ChatGPT modified code for the option of using OWW

README.md

@@ -9,7 +9,7 @@ Supports announcments, start/continue conversation, and timers.
 
 Install system dependencies (`apt-get`):
 
-* `libportaudio2` or `portaudio19-dev` (for `sounddevice`)
+* `libportaudio2` (for `sounddevice`)
 * `build-essential` (for `pymicro-features`)
 * `libmpv-dev` (for `python-mpv`)
 
@@ -25,25 +25,8 @@ script/setup
 
 Use `script/run` or `python3 -m linux_voice_assistant`
 
-You must specify `--name <NAME>` with a name that will be available in Home Assistant.
-
 See `--help` for more options.
 
-### Microphone
-
-Use `--audio-input-device` to change the microphone device. Use `python3 -m sounddevice` to see the available PortAudio devices. 
-
-The microphone device **must** support 16Khz mono audio.
-
-### Speaker
-
-Use `--audio-output-device` to change the speaker device. Use `mpv --audio-device=help` to see the available MPV devices.
-
-## Wake Word
-
-Change the default wake word with `--wake-model <id>` where `<id>` is the name of a model in the `wakewords` directory. For example, `--wake-model hey_jarvis` will load `wakewords/hey_jarvis.tflite` by default.
-
-
 ## Connecting to Home Assistant
 
 1. In Home Assistant, go to "Settings" -> "Device & services"

linux_voice_assistant.egg-info/PKG-INFO

@@ -0,0 +1,73 @@
+Metadata-Version: 2.4
+Name: linux-voice-assistant
+Version: 1.0.0
+Summary: Linux voice assistant for Home Assistant using the ESPHome protocol
+Author-email: The Home Assistant Authors <hello@home-assistant.io>
+License: Apache-2.0
+Project-URL: Source Code, http://github.com/OHF-Voice/linux-voice-assistant
+Keywords: home,assistant,voice,esphome,linux
+Platform: any
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: Topic :: Text Processing :: Linguistic
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Requires-Python: >=3.9.0
+Description-Content-Type: text/markdown
+License-File: LICENSE.md
+Requires-Dist: aioesphomeapi==37.2.1
+Requires-Dist: sounddevice<1
+Requires-Dist: numpy<3,>=2
+Requires-Dist: pymicro-features==1.0.0
+Provides-Extra: dev
+Requires-Dist: black==24.8.0; extra == "dev"
+Requires-Dist: flake8==7.2.0; extra == "dev"
+Requires-Dist: mypy==1.14.0; extra == "dev"
+Requires-Dist: pylint==3.2.7; extra == "dev"
+Requires-Dist: pytest==8.3.5; extra == "dev"
+Dynamic: license-file
+
+# Linux Voice Assistant
+
+Experimental Linux voice assistant for [Home Assistant][homeassistant] that uses the [ESPHome][esphome] protocol.
+
+Runs on Linux `aarch64` and `x86_64` platforms. Tested with Python 3.13 and Python 3.11.
+Supports announcments, start/continue conversation, and timers.
+
+## Installation
+
+Install system dependencies (`apt-get`):
+
+* `libportaudio2` (for `sounddevice`)
+* `build-essential` (for `pymicro-features`)
+* `libmpv-dev` (for `python-mpv`)
+
+Clone and install project:
+
+``` sh
+git clone https://github.com/OHF-Voice/linux-voice-assistant.git
+cd linux-voice-assistant
+script/setup
+```
+
+## Running
+
+Use `script/run` or `python3 -m linux_voice_assistant`
+
+See `--help` for more options.
+
+## Connecting to Home Assistant
+
+1. In Home Assistant, go to "Settings" -> "Device & services"
+2. Click the "Add integration" button
+3. Choose "ESPHome" and then "Set up another instance of ESPHome"
+4. Enter the IP address of your voice satellite with port 6053
+5. Click "Submit"
+
+<!-- Links -->
+[homeassistant]: https://www.home-assistant.io/
+[esphome]: https://esphome.io/

linux_voice_assistant.egg-info/SOURCES.txt

@@ -0,0 +1,19 @@
+LICENSE.md
+README.md
+pyproject.toml
+setup.cfg
+linux_voice_assistant/__init__.py
+linux_voice_assistant/__main__.py
+linux_voice_assistant/api_server.py
+linux_voice_assistant/entity.py
+linux_voice_assistant/event_bus.py
+linux_voice_assistant/event_led.py
+linux_voice_assistant/microwakeword.py
+linux_voice_assistant/mpv_player.py
+linux_voice_assistant/util.py
+linux_voice_assistant.egg-info/PKG-INFO
+linux_voice_assistant.egg-info/SOURCES.txt
+linux_voice_assistant.egg-info/dependency_links.txt
+linux_voice_assistant.egg-info/requires.txt
+linux_voice_assistant.egg-info/top_level.txt
+linux_voice_assistant.egg-info/zip-safe

