' to 'inactive' +2025-07-23 11:49:28.062 - RealTimeSTT: realtimestt - INFO - Starting RealTimeSTT +2025-07-23 11:49:28.072 - RealTimeSTT: realtimestt - INFO - Initializing audio recording (creating pyAudio input stream, sample rate: 16000 buffer size: 512 +2025-07-23 11:49:28.155 - RealTimeSTT: realtimestt - INFO - Successfully loaded openwakeword model: alexa +2025-07-23 11:49:28.155 - RealTimeSTT: realtimestt - INFO - Successfully loaded openwakeword model: hey_mycroft +2025-07-23 11:49:28.155 - RealTimeSTT: realtimestt - INFO - Successfully loaded openwakeword model: hey_jarvis +2025-07-23 11:49:28.155 - RealTimeSTT: realtimestt - INFO - Successfully loaded openwakeword model: hey_rhasspy +2025-07-23 11:49:28.155 - RealTimeSTT: realtimestt - INFO - Successfully loaded openwakeword model: timer +2025-07-23 11:49:28.155 - RealTimeSTT: realtimestt - INFO - Successfully loaded openwakeword model: weather +2025-07-23 11:49:28.155 - RealTimeSTT: realtimestt - DEBUG - Open wake word detection engine initialized successfully +2025-07-23 11:49:28.155 - RealTimeSTT: realtimestt - INFO - Initializing WebRTC voice with Sensitivity 3 +2025-07-23 11:49:28.155 - RealTimeSTT: realtimestt - DEBUG - WebRTC VAD voice activity detection engine initialized successfully +2025-07-23 11:49:28.641 - RealTimeSTT: realtimestt - DEBUG - Silero VAD voice activity detection engine initialized successfully +2025-07-23 11:49:28.641 - RealTimeSTT: realtimestt - DEBUG - Starting realtime worker +2025-07-23 11:49:28.641 - RealTimeSTT: realtimestt - DEBUG - Waiting for main transcription model to start +2025-07-23 11:49:31.028 - RealTimeSTT: realtimestt - DEBUG - Main transcription model ready +2025-07-23 11:49:31.028 - RealTimeSTT: realtimestt - DEBUG - RealtimeSTT initialization completed successfully +2025-07-23 11:49:31.029 - RealTimeSTT: realtimestt - INFO - Setting listen time +2025-07-23 11:49:31.029 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'listening' +2025-07-23 11:49:31.029 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording start +2025-07-23 11:49:31.056 - RealTimeSTT: realtimestt - INFO - State changed from 'listening' to 'wakeword' +2025-07-23 11:50:34.052 - RealTimeSTT: realtimestt - DEBUG - No samples removed, final audio length: 0 +2025-07-23 11:50:34.053 - RealTimeSTT: realtimestt - INFO - State changed from 'wakeword' to 'inactive' +2025-07-23 11:50:34.103 - RealTimeSTT: realtimestt - ERROR - Wake word processing error: [ONNXRuntimeError] : 6 : RUNTIME_EXCEPTION : Non-zero status code returned while running Max node. Name:'model/tf.math.maximum_11/Maximum' Status Message: GetElementType is not implemented +Traceback (most recent call last): + File "/Users/wongdingfeng/.local/share/uv/tools/tooling/lib/python3.11/site-packages/RealtimeSTT/audio_recorder.py", line 2036, in _recording_worker + wakeword_index = self._process_wakeword(data) + ^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + File "/Users/wongdingfeng/.local/share/uv/tools/tooling/lib/python3.11/site-packages/RealtimeSTT/audio_recorder.py", line 1607, in _process_wakeword + prediction = self.owwModel.predict(pcm) + ^^^^^^^^^^^^^^^^^^^^^^^^^^ + File "/Users/wongdingfeng/.local/share/uv/tools/tooling/lib/python3.11/site-packages/openwakeword/model.py", line 275, in predict + n_prepared_samples = self.preprocessor(x) + ^^^^^^^^^^^^^^^^^^^^ + File "/Users/wongdingfeng/.local/share/uv/tools/tooling/lib/python3.11/site-packages/openwakeword/utils.py", line 463, in __call__ + return self._streaming_features(x) + ^^^^^^^^^^^^^^^^^^^^^^^^^^^ + File "/Users/wongdingfeng/.local/share/uv/tools/tooling/lib/python3.11/site-packages/openwakeword/utils.py", line 443, in _streaming_features + self.embedding_model_predict(x))) + ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + File "/Users/wongdingfeng/.local/share/uv/tools/tooling/lib/python3.11/site-packages/openwakeword/utils.py", line 93, in + self.embedding_model_predict = lambda x: self.embedding_model.run(None, {'input_1': x})[0].squeeze() + ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + File "/Users/wongdingfeng/.local/share/uv/tools/tooling/lib/python3.11/site-packages/onnxruntime/capi/onnxruntime_inference_collection.py", line 273, in run + return self._sess.run(output_names, input_feed, run_options) + ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ +onnxruntime.capi.onnxruntime_pybind11_state.RuntimeException: [ONNXRuntimeError] : 6 : RUNTIME_EXCEPTION : Non-zero status code returned while running Max node. Name:'model/tf.math.maximum_11/Maximum' Status Message: GetElementType is not implemented +2025-07-23 11:50:34.141 - RealTimeSTT: realtimestt - INFO - Setting listen time +2025-07-23 11:50:34.141 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'listening' +2025-07-23 11:50:34.142 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording start +2025-07-23 11:50:43.387 - RealTimeSTT: realtimestt - INFO - Starting RealTimeSTT +2025-07-23 11:50:43.398 - RealTimeSTT: realtimestt - INFO - Initializing audio recording (creating pyAudio input stream, sample rate: 16000 buffer size: 512 +2025-07-23 11:50:43.402 - RealTimeSTT: realtimestt - INFO - Initializing WebRTC voice with Sensitivity 3 +2025-07-23 11:50:43.403 - RealTimeSTT: realtimestt - DEBUG - WebRTC VAD voice activity detection engine initialized successfully +2025-07-23 11:50:43.873 - RealTimeSTT: realtimestt - DEBUG - Silero VAD voice activity detection engine initialized successfully +2025-07-23 11:50:43.873 - RealTimeSTT: realtimestt - DEBUG - Starting realtime worker +2025-07-23 11:50:43.873 - RealTimeSTT: realtimestt - DEBUG - Waiting for main transcription model to start +2025-07-23 11:50:49.464 - RealTimeSTT: realtimestt - DEBUG - Main transcription model ready +2025-07-23 11:50:49.464 - RealTimeSTT: realtimestt - DEBUG - RealtimeSTT initialization completed successfully +2025-07-23 11:50:49.465 - RealTimeSTT: realtimestt - INFO - Setting listen time +2025-07-23 11:50:49.465 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'listening' +2025-07-23 11:50:49.465 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording start +2025-07-23 11:50:50.004 - RealTimeSTT: realtimestt - INFO - voice activity detected +2025-07-23 11:50:50.004 - RealTimeSTT: realtimestt - INFO - recording started +2025-07-23 11:50:50.004 - RealTimeSTT: realtimestt - INFO - State changed from 'listening' to 'recording' +2025-07-23 11:50:50.004 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording stop +2025-07-23 11:50:52.054 - RealTimeSTT: realtimestt - INFO - recording stopped +2025-07-23 11:50:52.054 - RealTimeSTT: realtimestt - DEBUG - No samples removed, final audio length: 49152 +2025-07-23 11:50:52.054 - RealTimeSTT: realtimestt - INFO - State changed from 'recording' to 'inactive' +2025-07-23 11:50:52.146 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'transcribing' +2025-07-23 11:50:52.147 - RealTimeSTT: realtimestt - DEBUG - Adding transcription request, no early transcription started +2025-07-23 11:50:52.156 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 11:50:52.258 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 11:50:52.352 - RealTimeSTT: realtimestt - INFO - State changed from 'transcribing' to 'inactive' +2025-07-23 11:50:52.366 - RealTimeSTT: realtimestt - DEBUG - Model tiny completed transcription in 0.22 seconds +2025-07-23 11:50:52.367 - RealTimeSTT: realtimestt - INFO - Setting listen time +2025-07-23 11:50:52.367 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'listening' +2025-07-23 11:50:52.367 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording start +2025-07-23 11:50:52.823 - RealTimeSTT: realtimestt - INFO - voice activity detected +2025-07-23 11:50:52.824 - RealTimeSTT: realtimestt - INFO - recording started +2025-07-23 11:50:52.824 - RealTimeSTT: realtimestt - INFO - State changed from 'listening' to 'recording' +2025-07-23 11:50:52.824 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording stop +2025-07-23 11:50:55.636 - RealTimeSTT: realtimestt - INFO - recording stopped +2025-07-23 11:50:55.637 - RealTimeSTT: realtimestt - DEBUG - No samples removed, final audio length: 61440 +2025-07-23 11:50:55.637 - RealTimeSTT: realtimestt - INFO - State changed from 'recording' to 'inactive' +2025-07-23 11:50:55.667 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'transcribing' +2025-07-23 11:50:55.667 - RealTimeSTT: realtimestt - DEBUG - Adding transcription request, no early transcription started +2025-07-23 11:50:55.670 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 11:50:55.771 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 11:50:55.873 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 11:50:55.892 - RealTimeSTT: realtimestt - INFO - State changed from 'transcribing' to 'inactive' +2025-07-23 11:50:55.942 - RealTimeSTT: realtimestt - DEBUG - Model tiny completed transcription in 0.27 seconds +2025-07-23 11:50:55.942 - RealTimeSTT: realtimestt - INFO - Setting listen time +2025-07-23 