fix: iMac mic quiet - arecord raw + 12x software gain, strip WAV RIFF header, wakeword api 0.4.0, STT base.en tests, voiceID Adolfo 0.97 enrolled

scripts/build_portaudio.sh

@@ -0,0 +1,16 @@
+#!/bin/bash
+# Build PortAudio locally in user space if system lib missing
+set -e
+cd /tmp
+if [ -d portaudio ]; then
+    echo "portaudio src exists, skipping clone"
+else
+    git clone https://github.com/PortAudio/portaudio.git
+fi
+cd portaudio
+./configure --prefix=$HOME/.local --without-jack
+make -j$(nproc)
+make install
+echo "Installed to ~/.local/lib"
+echo "Add to LD_LIBRARY_PATH: export LD_LIBRARY_PATH=\$HOME/.local/lib:\$LD_LIBRARY_PATH"
+ldconfig -n $HOME/.local/lib || true

scripts/enroll_face.py

@@ -0,0 +1,10 @@
+import sys
+from jarvis.cli import main
+if len(sys.argv) == 1:
+    print("Usage: python scripts/enroll_face.py --name NAME")
+    sys.exit(1)
+if sys.argv[1] != "enroll-face" and not sys.argv[1].startswith("--"):
+    sys.argv.insert(1, "enroll-face")
+elif sys.argv[1].startswith("--"):
+    sys.argv.insert(1, "enroll-face")
+main()

scripts/enroll_speaker.py

@@ -0,0 +1,13 @@
+import sys
+from jarvis.cli import main
+# Pass through args
+sys.argv[0] = "jarvis"
+if len(sys.argv) == 1:
+    print("Usage: python scripts/enroll_speaker.py --name NAME --mic")
+    sys.exit(1)
+# ensure first arg is enroll-speaker
+if sys.argv[1] != "enroll-speaker" and not sys.argv[1].startswith("--"):
+    sys.argv.insert(1, "enroll-speaker")
+elif sys.argv[1].startswith("--"):
+    sys.argv.insert(1, "enroll-speaker")
+main()

scripts/install_service.sh

@@ -0,0 +1,16 @@
+#!/bin/bash
+set -e
+DIR="$(cd "$(dirname "$0")/.." && pwd)"
+SERVICE_FILE="$DIR/systemd/jarvis.service"
+DEST="$HOME/.config/systemd/user/jarvis.service"
+
+mkdir -p "$HOME/.config/systemd/user"
+cp "$SERVICE_FILE" "$DEST"
+
+echo "Reloading systemd user daemon"
+systemctl --user daemon-reload
+echo "Enabling jarvis service"
+systemctl --user enable jarvis.service
+echo "To start: systemctl --user start jarvis"
+echo "To logs: journalctl --user -u jarvis -f"
+echo "To stop: systemctl --user stop jarvis"

scripts/test_mic.py

@@ -0,0 +1,4 @@
+from jarvis.cli import main
+import sys
+sys.argv = ["jarvis","test-mic"]
+main()

scripts/test_stt.py

@@ -0,0 +1,50 @@
+"""Test STT with mic"""
+from jarvis.audio.capture import AudioCapture
+from jarvis.stt.faster_whisper_engine import FasterWhisperSTT
+from jarvis.audio.vad import create_vad
+from jarvis.config import load_config
+import numpy as np, time, collections
+
+cfg = load_config(None)
+vad = create_vad(cfg)
+stt = FasterWhisperSTT(model=cfg.get('stt',{}).get('model','base'), device='cpu', compute_type='int8')
+cap = AudioCapture()
+cap.start()
+
+print("Speak, with 1.5s silence to trigger transcription. Ctrl+C to exit")
+buffer = []
+silence_start = None
+recording = False
+
+try:
+    while True:
+        chunk = cap.read(timeout=0.1)
+        if chunk is None:
+            continue
+        is_speech = vad.is_speech(chunk)
+        if is_speech:
+            if not recording:
+                print("Speech start")
+                recording = True
+            buffer.append(chunk)
+            silence_start = None
+        else:
+            if recording:
+                if silence_start is None:
+                    silence_start = time.time()
+                buffer.append(chunk)
+                if time.time() - silence_start > 1.2:
+                    # transcribe
+                    audio = np.concatenate(buffer)
+                    print(f"Transcribing {len(audio)/16000:.2f}s...")
+                    res = stt.transcribe(audio)
+                    print(f" => {res.get('text')}")
+                    buffer = []
+                    recording = False
+                    silence_start = None
+                    print("Listening again...")
+            # else silence, continue
+except KeyboardInterrupt:
+    pass
+finally:
+    cap.stop()

scripts/test_wakeword.py

@@ -0,0 +1,29 @@
+"""Test wakeword detection without full pipeline"""
+from jarvis.audio.capture import AudioCapture
+from jarvis.audio.wakeword import WakeWordDetector
+from jarvis.audio.vad import create_vad
+from jarvis.config import load_config
+import time
+
+cfg = load_config(None)
+vad = create_vad(cfg)
+ww = WakeWordDetector(models=cfg.get('wakeword',{}).get('models',['hey_jarvis']), threshold=0.45)
+
+cap = AudioCapture()
+cap.start()
+print("Say 'Hey Jarvis'...")
+try:
+    while True:
+        chunk = cap.read(timeout=0.1)
+        if chunk is None:
+            continue
+        # Optional VAD gate
+        if not vad.is_speech(chunk):
+            continue
+        det = ww.detect(chunk)
+        if det:
+            print(f"Wake detected: {det}")
+except KeyboardInterrupt:
+    pass
+finally:
+    cap.stop()