linux_voice_assistant.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

linux_voice_assistant.egg-info/requires.txt

@@ -0,0 +1,11 @@
+aioesphomeapi==37.2.1
+sounddevice<1
+numpy<3,>=2
+pymicro-features==1.0.0
+
+[dev]
+black==24.8.0
+flake8==7.2.0
+mypy==1.14.0
+pylint==3.2.7
+pytest==8.3.5

linux_voice_assistant.egg-info/top_level.txt

@@ -0,0 +1 @@
+linux_voice_assistant

linux_voice_assistant.egg-info/zip-safe

@@ -0,0 +1 @@
+

linux_voice_assistant/__main__.py

@@ -42,9 +42,13 @@
 from .api_server import APIServer
 from .entity import ESPHomeEntity, MediaPlayerEntity
 from .microwakeword import MicroWakeWord
+from .openwakeword_client import WyomingWakeClient
 from .mpv_player import MpvMediaPlayer
 from .util import call_all, get_mac, is_arm
 
+from .event_bus import EventBus
+from .event_led import LedEvent
+
 _LOGGER = logging.getLogger(__name__)
 _MODULE_DIR = Path(__file__).parent
 _REPO_DIR = _MODULE_DIR.parent
@@ -78,8 +82,12 @@ class ServerState:
     tts_player: MpvMediaPlayer
     wakeup_sound: str
     timer_finished_sound: str
+    loop: asyncio.AbstractEventLoop
+    event_bus: EventBus
     media_player_entity: Optional[MediaPlayerEntity] = None
     satellite: "Optional[VoiceSatelliteProtocol]" = None
+    wyoming_wake: Optional[WyomingWakeClient] = None
+    use_wyoming_wake: bool = False
 
 
 # -----------------------------------------------------------------------------
@@ -110,11 +118,16 @@ def __init__(self, state: ServerState) -> None:
         self._continue_conversation = False
         self._timer_finished = False
 
+        self.state.event_bus.publish('ready', {})
+        _LOGGER.info('System is ready!')
+
     def handle_voice_event(
         self, event_type: VoiceAssistantEventType, data: Dict[str, str]
     ) -> None:
         _LOGGER.debug("Voice event: type=%s, data=%s", event_type.name, data)
 
+        self.state.event_bus.publish(f'voice_{event_type.name}', data)
+
         if event_type == VoiceAssistantEventType.VOICE_ASSISTANT_RUN_START:
             self._tts_url = data.get("url")
             self._tts_played = False
@@ -157,6 +170,7 @@ def handle_timer_event(
                 self._play_timer_finished()
 
     def handle_message(self, msg: message.Message) -> Iterable[message.Message]:
+        _LOGGER.debug(f'message {msg.__name__}')
         if isinstance(msg, VoiceAssistantEventResponse):
             # Pipeline event
             data: Dict[str, str] = {}
@@ -197,14 +211,11 @@ def handle_message(self, msg: message.Message) -> Iterable[message.Message]:
                     | VoiceAssistantFeature.TIMERS
                 ),
             )
-        elif isinstance(
-            msg,
-            (
-                ListEntitiesRequest,
-                SubscribeHomeAssistantStatesRequest,
-                MediaPlayerCommandRequest,
-            ),
-        ):
+        elif isinstance(msg, (
+            ListEntitiesRequest,
+            SubscribeHomeAssistantStatesRequest,
+            MediaPlayerCommandRequest,
+        ),):
             for entity in self.state.entities:
                 yield from entity.handle_message(msg)
 
@@ -245,13 +256,13 @@ def handle_message(self, msg: message.Message) -> Iterable[message.Message]:
                 break
 
     def handle_audio(self, audio_chunk: bytes) -> None:
-
         if not self._is_streaming_audio:
             return
 
         self.send_messages([VoiceAssistantAudio(data=audio_chunk)])
 
     def wakeup(self) -> None:
+        # Why are we stopping the timer? Wouldn't it be better to delay it?
         if self._timer_finished:
             # Stop timer instead
             self._timer_finished = False
@@ -264,6 +275,10 @@ def wakeup(self) -> None:
         self.send_messages(
             [VoiceAssistantRequest(start=True, wake_word_phrase=wake_word_phrase)]
         )
+
+        self.state.event_bus.publish('voice_wakeword', {'wake_word_phrase': wake_word_phrase})
+
+
         self.duck()
         self._is_streaming_audio = True
         self.state.tts_player.play(self.state.wakeup_sound)
@@ -286,6 +301,8 @@ def play_tts(self) -> None:
         self._tts_played = True
         _LOGGER.debug("Playing TTS response: %s", self._tts_url)
 
+        self.state.event_bus.publish('voice_play_tts', {})
+
         self.state.stop_word.is_active = True
         self.state.tts_player.play(self._tts_url, done_callback=self._tts_finished)
 