11:50:55.942 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'listening' +2025-07-23 11:50:55.942 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording start +2025-07-23 11:50:56.409 - RealTimeSTT: realtimestt - INFO - voice activity detected +2025-07-23 11:50:56.409 - RealTimeSTT: realtimestt - INFO - recording started +2025-07-23 11:50:56.409 - RealTimeSTT: realtimestt - INFO - State changed from 'listening' to 'recording' +2025-07-23 11:50:56.409 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording stop +2025-07-23 11:50:57.748 - RealTimeSTT: realtimestt - INFO - recording stopped +2025-07-23 11:50:57.749 - RealTimeSTT: realtimestt - DEBUG - No samples removed, final audio length: 37888 +2025-07-23 11:50:57.749 - RealTimeSTT: realtimestt - INFO - State changed from 'recording' to 'inactive' +2025-07-23 11:50:57.785 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'transcribing' +2025-07-23 11:50:57.785 - RealTimeSTT: realtimestt - DEBUG - Adding transcription request, no early transcription started +2025-07-23 11:50:57.806 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 11:50:57.889 - RealTimeSTT: realtimestt - INFO - State changed from 'transcribing' to 'inactive' +2025-07-23 11:50:57.922 - RealTimeSTT: realtimestt - DEBUG - Model tiny completed transcription in 0.14 seconds +2025-07-23 11:50:57.922 - RealTimeSTT: realtimestt - INFO - Setting listen time +2025-07-23 11:50:57.922 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'listening' +2025-07-23 11:50:57.923 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording start +2025-07-23 11:51:46.843 - RealTimeSTT: realtimestt - DEBUG - Receive from stdout pipe +2025-07-23 11:51:46.846 - RealTimeSTT: realtimestt - INFO - None +2025-07-23 11:51:46.861 - RealTimeSTT: realtimestt - DEBUG - No samples removed, final audio length: 0 +2025-07-23 11:51:46.862 - RealTimeSTT: realtimestt - INFO - State changed from 'listening' to 'inactive' +2025-07-23 11:51:46.905 - RealTimeSTT: realtimestt - INFO - Setting listen time +2025-07-23 11:51:46.905 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'listening' +2025-07-23 11:51:46.908 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording start +2025-07-23 11:52:07.918 - RealTimeSTT: realtimestt - INFO - Starting RealTimeSTT +2025-07-23 11:52:07.926 - RealTimeSTT: realtimestt - INFO - Initializing audio recording (creating pyAudio input stream, sample rate: 16000 buffer size: 512 +2025-07-23 11:52:08.009 - RealTimeSTT: realtimestt - INFO - Successfully loaded openwakeword model: alexa +2025-07-23 11:52:08.009 - RealTimeSTT: realtimestt - INFO - Successfully loaded openwakeword model: hey_mycroft +2025-07-23 11:52:08.009 - RealTimeSTT: realtimestt - INFO - Successfully loaded openwakeword model: hey_jarvis +2025-07-23 11:52:08.009 - RealTimeSTT: realtimestt - INFO - Successfully loaded openwakeword model: hey_rhasspy +2025-07-23 11:52:08.009 - RealTimeSTT: realtimestt - INFO - Successfully loaded openwakeword model: timer +2025-07-23 11:52:08.009 - RealTimeSTT: realtimestt - INFO - Successfully loaded openwakeword model: weather +2025-07-23 11:52:08.009 - RealTimeSTT: realtimestt - DEBUG - Open wake word detection engine initialized successfully +2025-07-23 11:52:08.010 - RealTimeSTT: realtimestt - INFO - Initializing WebRTC voice with Sensitivity 3 +2025-07-23 11:52:08.010 - RealTimeSTT: realtimestt - DEBUG - WebRTC VAD voice activity detection engine initialized successfully +2025-07-23 11:52:08.502 - RealTimeSTT: realtimestt - DEBUG - Silero VAD voice activity detection engine initialized successfully +2025-07-23 11:52:08.502 - RealTimeSTT: realtimestt - DEBUG - Starting realtime worker +2025-07-23 11:52:08.502 - RealTimeSTT: realtimestt - DEBUG - Waiting for main transcription model to start +2025-07-23 11:52:11.247 - RealTimeSTT: realtimestt - DEBUG - Main transcription model ready +2025-07-23 11:52:11.247 - RealTimeSTT: realtimestt - DEBUG - RealtimeSTT initialization completed successfully +2025-07-23 11:52:11.247 - RealTimeSTT: realtimestt - INFO - Setting listen time +2025-07-23 11:52:11.248 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'listening' +2025-07-23 11:52:11.248 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording start +2025-07-23 11:52:11.256 - RealTimeSTT: realtimestt - INFO - State changed from 'listening' to 'wakeword' +2025-07-23 11:52:36.382 - RealTimeSTT: realtimestt - DEBUG - No samples removed, final audio length: 0 +2025-07-23 11:52:36.383 - RealTimeSTT: realtimestt - INFO - State changed from 'wakeword' to 'inactive' +2025-07-23 11:52:50.710 - RealTimeSTT: realtimestt - INFO - Starting RealTimeSTT +2025-07-23 11:52:50.720 - RealTimeSTT: realtimestt - INFO - Initializing audio recording (creating pyAudio input stream, sample rate: 16000 buffer size: 512 +2025-07-23 11:52:50.801 - RealTimeSTT: realtimestt - INFO - Successfully loaded openwakeword model: alexa +2025-07-23 11:52:50.802 - RealTimeSTT: realtimestt - INFO - Successfully loaded openwakeword model: hey_mycroft +2025-07-23 11:52:50.802 - RealTimeSTT: realtimestt - INFO - Successfully loaded openwakeword model: hey_jarvis +2025-07-23 11:52:50.802 - RealTimeSTT: realtimestt - INFO - Successfully loaded openwakeword model: hey_rhasspy +2025-07-23 11:52:50.802 - RealTimeSTT: realtimestt - INFO - Successfully loaded openwakeword model: timer +2025-07-23 11:52:50.802 - RealTimeSTT: realtimestt - INFO - Successfully loaded openwakeword model: weather +2025-07-23 11:52:50.802 - RealTimeSTT: realtimestt - DEBUG - Open wake word detection engine initialized successfully +2025-07-23 11:52:50.802 - RealTimeSTT: realtimestt - INFO - Initializing WebRTC voice with Sensitivity 3 +2025-07-23 11:52:50.802 - RealTimeSTT: realtimestt - DEBUG - WebRTC VAD voice activity detection engine initialized successfully +2025-07-23 11:52:51.316 - RealTimeSTT: realtimestt - DEBUG - Silero VAD voice activity detection engine initialized successfully +2025-07-23 11:52:51.316 - RealTimeSTT: realtimestt - DEBUG - Starting realtime worker +2025-07-23 11:52:51.316 - RealTimeSTT: realtimestt - DEBUG - Waiting for main transcription model to start +2025-07-23 11:52:53.840 - RealTimeSTT: realtimestt - DEBUG - Main transcription model ready +2025-07-23 11:52:53.840 - RealTimeSTT: realtimestt - DEBUG - RealtimeSTT initialization completed successfully +2025-07-23 11:52:53.841 - RealTimeSTT: realtimestt - INFO - Setting listen time +2025-07-23 11:52:53.841 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'listening' +2025-07-23 11:52:53.841 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording start +2025-07-23 11:52:53.877 - RealTimeSTT: realtimestt - INFO - State changed from 'listening' to 'wakeword' +2025-07-23 11:53:01.377 - RealTimeSTT: realtimestt - INFO - State changed from 'wakeword' to 'listening' +2025-07-23 11:53:05.274 - RealTimeSTT: realtimestt - INFO - voice activity detected +2025-07-23 11:53:05.274 - RealTimeSTT: realtimestt - INFO - recording started +2025-07-23 11:53:05.274 - RealTimeSTT: realtimestt - INFO - State changed from 'listening' to 'recording' +2025-07-23 11:53:05.274 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording stop +2025-07-23 11:53:06.422 - RealTimeSTT: realtimestt - INFO - recording stopped +2025-07-23 11:53:06.423 - RealTimeSTT: realtimestt - DEBUG - No samples removed, final audio length: 32256 +2025-07-23 11:53:06.423 - RealTimeSTT: realtimestt - INFO - State changed from 'recording' to 'inactive' +2025-07-23 11:53:06.452 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'transcribing' +2025-07-23 11:53:06.453 - RealTimeSTT: realtimestt - DEBUG - Adding transcription request, no early transcription started +2025-07-23 11:53:06.453 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 11:53:06.555 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 11:53:06.656 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 11:53:06.757 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 11:53:06.853 - RealTimeSTT: realtimestt - INFO - State changed from 'transcribing' to 'inactive' +2025-07-23 11:53:06.877 - RealTimeSTT: realtimestt - DEBUG - Model base completed transcription in 0.42 seconds +2025-07-23 11:53:06.877 - RealTimeSTT: realtimestt - INFO - Setting listen time +2025-07-23 11:53:06.877 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'listening' +2025-07-23 11:53:06.877 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording start +2025-07-23 11:54:56.769 - RealTimeSTT: realtimestt - DEBUG - No samples removed, final audio length: 0 +2025-07-23 11:54:56.769 - RealTimeSTT: realtimestt - INFO - State changed from 'listening' to 'inactive' +2025-07-23 11:54:56.894 - RealTimeSTT: realtimestt - INFO - Setting listen time +2025-07-23 11:54:56.895 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'listening' +2025-07-23 11:54:56.909 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording start +2025-07-23 11:59:14.451 - RealTimeSTT: realtimestt - INFO - Starting RealTimeSTT +2025-07-23 