c31724c92b
P2 — homeai-llm: - Fix ollama launchd plist path for Apple Silicon (/opt/homebrew/bin/ollama) - Add Modelfiles for local GGUF models: llama3.3:70b, qwen3:32b, codestral:22b (registered via `ollama create` — no re-download needed) P3 — homeai-voice: - Wyoming STT: wyoming-faster-whisper, large-v3 model, port 10300 - Wyoming TTS: custom Kokoro ONNX server (wyoming_kokoro_server.py), port 10301 Voice af_heart; models at ~/models/kokoro/ - Wake word: openWakeWord daemon (hey_jarvis), notifies OpenClaw at /wake - launchd plists for all three services + load-all-launchd.sh helper - Smoke test: wyoming/test-pipeline.sh — 3/3 passing HA Wyoming integration pending manual UI config (STT 10.0.0.200:10300, TTS 10.0.0.200:10301). Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
111 lines
3.3 KiB
Python
111 lines
3.3 KiB
Python
#!/usr/bin/env python3
|
|
"""Always-on wake word detection daemon using openWakeWord.
|
|
|
|
Listens on the default microphone, fires an HTTP POST to --notify-url
|
|
when the wake word is detected.
|
|
|
|
Usage:
|
|
python wakeword_daemon.py --wake-word hey_jarvis --notify-url http://localhost:8080/wake
|
|
"""
|
|
|
|
import argparse
|
|
import logging
|
|
import time
|
|
import urllib.request
|
|
import json
|
|
import numpy as np
|
|
|
|
_LOGGER = logging.getLogger(__name__)
|
|
|
|
SAMPLE_RATE = 16000
|
|
CHUNK_SIZE = 1280 # ~80ms at 16kHz — recommended by openWakeWord
|
|
|
|
|
|
def notify(url: str, wake_word: str, score: float):
|
|
payload = json.dumps({"wake_word": wake_word, "score": float(score)}).encode()
|
|
try:
|
|
req = urllib.request.Request(
|
|
url,
|
|
data=payload,
|
|
headers={"Content-Type": "application/json"},
|
|
method="POST",
|
|
)
|
|
with urllib.request.urlopen(req, timeout=2):
|
|
pass
|
|
_LOGGER.info("Wake word '%s' detected (score=%.3f) — notified %s", wake_word, score, url)
|
|
except Exception as e:
|
|
_LOGGER.warning("Failed to notify %s: %s", url, e)
|
|
|
|
|
|
def main():
|
|
parser = argparse.ArgumentParser()
|
|
parser.add_argument("--wake-word", default="hey_jarvis")
|
|
parser.add_argument("--notify-url", default="http://localhost:8080/wake")
|
|
parser.add_argument("--threshold", type=float, default=0.5)
|
|
parser.add_argument("--cooldown", type=float, default=3.0, help="Seconds between triggers")
|
|
parser.add_argument("--model-dir", default=None, help="Path to custom .onnx wake word model")
|
|
parser.add_argument("--debug", action="store_true")
|
|
args = parser.parse_args()
|
|
|
|
logging.basicConfig(
|
|
level=logging.DEBUG if args.debug else logging.INFO,
|
|
format="%(asctime)s %(levelname)s %(message)s",
|
|
)
|
|
|
|
try:
|
|
import pyaudio
|
|
except ImportError:
|
|
_LOGGER.error("pyaudio not installed. Run: pip install pyaudio")
|
|
raise SystemExit(1)
|
|
|
|
import openwakeword
|
|
from openwakeword.model import Model
|
|
|
|
_LOGGER.info("Loading wake word model: %s", args.wake_word)
|
|
|
|
model_paths = []
|
|
if args.model_dir:
|
|
import os, glob
|
|
model_paths = glob.glob(os.path.join(args.model_dir, "*.onnx"))
|
|
|
|
oww = Model(
|
|
wakeword_models=model_paths if model_paths else [args.wake_word],
|
|
inference_framework="onnx",
|
|
)
|
|
|
|
audio = pyaudio.PyAudio()
|
|
stream = audio.open(
|
|
rate=SAMPLE_RATE,
|
|
channels=1,
|
|
format=pyaudio.paInt16,
|
|
input=True,
|
|
frames_per_buffer=CHUNK_SIZE,
|
|
)
|
|
|
|
_LOGGER.info("Listening for wake word '%s'...", args.wake_word)
|
|
last_trigger = 0.0
|
|
|
|
try:
|
|
while True:
|
|
raw = stream.read(CHUNK_SIZE, exception_on_overflow=False)
|
|
chunk = np.frombuffer(raw, dtype=np.int16)
|
|
oww.predict(chunk)
|
|
|
|
for ww, scores in oww.prediction_buffer.items():
|
|
score = scores[-1] if scores else 0.0
|
|
if score >= args.threshold:
|
|
now = time.time()
|
|
if now - last_trigger >= args.cooldown:
|
|
last_trigger = now
|
|
notify(args.notify_url, ww, score)
|
|
except KeyboardInterrupt:
|
|
pass
|
|
finally:
|
|
stream.stop_stream()
|
|
stream.close()
|
|
audio.terminate()
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main()
|