@@ -301,6 +318,9 @@ def _tts_finished(self) -> None:
         self.state.stop_word.is_active = False
         self.send_messages([VoiceAssistantAnnounceFinished()])
 
+        # Actual time the TTS stops speaking
+        self.state.event_bus.publish('voice__tts_finished', {})
+
         if self._continue_conversation:
             self.send_messages([VoiceAssistantRequest(start=True)])
             self._is_streaming_audio = True
@@ -328,6 +348,9 @@ def connection_lost(self, exc):
 
 
 def process_audio(state: ServerState):
+    # debug counters
+    chunks_sent = 0
+    last_log = 0.0
 
     try:
         while True:
@@ -340,11 +363,18 @@ def process_audio(state: ServerState):
 
             try:
                 state.satellite.handle_audio(audio_chunk)
-
-                if state.wake_word.is_active and state.wake_word.process_streaming(
-                    audio_chunk
-                ):
-                    state.satellite.wakeup()
+                chunks_sent += 1
+                if state.use_wyoming_wake and chunks_sent % 100 == 0:
+                    _LOGGER.debug("[OWW] chunks_sent=%d (approx %.1fs of audio)", chunks_sent, chunks_sent*0.064)
+
+                if state.use_wyoming_wake:
+                    if state.wyoming_wake:
+                        state.wyoming_wake.send_audio_chunk(audio_chunk)
+                else:
+                    if state.wake_word.is_active and state.wake_word.process_streaming(
+                        audio_chunk
+                    ):
+                        state.satellite.wakeup()
 
                 if state.stop_word.is_active and state.stop_word.process_streaming(
                     audio_chunk
@@ -363,6 +393,8 @@ def process_audio(state: ServerState):
 async def main() -> None:
     parser = argparse.ArgumentParser()
     parser.add_argument("--name", required=True)
+    parser.add_argument("--wake-uri", help="Wyoming wake server URI (e.g., tcp://127.0.0.1:10400)")
+    parser.add_argument("--wake-word-name", help="Wake word name on the Wyoming server (e.g., hal)")
     parser.add_argument(
         "--audio-input-device",
         default="default",
@@ -401,6 +433,12 @@ async def main() -> None:
     logging.basicConfig(level=logging.DEBUG if args.debug else logging.INFO)
     _LOGGER.debug(args)
 
+    use_wyoming = bool(args.wake_uri and args.wake_word_name)
+    wyoming_client = None
+    if use_wyoming:
+        _LOGGER.info("Using Wyoming openWakeWord at %s (name=%s)", args.wake_uri, args.wake_word_name)
+        wyoming_client = WyomingWakeClient(args.wake_uri, args.wake_word_name)
+
     # Load available wake words
     wake_word_dir = Path(args.wake_word_dir)
     available_wake_words: Dict[str, AvailableWakeWord] = {}
@@ -432,6 +470,8 @@ async def main() -> None:
     stop_config_path = wake_word_dir / f"{args.stop_model}.json"
     _LOGGER.debug("Loading stop model: %s", stop_config_path)
     stop_model = MicroWakeWord.from_config(stop_config_path, libtensorflowlite_c_path)
+
+    loop = asyncio.get_running_loop()
 
     state = ServerState(
         name=args.name,
@@ -441,12 +481,28 @@ async def main() -> None:
         available_wake_words=available_wake_words,
         wake_word=wake_model,
         stop_word=stop_model,
+        event_bus=EventBus(),
+        loop=loop,
         music_player=MpvMediaPlayer(device=args.audio_output_device),
         tts_player=MpvMediaPlayer(device=args.audio_output_device),
         wakeup_sound=args.wakeup_sound,
         timer_finished_sound=args.timer_finished_sound,
+        wyoming_wake=wyoming_client,
+        use_wyoming_wake=use_wyoming,
     )
 
+    LedEvent(state)
+
+    # Connect to Wyoming wake server if enabled
+    if state.use_wyoming_wake and state.wyoming_wake:
+        def _on_detect(_name, _ts):
+            _LOGGER.debug("[OWW] detection callback fired name=%s ts=%s", _name, _ts)
+            if state.satellite is not None:
+                state.loop.call_soon_threadsafe(lambda: state.satellite.wakeup())
+        state.wyoming_wake.connect(_on_detect)
+        state.wake_word.is_active = False
+        _LOGGER.debug("[OWW] Local MicroWakeWord disabled; streaming audio to Wyoming")
+
     process_audio_thread = threading.Thread(
         target=process_audio, args=(state,), daemon=True
     )
@@ -455,7 +511,6 @@ async def main() -> None:
     def sd_callback(indata, _frames, _time, _status):
         state.audio_queue.put_nowait(bytes(indata))
 
-    loop = asyncio.get_running_loop()
     server = await loop.create_server(
         lambda: VoiceSatelliteProtocol(state), host=args.host, port=args.port
     )