11:59:14.459 - RealTimeSTT: realtimestt - INFO - Initializing audio recording (creating pyAudio input stream, sample rate: 16000 buffer size: 512 +2025-07-23 11:59:14.463 - RealTimeSTT: realtimestt - INFO - Initializing faster_whisper realtime transcription model tiny, default device: cpu, compute type: default, device index: 0, download root: None +2025-07-23 11:59:15.000 - RealTimeSTT: realtimestt - DEBUG - Faster_whisper realtime speech to text transcription model initialized successfully +2025-07-23 11:59:15.000 - RealTimeSTT: realtimestt - INFO - Initializing WebRTC voice with Sensitivity 3 +2025-07-23 11:59:15.000 - RealTimeSTT: realtimestt - DEBUG - WebRTC VAD voice activity detection engine initialized successfully +2025-07-23 11:59:15.505 - RealTimeSTT: realtimestt - DEBUG - Silero VAD voice activity detection engine initialized successfully +2025-07-23 11:59:15.505 - RealTimeSTT: realtimestt - DEBUG - Starting realtime worker +2025-07-23 11:59:15.505 - RealTimeSTT: realtimestt - DEBUG - Waiting for main transcription model to start +2025-07-23 11:59:18.121 - RealTimeSTT: realtimestt - DEBUG - Main transcription model ready +2025-07-23 11:59:18.121 - RealTimeSTT: realtimestt - DEBUG - RealtimeSTT initialization completed successfully +2025-07-23 11:59:18.121 - RealTimeSTT: realtimestt - INFO - Setting listen time +2025-07-23 11:59:18.121 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'listening' +2025-07-23 11:59:18.122 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording start +2025-07-23 11:59:24.369 - RealTimeSTT: realtimestt - INFO - voice activity detected +2025-07-23 11:59:24.370 - RealTimeSTT: realtimestt - INFO - recording started +2025-07-23 11:59:24.370 - RealTimeSTT: realtimestt - INFO - State changed from 'listening' to 'recording' +2025-07-23 11:59:24.370 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording stop +2025-07-23 11:59:24.387 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 16896 +2025-07-23 11:59:24.740 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: No. +2025-07-23 11:59:24.740 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 22016 +2025-07-23 11:59:24.934 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: No, that +2025-07-23 11:59:24.941 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 25088 +2025-07-23 11:59:25.136 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: No, that... +2025-07-23 11:59:25.141 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 29184 +2025-07-23 11:59:25.364 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: No, there I am. +2025-07-23 11:59:25.364 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 32256 +2025-07-23 11:59:25.577 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: No, that I have. +2025-07-23 11:59:25.840 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 40448 +2025-07-23 11:59:26.054 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: No, there I have. +2025-07-23 11:59:26.054 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 43520 +2025-07-23 11:59:26.263 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: Now that I have my... +2025-07-23 11:59:26.264 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 46592 +2025-07-23 11:59:26.480 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: No, that I have my own +2025-07-23 11:59:26.480 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 49664 +2025-07-23 11:59:26.694 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: No, that I have my own +2025-07-23 11:59:26.694 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 53760 +2025-07-23 11:59:26.926 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: Now that I have my own tech +2025-07-23 11:59:26.926 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 57856 +2025-07-23 11:59:27.150 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: Now that I have my own thing +2025-07-23 11:59:27.890 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 73216 +2025-07-23 11:59:28.129 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: Now that I have my own thing +2025-07-23 11:59:28.593 - RealTimeSTT: realtimestt - INFO - recording stopped +2025-07-23 11:59:28.593 - RealTimeSTT: realtimestt - DEBUG - No samples removed, final audio length: 83968 +2025-07-23 11:59:28.593 - RealTimeSTT: realtimestt - INFO - State changed from 'recording' to 'inactive' +2025-07-23 11:59:28.676 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'transcribing' +2025-07-23 11:59:28.677 - RealTimeSTT: realtimestt - DEBUG - Adding transcription request, no early transcription started +2025-07-23 11:59:28.688 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 11:59:28.789 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 11:59:28.890 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 11:59:28.991 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 11:59:29.093 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 11:59:29.116 - RealTimeSTT: realtimestt - INFO - State changed from 'transcribing' to 'inactive' +2025-07-23 11:59:29.169 - RealTimeSTT: realtimestt - DEBUG - Model base completed transcription in 0.49 seconds +2025-07-23 11:59:29.170 - RealTimeSTT: realtimestt - INFO - Setting listen time +2025-07-23 11:59:29.170 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'listening' +2025-07-23 11:59:29.170 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording start +2025-07-23 11:59:29.296 - RealTimeSTT: realtimestt - INFO - voice activity detected +2025-07-23 11:59:29.296 - RealTimeSTT: realtimestt - INFO - recording started +2025-07-23 11:59:29.296 - RealTimeSTT: realtimestt - INFO - State changed from 'listening' to 'recording' +2025-07-23 11:59:29.296 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording stop +2025-07-23 11:59:29.314 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 16896 +2025-07-23 11:59:29.544 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: There's a... +2025-07-23 11:59:29.544 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 19968 +2025-07-23 11:59:29.733 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: There's this one. +2025-07-23 11:59:29.745 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 24064 +2025-07-23 11:59:29.935 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: That's a joke. +2025-07-23 11:59:29.945 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 27136 +2025-07-23 11:59:30.137 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: That's a joke. +2025-07-23 11:59:30.146 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 30208 +2025-07-23 11:59:30.347 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: That's a good one. +2025-07-23 11:59:30.898 - RealTimeSTT: realtimestt - INFO - recording stopped +2025-07-23 11:59:30.899 - RealTimeSTT: realtimestt - DEBUG - No samples removed, final audio length: 41984 +2025-07-23 11:59:30.899 - RealTimeSTT: realtimestt - INFO - State changed from 'recording' to 'inactive' +2025-07-23 11:59:30.984 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'transcribing' +2025-07-23 11:59:30.985 - RealTimeSTT: realtimestt - DEBUG - Adding transcription request, no early transcription started +2025-07-23 11:59:31.009 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 11:59:31.110 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 11:59:31.211 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 11:59:31.313 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 11:59:31.340 - RealTimeSTT: realtimestt - INFO - State changed from 'transcribing' to 'inactive' +2025-07-23 11:59:31.366 - RealTimeSTT: realtimestt - DEBUG - Model base completed transcription in 0.38 seconds +2025-07-23 11:59:31.367 - RealTimeSTT: realtimestt - INFO - Setting listen time +2025-07-23 11:59:31.367 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'listening' +2025-07-23 11:59:31.367 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording start +2025-07-23 11:59:31.792 - RealTimeSTT: realtimestt - INFO - voice activity detected +2025-07-23 11:59:31.792 - RealTimeSTT: realtimestt - INFO - recording started +2025-07-23 11:59:31.792 - RealTimeSTT: realtimestt - INFO - State changed from 'listening' to 'recording' +2025-07-23 11:59:31.792 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording stop +2025-07-23 11:59:31.817 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 16896 +2025-07-23 11:59:32.007 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: Oh my god +2025-07-23 11:59:32.017 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 19968 +2025-07-23 11:59:32.183 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: you +2025-07-23 11:59:32.217 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 23040 +2025-07-23 11:59:32.381 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: you +2025-07-23 11:59:32.418 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 26112 +2025-07-23 11:59:32.585 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: you +2025-07-23 11:59:32.944 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 35328 +2025-07-23 11:59:33.145 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: you +2025-07-23 11:59:33.145 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 38400 +2025-07-23 11:59:33.319 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: Is... +2025-07-23 11:59:33.346 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 41472 +2025-07-23 11:59:33.529 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: Is this? +2025-07-23 11:59:33.546 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 44544 +2025-07-23 11:59:33.744 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: Is this what? +2025-07-23 11:59:33.747 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 47616 +2025-07-23 11:59:33.935 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: Is this working? +2025-07-23 11:59:33.948 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 50688 +2025-07-23 11:59:34.140 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: Is this working? +2025-07-23 11:59:34.607 - RealTimeSTT: realtimestt - INFO - recording stopped +2025-07-23 11:59:34.608 - RealTimeSTT: realtimestt - DEBUG - No samples removed, final audio length: 61440 +2025-07-23 11:59:34.608 - RealTimeSTT: realtimestt - INFO - State changed from 'recording' to 'inactive' +2025-07-23 11:59:34.654 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'transcribing' +2025-07-23 11:59:34.655 - RealTimeSTT: realtimestt - DEBUG - Adding transcription request, no early transcription started +2025-07-23 11:59:34.660 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 11:59:34.761 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 11:59:34.862 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 11:59:34.964 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 11:59:35.041 - RealTimeSTT: realtimestt - INFO - State changed from 'transcribing' to 'inactive' +2025-07-23 11:59:35.068 - RealTimeSTT: realtimestt - DEBUG - Model base completed transcription in 0.41 seconds +2025-07-23 11:59:35.068 - RealTimeSTT: realtimestt - INFO - Setting listen time +2025-07-23 11:59:35.068 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'listening' +2025-07-23 11:59:35.068 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording start +2025-07-23 11:59:35.504 - RealTimeSTT: realtimestt - INFO - voice activity detected +2025-07-23 11:59:35.504 - RealTimeSTT: realtimestt - INFO - recording started +2025-07-23 11:59:35.504 - RealTimeSTT: realtimestt - INFO - State changed from 'listening' to 'recording' +2025-07-23 11:59:35.504 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording stop +2025-07-23 11:59:35.520 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 16896 +2025-07-23 11:59:35.614 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: +2025-07-23 11:59:35.721 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 19968 +2025-07-23 11:59:35.805 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: +2025-07-23 11:59:35.922 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 23040 +2025-07-23 11:59:36.052 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: +2025-07-23 11:59:36.122 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 26112 +2025-07-23 11:59:36.204 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: +2025-07-23 11:59:36.785 - RealTimeSTT: realtimestt - INFO - recording stopped +2025-07-23 11:59:36.786 - RealTimeSTT: realtimestt - DEBUG - No samples removed, final audio length: 36864 +2025-07-23 11:59:36.786 - RealTimeSTT: realtimestt - INFO - State changed from 'recording' to 'inactive' +2025-07-23 11:59:36.814 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'transcribing' +2025-07-23 11:59:36.815 - RealTimeSTT: realtimestt - DEBUG - Adding transcription request, no early transcription started +2025-07-23 11:59:36.826 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 11:59:36.928 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 11:59:36.994 - RealTimeSTT: realtimestt - INFO - State changed from 'transcribing' to 'inactive' +2025-07-23 11:59:37.009 - RealTimeSTT: realtimestt - DEBUG - Model base completed transcription in 0.19 seconds +2025-07-23 11:59:37.009 - RealTimeSTT: realtimestt - INFO - Setting listen time +2025-07-23 11:59:37.009 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'listening' +2025-07-23 11:59:37.009 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording start +2025-07-23 11:59:39.346 - RealTimeSTT: realtimestt - INFO - voice activity detected +2025-07-23 11:59:39.346 - RealTimeSTT: realtimestt - INFO - recording started +2025-07-23 11:59:39.346 - RealTimeSTT: realtimestt - INFO - State changed from 'listening' to 'recording' +2025-07-23 11:59:39.346 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording stop +2025-07-23 11:59:39.363 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 16896 +2025-07-23 11:59:39.580 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: You bet. +2025-07-23 11:59:39.580 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 19968 +2025-07-23 11:59:39.761 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: You bet it +2025-07-23 11:59:39.781 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 23040 +2025-07-23 11:59:39.967 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: You better do +2025-07-23 11:59:40.560 - RealTimeSTT: realtimestt - INFO - recording stopped +2025-07-23 11:59:40.560 - RealTimeSTT: realtimestt - DEBUG - No samples removed, final audio length: 35840 +2025-07-23 11:59:40.560 - RealTimeSTT: realtimestt - INFO - State changed from 'recording' to 'inactive' +2025-07-23 11:59:40.628 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'transcribing' +2025-07-23 11:59:40.628 - RealTimeSTT: realtimestt - DEBUG - Adding transcription request, no early transcription started +2025-07-23 11:59:40.651 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 11:59:40.752 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 11:59:40.853 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 11:59:40.955 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 11:59:41.037 - RealTimeSTT: realtimestt - INFO - State changed from 'transcribing' to 'inactive' +2025-07-23 11:59:41.060 - RealTimeSTT: realtimestt - DEBUG - Model base completed transcription in 0.43 seconds +2025-07-23 11:59:41.061 - RealTimeSTT: realtimestt - INFO - Setting listen time +2025-07-23 11:59:41.061 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'listening' +2025-07-23 11:59:41.061 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording start +2025-07-23 11:59:41.519 - RealTimeSTT: realtimestt - INFO - voice activity detected +2025-07-23 11:59:41.519 - RealTimeSTT: realtimestt - INFO - recording started +2025-07-23 11:59:41.519 - RealTimeSTT: realtimestt - INFO - State changed from 'listening' to 'recording' +2025-07-23 11:59:41.519 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording stop +2025-07-23 11:59:41.536 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 16896 +2025-07-23 11:59:41.678 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: +2025-07-23 11:59:41.737 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 19968 +2025-07-23 11:59:41.846 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: +2025-07-23 11:59:41.937 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 23040 +2025-07-23 11:59:42.019 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: +2025-07-23 11:59:42.673 - RealTimeSTT: realtimestt - INFO - recording stopped +2025-07-23 11:59:42.674 - RealTimeSTT: realtimestt - DEBUG - No samples removed, final audio length: 34816 +2025-07-23 11:59:42.674 - RealTimeSTT: realtimestt - INFO - State changed from 'recording' to 'inactive' +2025-07-23 11:59:42.688 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'transcribing' +2025-07-23 11:59:42.688 - RealTimeSTT: realtimestt - DEBUG - Adding transcription request, no early transcription started +2025-07-23 11:59:42.708 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 11:59:42.809 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 11:59:42.884 - RealTimeSTT: realtimestt - INFO - State changed from 'transcribing' to 'inactive' +2025-07-23 11:59:42.904 - RealTimeSTT: realtimestt - DEBUG - Model base completed transcription in 0.22 seconds +2025-07-23 11:59:42.904 - RealTimeSTT: realtimestt - INFO - Setting listen time +2025-07-23 11:59:42.904 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'listening' +2025-07-23 11:59:42.905 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording start +2025-07-23 12:02:21.413 - RealTimeSTT: realtimestt - DEBUG - No samples removed, final audio length: 0 +2025-07-23 12:02:21.414 - RealTimeSTT: realtimestt - INFO - State changed from 'listening' to 'inactive' +2025-07-23 12:02:21.538 - RealTimeSTT: realtimestt - INFO - Setting listen time +2025-07-23 12:02:21.538 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'listening' +2025-07-23 12:02:21.542 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording start +2025-07-23 12:03:01.407 - RealTimeSTT: realtimestt - INFO - Starting RealTimeSTT +2025-07-23 12:03:01.408 - RealTimeSTT: realtimestt - INFO - Using CPU (no GPU acceleration) +2025-07-23 12:03:01.418 - RealTimeSTT: realtimestt - INFO - Initializing audio recording (creating pyAudio input stream, sample rate: 16000 buffer size: 512 +2025-07-23 12:03:01.424 - RealTimeSTT: realtimestt - INFO - Initializing faster_whisper realtime transcription model tiny, default device: cpu, compute type: default, device index: 0, download root: None +2025-07-23 12:03:02.036 - RealTimeSTT: realtimestt - DEBUG - Faster_whisper realtime speech to text transcription model initialized successfully +2025-07-23 12:03:02.036 - RealTimeSTT: realtimestt - INFO - Initializing WebRTC voice with Sensitivity 3 +2025-07-23 12:03:02.036 - RealTimeSTT: realtimestt - DEBUG - WebRTC VAD voice activity detection engine initialized successfully +2025-07-23 12:03:02.619 - RealTimeSTT: realtimestt - DEBUG - Silero VAD voice activity detection engine initialized successfully +2025-07-23 12:03:02.619 - RealTimeSTT: realtimestt - DEBUG - Starting realtime worker +2025-07-23 12:03:02.619 - RealTimeSTT: realtimestt - DEBUG - Waiting for main transcription model to start +2025-07-23 12:03:06.187 - RealTimeSTT: realtimestt - DEBUG - Main transcription model ready +2025-07-23 12:03:06.187 - RealTimeSTT: realtimestt - DEBUG - RealtimeSTT initialization completed successfully +2025-07-23 12:03:06.188 - RealTimeSTT: realtimestt - INFO - Setting listen time +2025-07-23 12:03:06.188 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'listening' +2025-07-23 12:03:06.188 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording start +2025-07-23 12:03:08.906 - RealTimeSTT: realtimestt - INFO - voice activity detected +2025-07-23 12:03:08.907 - RealTimeSTT: realtimestt - INFO - recording started +2025-07-23 12:03:08.907 - RealTimeSTT: realtimestt - INFO - State changed from 'listening' to 'recording' +2025-07-23 12:03:08.907 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording stop +2025-07-23 12:03:08.908 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 15872 +2025-07-23 12:03:09.247 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: Goodbye. +2025-07-23 12:03:09.247 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 22016 +2025-07-23 12:03:09.620 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: What is that? +2025-07-23 12:03:09.744 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 30208 +2025-07-23 12:03:10.094 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: What is the pack? +2025-07-23 12:03:10.095 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 35328 +2025-07-23 12:03:10.449 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: What is the pack and +2025-07-23 12:03:10.450 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 41472 +2025-07-23 12:03:10.888 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: Bagaimana ini beritahu dan awak? +2025-07-23 12:03:10.888 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 47616 +2025-07-23 12:03:11.316 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: Bagaimana saya menurutkan dan awak? +2025-07-23 12:03:11.917 - RealTimeSTT: realtimestt - INFO - recording stopped +2025-07-23 12:03:11.918 - RealTimeSTT: realtimestt - DEBUG - No samples removed, final audio length: 64512 +2025-07-23 12:03:11.918 - RealTimeSTT: realtimestt - INFO - State changed from 'recording' to 'inactive' +2025-07-23 12:03:11.980 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'transcribing' +2025-07-23 12:03:11.980 - RealTimeSTT: realtimestt - DEBUG - Adding transcription request, no early transcription started +2025-07-23 12:03:11.981 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 12:03:12.083 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 12:03:12.184 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 12:03:12.284 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 12:03:12.385 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 12:03:12.487 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 12:03:12.555 - RealTimeSTT: realtimestt - INFO - State changed from 'transcribing' to 'inactive' +2025-07-23 12:03:12.599 - RealTimeSTT: realtimestt - DEBUG - Model base completed transcription in 0.62 seconds +2025-07-23 12:03:12.599 - RealTimeSTT: realtimestt - INFO - Setting listen time +2025-07-23 12:03:12.599 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'listening' +2025-07-23 12:03:12.599 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording start +2025-07-23 12:03:13.133 - RealTimeSTT: realtimestt - INFO - voice activity detected +2025-07-23 12:03:13.133 - RealTimeSTT: realtimestt - INFO - recording started +2025-07-23 12:03:13.133 - RealTimeSTT: realtimestt - INFO - State changed from 'listening' to 'recording' +2025-07-23 12:03:13.134 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording stop +2025-07-23 12:03:13.140 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 16896 +2025-07-23 12:03:13.252 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: +2025-07-23 12:03:13.341 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 19968 +2025-07-23 12:03:13.419 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: +2025-07-23 12:03:13.542 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 23040 +2025-07-23 12:03:13.619 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: +2025-07-23 12:03:14.286 - RealTimeSTT: realtimestt - INFO - recording stopped +2025-07-23 12:03:14.287 - RealTimeSTT: realtimestt - DEBUG - No samples removed, final audio length: 34816 +2025-07-23 12:03:14.287 - RealTimeSTT: realtimestt - INFO - State changed from 'recording' to 'inactive' +2025-07-23 12:03:14.337 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'transcribing' +2025-07-23 12:03:14.337 - RealTimeSTT: realtimestt - DEBUG - Adding transcription request, no early transcription started +2025-07-23 12:03:14.337 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 12:03:14.438 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 12:03:14.487 - RealTimeSTT: realtimestt - INFO - State changed from 'transcribing' to 'inactive' +2025-07-23 12:03:14.532 - RealTimeSTT: realtimestt - DEBUG - Model base completed transcription in 0.19 seconds +2025-07-23 12:03:14.532 - RealTimeSTT: realtimestt - INFO - Setting listen time +2025-07-23 12:03:14.532 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'listening' +2025-07-23 12:03:14.532 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording start +2025-07-23 12:03:16.713 - RealTimeSTT: realtimestt - INFO - voice activity detected +2025-07-23 12:03:16.715 - RealTimeSTT: realtimestt - INFO - recording started +2025-07-23 12:03:16.715 - RealTimeSTT: realtimestt - INFO - State changed from 'listening' to 'recording' +2025-07-23 12:03:16.715 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording stop +2025-07-23 12:03:16.725 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 16896 +2025-07-23 12:03:17.051 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: What? +2025-07-23 12:03:17.051 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 22016 +2025-07-23 12:03:17.409 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: What is it? +2025-07-23 12:03:17.410 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 27136 +2025-07-23 12:03:17.787 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: What is the packet? +2025-07-23 12:03:18.318 - RealTimeSTT: realtimestt - INFO - recording stopped +2025-07-23 12:03:18.318 - RealTimeSTT: realtimestt - DEBUG - No samples removed, final audio length: 41984 +2025-07-23 12:03:18.319 - RealTimeSTT: realtimestt - INFO - State changed from 'recording' to 'inactive' +2025-07-23 12:03:18.355 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'transcribing' +2025-07-23 12:03:18.355 - RealTimeSTT: realtimestt - DEBUG - Adding transcription request, no early transcription started +2025-07-23 12:03:18.355 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 12:03:18.456 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 12:03:18.559 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 12:03:18.660 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 12:03:18.761 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 12:03:18.862 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 12:03:18.908 - RealTimeSTT: realtimestt - INFO - State changed from 'transcribing' to 'inactive' +2025-07-23 12:03:18.963 - RealTimeSTT: realtimestt - DEBUG - Model base completed transcription in 0.61 seconds +2025-07-23 12:03:18.963 - RealTimeSTT: realtimestt - INFO - Setting listen time +2025-07-23 12:03:18.963 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'listening' +2025-07-23 12:03:18.964 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording start +2025-07-23 12:03:22.093 - RealTimeSTT: realtimestt - INFO - voice activity detected +2025-07-23 12:03:22.093 - RealTimeSTT: realtimestt - INFO - recording started +2025-07-23 12:03:22.093 - RealTimeSTT: realtimestt - INFO - State changed from 'listening' to 'recording' +2025-07-23 12:03:22.093 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording stop +2025-07-23 12:03:22.118 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 16896 +2025-07-23 12:03:22.447 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: You got it +2025-07-23 12:03:22.448 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 22016 +2025-07-23 12:03:22.763 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: And back ends. +2025-07-23 12:03:22.763 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 27136 +2025-07-23 12:03:23.138 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: and back and sister. +2025-07-23 12:03:23.626 - RealTimeSTT: realtimestt - INFO - recording stopped +2025-07-23 12:03:23.627 - RealTimeSTT: realtimestt - DEBUG - No samples removed, final audio length: 40960 +2025-07-23 12:03:23.627 - RealTimeSTT: realtimestt - INFO - State changed from 'recording' to 'inactive' +2025-07-23 12:03:23.712 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'transcribing' +2025-07-23 12:03:23.713 - RealTimeSTT: realtimestt - DEBUG - Adding transcription request, no early transcription started +2025-07-23 12:03:23.714 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 12:03:23.815 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 12:03:23.916 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 12:03:24.017 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 12:03:24.118 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 12:03:24.218 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 12:03:24.228 - RealTimeSTT: realtimestt - INFO - State changed from 'transcribing' to 'inactive' +2025-07-23 12:03:24.229 - RealTimeSTT: realtimestt - DEBUG - Model base completed transcription in 0.52 seconds +2025-07-23 12:03:24.229 - RealTimeSTT: realtimestt - INFO - Setting listen time +2025-07-23 12:03:24.229 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'listening' +2025-07-23 12:03:24.230 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording start +2025-07-23 12:03:24.716 - RealTimeSTT: realtimestt - INFO - voice activity detected +2025-07-23 12:03:24.716 - RealTimeSTT: realtimestt - INFO - recording started +2025-07-23 12:03:24.716 - RealTimeSTT: realtimestt - INFO - State changed from 'listening' to 'recording' +2025-07-23 12:03:24.716 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording stop +2025-07-23 12:03:24.733 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 16896 +2025-07-23 12:03:24.812 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: +2025-07-23 12:03:24.934 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 19968 +2025-07-23 12:03:25.014 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: +2025-07-23 12:03:25.134 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 23040 +2025-07-23 12:03:25.214 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: +2025-07-23 12:03:25.358 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 27136 +2025-07-23 12:03:25.492 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: +2025-07-23 12:03:25.559 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 30208 +2025-07-23 12:03:25.644 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: +2025-07-23 12:03:25.760 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 33280 +2025-07-23 12:03:25.841 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: +2025-07-23 12:03:26.320 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 42496 +2025-07-23 12:03:26.401 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: +2025-07-23 12:03:26.520 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 45568 +2025-07-23 12:03:26.602 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: +2025-07-23 12:03:26.721 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 48640 +2025-07-23 12:03:26.805 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: +2025-07-23 12:03:26.922 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 51712 +2025-07-23 12:03:27.013 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: +2025-07-23 12:03:27.123 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 54784 +2025-07-23 12:03:27.207 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: +2025-07-23 12:03:27.594 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 62976 +2025-07-23 12:03:27.693 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: +2025-07-23 12:03:28.043 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 70144 +2025-07-23 12:03:28.132 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: +2025-07-23 12:03:28.750 - RealTimeSTT: realtimestt - INFO - recording stopped +2025-07-23 12:03:28.750 - RealTimeSTT: realtimestt - DEBUG - No samples removed, final audio length: 80896 +2025-07-23 12:03:28.750 - RealTimeSTT: realtimestt - INFO - State changed from 'recording' to 'inactive' +2025-07-23 12:03:28.753 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'transcribing' +2025-07-23 12:03:28.754 - RealTimeSTT: realtimestt - DEBUG - Adding transcription request, no early transcription started +2025-07-23 12:03:28.757 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 12:03:28.858 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 12:03:28.928 - RealTimeSTT: realtimestt - INFO - State changed from 'transcribing' to 'inactive' +2025-07-23 12:03:28.946 - RealTimeSTT: realtimestt - DEBUG - Model base completed transcription in 0.19 seconds +2025-07-23 12:03:28.947 - RealTimeSTT: realtimestt - INFO - Setting listen time +2025-07-23 12:03:28.947 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'listening' +2025-07-23 12:03:28.947 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording start +2025-07-23 12:03:37.946 - RealTimeSTT: realtimestt - DEBUG - No samples removed, final audio length: 0 +2025-07-23 12:03:37.946 - RealTimeSTT: realtimestt - INFO - State changed from 'listening' to 'inactive' +2025-07-23 12:03:38.091 - RealTimeSTT: realtimestt - INFO - Setting listen time +2025-07-23 12:03:38.091 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'listening' +2025-07-23 12:03:38.092 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording start +2025-07-23 12:03:44.774 - RealTimeSTT: realtimestt - INFO - Starting RealTimeSTT +2025-07-23 12:03:44.785 - RealTimeSTT: realtimestt - INFO - Using Apple Metal Performance Shaders (MPS) +2025-07-23 12:03:44.793 - RealTimeSTT: realtimestt - INFO - Initializing audio recording (creating pyAudio input stream, sample rate: 16000 buffer size: 512 +2025-07-23 12:03:44.796 - RealTimeSTT: realtimestt - INFO - Initializing faster_whisper realtime transcription model tiny, default device: mps, compute type: default, device index: 0, download root: None +2025-07-23 12:03:45.210 - RealTimeSTT: realtimestt - ERROR - Error initializing faster_whisper realtime transcription model: unsupported device mps +Traceback (most recent call last): + File "/Users/wongdingfeng/.config/tooling/.venv/lib/python3.11/site-packages/RealtimeSTT/audio_recorder.py", line 823, in __init__ + self.realtime_model_type = faster_whisper.WhisperModel( + ^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + File "/Users/wongdingfeng/.config/tooling/.venv/lib/python3.11/site-packages/faster_whisper/transcribe.py", line 647, in __init__ + self.model = ctranslate2.models.Whisper( + ^^^^^^^^^^^^^^^^^^^^^^^^^^^ +ValueError: unsupported device mps +2025-07-23 12:04:41.790 - RealTimeSTT: realtimestt - INFO - Starting RealTimeSTT +2025-07-23 12:04:41.791 - RealTimeSTT: realtimestt - INFO - Using Apple Metal Performance Shaders (MPS) +2025-07-23 12:04:41.801 - RealTimeSTT: realtimestt - INFO - Initializing audio recording (creating pyAudio input stream, sample rate: 16000 buffer size: 512 +2025-07-23 12:04:41.806 - RealTimeSTT: realtimestt - INFO - Initializing faster_whisper realtime transcription model tiny, default device: mps, compute type: default, device index: 0, download root: None +2025-07-23 12:04:41.849 - RealTimeSTT: realtimestt - ERROR - Error initializing faster_whisper realtime transcription model: unsupported device mps +Traceback (most recent call last): + File "/Users/wongdingfeng/.config/tooling/.venv/lib/python3.11/site-packages/RealtimeSTT/audio_recorder.py", line 823, in __init__ + self.realtime_model_type = faster_whisper.WhisperModel( + ^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + File "/Users/wongdingfeng/.config/tooling/.venv/lib/python3.11/site-packages/faster_whisper/transcribe.py", line 647, in __init__ + self.model = ctranslate2.models.Whisper( + ^^^^^^^^^^^^^^^^^^^^^^^^^^^ +ValueError: unsupported device mps +2025-07-23 12:08:10.941 - RealTimeSTT: realtimestt - INFO - Starting RealTimeSTT +2025-07-23 12:08:10.943 - RealTimeSTT: realtimestt - INFO - Using Apple Metal Performance Shaders (MPS) +2025-07-23 12:08:10.950 - RealTimeSTT: realtimestt - INFO - Initializing audio recording (creating pyAudio input stream, sample rate: 16000 buffer size: 512 +2025-07-23 12:08:10.953 - RealTimeSTT: realtimestt - INFO - Initializing faster_whisper realtime transcription model tiny, default device: mps, compute type: default, device index: 0, download root: None +2025-07-23 12:08:12.114 - RealTimeSTT: realtimestt - ERROR - Error initializing faster_whisper realtime transcription model: unsupported device mps +Traceback (most recent call last): + File "/Users/wongdingfeng/.config/tooling/.venv/lib/python3.11/site-packages/RealtimeSTT/audio_recorder.py", line 823, in __init__ + self.realtime_model_type = faster_whisper.WhisperModel( + ^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + File "/Users/wongdingfeng/.config/tooling/.venv/lib/python3.11/site-packages/faster_whisper/transcribe.py", line 647, in __init__ + self.model = ctranslate2.models.Whisper( + ^^^^^^^^^^^^^^^^^^^^^^^^^^^ +ValueError: unsupported device mps +2025-07-23 12:11:34.782 - RealTimeSTT: realtimestt - INFO - Starting RealTimeSTT +2025-07-23 12:11:34.784 - RealTimeSTT: realtimestt - WARNING - MPS requested but not yet supported by faster_whisper library. Falling back to CPU. +2025-07-23 12:11:34.784 - RealTimeSTT: realtimestt - INFO - Note: MPS support will be available once faster_whisper/CTranslate2 adds MPS support. +2025-07-23 12:11:34.792 - RealTimeSTT: realtimestt - INFO - Initializing audio recording (creating pyAudio input stream, sample rate: 16000 buffer size: 512 +2025-07-23 12:11:34.796 - RealTimeSTT: realtimestt - INFO - Initializing faster_whisper realtime transcription model tiny, default device: cpu, compute type: default, device index: 0, download root: None +2025-07-23 12:11:35.501 - RealTimeSTT: realtimestt - DEBUG - Faster_whisper realtime speech to text transcription model initialized successfully +2025-07-23 12:11:35.501 - RealTimeSTT: realtimestt - INFO - Initializing WebRTC voice with Sensitivity 3 +2025-07-23 12:11:35.501 - RealTimeSTT: realtimestt - DEBUG - WebRTC VAD voice activity detection engine initialized successfully +2025-07-23 12:11:36.176 - RealTimeSTT: realtimestt - DEBUG - Silero VAD voice activity detection engine initialized successfully +2025-07-23 12:11:36.177 - RealTimeSTT: realtimestt - DEBUG - Starting realtime worker +2025-07-23 12:11:36.177 - RealTimeSTT: realtimestt - DEBUG - Waiting for main transcription model to start +2025-07-23 12:11:40.303 - RealTimeSTT: realtimestt - DEBUG - Main transcription model ready +2025-07-23 12:11:40.303 - RealTimeSTT: realtimestt - DEBUG - RealtimeSTT initialization completed successfully +2025-07-23 12:11:40.304 - RealTimeSTT: realtimestt - INFO - Setting listen time +2025-07-23 12:11:40.304 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'listening' +2025-07-23 12:11:40.304 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording start +2025-07-23 12:11:40.844 - RealTimeSTT: realtimestt - INFO - voice activity detected +2025-07-23 12:11:40.844 - RealTimeSTT: realtimestt - INFO - recording started +2025-07-23 12:11:40.844 - RealTimeSTT: realtimestt - INFO - State changed from 'listening' to 'recording' +2025-07-23 12:11:40.844 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording stop +2025-07-23 12:11:40.847 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 15360 +2025-07-23 12:11:40.981 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: +2025-07-23 12:11:41.048 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 18432 +2025-07-23 12:11:41.129 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: +2025-07-23 12:11:41.249 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 21504 +2025-07-23 12:11:41.339 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: +2025-07-23 12:11:41.998 - RealTimeSTT: realtimestt - INFO - recording stopped +2025-07-23 12:11:41.999 - RealTimeSTT: realtimestt - DEBUG - No samples removed, final audio length: 33280 +2025-07-23 12:11:41.999 - RealTimeSTT: realtimestt - INFO - State changed from 'recording' to 'inactive' +2025-07-23 12:11:42.028 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'transcribing' +2025-07-23 12:11:42.029 - RealTimeSTT: realtimestt - DEBUG - Adding transcription request, no early transcription started +2025-07-23 12:11:42.045 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 12:11:42.146 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 12:11:42.213 - RealTimeSTT: realtimestt - INFO - State changed from 'transcribing' to 'inactive' +2025-07-23 12:11:42.247 - RealTimeSTT: realtimestt - DEBUG - Model base completed transcription in 0.22 seconds +2025-07-23 12:11:42.247 - RealTimeSTT: realtimestt - INFO - Setting listen time +2025-07-23 12:11:42.247 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'listening' +2025-07-23 12:11:42.248 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording start +2025-07-23 12:11:43.727 - RealTimeSTT: realtimestt - INFO - voice activity detected +2025-07-23 12:11:43.727 - RealTimeSTT: realtimestt - INFO - recording started +2025-07-23 12:11:43.727 - RealTimeSTT: realtimestt - INFO - State changed from 'listening' to 'recording' +2025-07-23 12:11:43.727 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording stop +2025-07-23 12:11:43.728 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 15872 +2025-07-23 12:11:44.053 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: Okay. +2025-07-23 12:11:44.053 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 22016 +2025-07-23 12:11:44.382 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: Hello. +2025-07-23 12:11:44.938 - RealTimeSTT: realtimestt - INFO - recording stopped +2025-07-23 12:11:44.939 - RealTimeSTT: realtimestt - DEBUG - No samples removed, final audio length: 35840 +2025-07-23 12:11:44.939 - RealTimeSTT: realtimestt - INFO - State changed from 'recording' to 'inactive' +2025-07-23 12:11:45.012 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'transcribing' +2025-07-23 12:11:45.012 - RealTimeSTT: realtimestt - DEBUG - Adding transcription request, no early transcription started +2025-07-23 12:11:45.031 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 12:11:45.139 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 12:11:45.244 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 12:11:45.346 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 12:11:45.447 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 12:11:45.528 - RealTimeSTT: realtimestt - INFO - State changed from 'transcribing' to 'inactive' +2025-07-23 12:11:45.530 - RealTimeSTT: realtimestt - DEBUG - Model base completed transcription in 0.52 seconds +2025-07-23 12:11:45.531 - RealTimeSTT: realtimestt - INFO - Setting listen time +2025-07-23 12:11:45.531 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'listening' +2025-07-23 12:11:45.531 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording start +2025-07-23 12:11:45.964 - RealTimeSTT: realtimestt - INFO - voice activity detected +2025-07-23 12:11:45.964 - RealTimeSTT: realtimestt - INFO - recording started +2025-07-23 12:11:45.964 - RealTimeSTT: realtimestt - INFO - State changed from 'listening' to 'recording' +2025-07-23 12:11:45.965 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording stop +2025-07-23 12:11:45.986 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 16896 +2025-07-23 12:11:46.065 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: +2025-07-23 12:11:46.186 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 19968 +2025-07-23 12:11:46.263 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: +2025-07-23 12:11:46.387 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 23040 +2025-07-23 12:11:46.465 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: +2025-07-23 12:11:46.588 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 26112 +2025-07-23 12:11:46.668 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: +2025-07-23 12:11:47.246 - RealTimeSTT: realtimestt - INFO - recording stopped +2025-07-23 12:11:47.247 - RealTimeSTT: realtimestt - DEBUG - No samples removed, final audio length: 36864 +2025-07-23 12:11:47.247 - RealTimeSTT: realtimestt - INFO - State changed from 'recording' to 'inactive' +2025-07-23 12:11:47.290 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'transcribing' +2025-07-23 12:11:47.291 - RealTimeSTT: realtimestt - DEBUG - Adding transcription request, no early transcription started +2025-07-23 12:11:47.292 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 12:11:47.393 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 12:11:47.464 - RealTimeSTT: realtimestt - INFO - State changed from 'transcribing' to 'inactive' +2025-07-23 12:11:47.502 - RealTimeSTT: realtimestt - DEBUG - Model base completed transcription in 0.21 seconds +2025-07-23 12:11:47.502 - RealTimeSTT: realtimestt - INFO - Setting listen time +2025-07-23 12:11:47.502 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'listening' +2025-07-23 12:11:47.503 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording start +2025-07-23 12:12:07.081 - RealTimeSTT: realtimestt - INFO - voice activity detected +2025-07-23 12:12:07.081 - RealTimeSTT: realtimestt - INFO - recording started +2025-07-23 12:12:07.081 - RealTimeSTT: realtimestt - INFO - State changed from 'listening' to 'recording' +2025-07-23 12:12:07.081 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording stop +2025-07-23 12:12:07.101 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 16896 +2025-07-23 12:12:07.248 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: +2025-07-23 12:12:07.302 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 19968 +2025-07-23 12:12:07.389 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: +2025-07-23 12:12:07.502 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 23040 +2025-07-23 12:12:07.596 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: +2025-07-23 12:12:07.703 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 26112 +2025-07-23 12:12:07.794 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: +2025-07-23 12:12:08.173 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 34304 +2025-07-23 12:12:08.269 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: +2025-07-23 12:12:08.491 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 39424 +2025-07-23 12:12:08.575 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: +2025-07-23 12:12:08.944 - RealTimeSTT: realtimestt - DEBUG - Current realtime buffer size: 46592 +2025-07-23 12:12:09.034 - RealTimeSTT: realtimestt - DEBUG - Realtime text detected: +2025-07-23 12:12:09.644 - RealTimeSTT: realtimestt - INFO - recording stopped +2025-07-23 12:12:09.645 - RealTimeSTT: realtimestt - DEBUG - No samples removed, final audio length: 57344 +2025-07-23 12:12:09.645 - RealTimeSTT: realtimestt - INFO - State changed from 'recording' to 'inactive' +2025-07-23 12:12:09.709 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'transcribing' +2025-07-23 12:12:09.709 - RealTimeSTT: realtimestt - DEBUG - Adding transcription request, no early transcription started +2025-07-23 12:12:09.720 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 12:12:09.821 - RealTimeSTT: realtimestt - DEBUG - Receive from parent_transcription_pipe after sendiung transcription request, transcribe_count: 1 +2025-07-23 12:12:09.915 - RealTimeSTT: realtimestt - INFO - State changed from 'transcribing' to 'inactive' +2025-07-23 12:12:09.928 - RealTimeSTT: realtimestt - DEBUG - Model base completed transcription in 0.22 seconds +2025-07-23 12:12:09.928 - RealTimeSTT: realtimestt - INFO - Setting listen time +2025-07-23 12:12:09.928 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'listening' +2025-07-23 12:12:09.928 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording start +2025-07-23 12:15:05.320 - RealTimeSTT: realtimestt - DEBUG - No samples removed, final audio length: 0 +2025-07-23 12:15:05.321 - RealTimeSTT: realtimestt - INFO - State changed from 'listening' to 'inactive' +2025-07-23 12:15:05.513 - RealTimeSTT: realtimestt - INFO - Setting listen time +2025-07-23 12:15:05.513 - RealTimeSTT: realtimestt - INFO - State changed from 'inactive' to 'listening' +2025-07-23 12:15:05.515 - RealTimeSTT: realtimestt - DEBUG - Waiting for recording start diff --git a/src/tooling/stt_cli.py b/src/tooling/stt_cli.py index c0413ae..58b5b64 100644 --- a/src/tooling/stt_cli.py +++ b/src/tooling/stt_cli.py @@ -28,6 +28,12 @@ try: except ImportError: RUMPS_AVAILABLE = False +try: + import pyautogui + PYAUTOGUI_AVAILABLE = True +except ImportError: + PYAUTOGUI_AVAILABLE = False + # Create STT app that can be imported as a subcommand stt_app = typer.Typer( name="stt", @@ -111,7 +117,7 @@ if RUMPS_AVAILABLE: self.language = "" self.realtime = True self.sensitivity = 0.6 - self.device = "auto" + self.device = "mps" self.wakeword_backend = "openwakeword" self.save_to_file = None @@ -189,14 +195,14 @@ if RUMPS_AVAILABLE: self.wake_word = sender.title self.set_current_wake_word() if self.is_running: - rumps.notification("STT Settings", "Wake Word Changed", f"Restart STT to use '{self.wake_word}'") + rumps.notification("STT Settings", "Wake Word Changed", f"Restart STT to use '{self.wake_word}'", sound=False) def set_model(self, sender): """Set the model from menu selection.""" self.model = sender.title self.set_current_model() if self.is_running: - rumps.notification("STT Settings", "Model Changed", f"Restart STT to use '{self.model}' model") + rumps.notification("STT Settings", "Model Changed", f"Restart STT to use '{self.model}' model", sound=False) def start_stt(self, _): """Start STT functionality.""" @@ -229,9 +235,9 @@ if RUMPS_AVAILABLE: # Configure recorder recorder_config = { "model": self.model, - "wake_words": self.wake_word, - "wakeword_backend": self.wakeword_backend, - "wake_words_sensitivity": self.sensitivity, + # "wake_words": self.wake_word, + # "wakeword_backend": self.wakeword_backend, + # "wake_words_sensitivity": self.sensitivity, "device": self.device, "on_recording_start": self.on_recording_start, "on_recording_stop": self.on_recording_stop, @@ -260,7 +266,7 @@ if RUMPS_AVAILABLE: self.transcription_thread.start() self.update_menu_states() - rumps.notification("STT Started", f"Wake word: {self.wake_word}", f"Model: {self.model} | Device: {self.device}") + rumps.notification("STT Started", f"Wake word: {self.wake_word}", f"Model: {self.model} | Device: {self.device}", sound=False) except Exception as e: rumps.alert("STT Error", f"Failed to start STT: {str(e)}") @@ -288,7 +294,7 @@ if RUMPS_AVAILABLE: self.output_file = None self.update_menu_states() - rumps.notification("STT Stopped", "Speech-to-text has been stopped", "") + rumps.notification("STT Stopped", "Speech-to-text has been stopped", "", sound=False) def pause_stt(self, _): """Pause STT functionality.""" @@ -297,7 +303,7 @@ if RUMPS_AVAILABLE: self.is_paused = True self.update_menu_states() - rumps.notification("STT Paused", "Speech recognition paused", "Resume from menu") + rumps.notification("STT Paused", "Speech recognition paused", "Resume from menu", sound=False) def resume_stt(self, _): """Resume STT functionality.""" @@ -306,7 +312,7 @@ if RUMPS_AVAILABLE: self.is_paused = False self.update_menu_states() - rumps.notification("STT Resumed", "Speech recognition resumed", f"Listening for '{self.wake_word}'") + rumps.notification("STT Resumed", "Speech recognition resumed", f"Listening for '{self.wake_word}'", sound=False) def transcription_loop(self): """Main transcription loop running in background thread.""" @@ -337,8 +343,8 @@ if RUMPS_AVAILABLE: """Handle completed transcriptions.""" if text.strip(): # Show notification with transcription - rumps.notification("Transcription", "Speech detected:", text[:100] + ("..." if len(text) > 100 else "")) - + rumps.notification("Transcription", "Speech detected:", text[:100] + ("..." if len(text) > 100 else ""), sound=False) + pyautogui.typewrite(text + " ") # Save to file if specified if self.output_file: timestamp = datetime.datetime.now().strftime("%H:%M:%S") @@ -395,7 +401,7 @@ if RUMPS_AVAILABLE: if response.clicked and response.text: self.save_to_file = Path.home() / "Documents" / response.text - rumps.notification("File Set", "Transcriptions will be saved to:", str(self.save_to_file)) + rumps.notification("File Set", "Transcriptions will be saved to:", str(self.save_to_file), sound=False) except Exception as e: rumps.alert("Error", f"Could not set output file: {e}") diff --git a/test_realtime_stt.py b/test_realtime_stt.py new file mode 100755 index 0000000..9b498c5 --- /dev/null +++ b/test_realtime_stt.py @@ -0,0 +1,19 @@ +#!/usr/bin/env python3 +""" +Simple RealtimeSTT Test Script + +Test wake word detection and transcription functionality +without the complexity of threading and status bar apps. +""" + +from RealtimeSTT import AudioToTextRecorder + +def process_text(text): + print(text) + +if __name__ == '__main__': + print("Wait until it says 'speak now'") + recorder = AudioToTextRecorder() + + while True: + recorder.text(process_text) \ No newline at end of file diff --git a/uv.lock b/uv.lock index 1de518e..9f6ec60 100644 --- a/uv.lock +++ b/uv.lock @@ -6257,6 +6257,7 @@ source = { editable = "." } dependencies = [ { name = "pillow", version = "11.1.0", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version >= '3.13'" }, { name = "pillow", version = "11.2.1", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version < '3.13'" }, + { name = "pyautogui" }, { name = "pyperclip" }, { name = "python-doctr" }, { name = "realtimestt" }, @@ -6292,6 +6293,7 @@ requires-dist = [ { name = "mss", marker = "extra == 'screenshot-all'", specifier = ">=7.0.0" }, { name = "mss", marker = "extra == 'screenshot-fast'", specifier = ">=7.0.0" }, { name = "pillow", specifier = ">=11.1.0" }, + { name = "pyautogui", specifier = ">=0.9.54" }, { name = "pyautogui", marker = "extra == 'screenshot-all'", specifier = ">=0.9.54" }, { name = "pyautogui", marker = "extra == 'screenshot-full'", specifier = ">=0.9.54" }, { name = "pyperclip", specifier = ">=1.9.0" },