From 942c175b902586ae2791ff2343aa03727ec02f9c Mon Sep 17 00:00:00 2001
From: jango-blockchained <info@cryptolinx.de>
Date: Wed, 5 Feb 2025 03:30:15 +0100
Subject: [PATCH] refactor: improve Docker speech container audio configuration
 and user permissions

- Update Dockerfile to enhance audio setup and user management
- Modify setup-audio.sh to add robust PulseAudio socket and device checks
- Add proper user and directory permissions for audio and model directories
- Simplify container startup process and improve audio device detection
---
 .gitignore                   |  4 +++-
 docker/speech/Dockerfile     | 37 ++++++++++++++++++------------------
 docker/speech/setup-audio.sh | 22 +++++++++++++++++++--
 3 files changed, 41 insertions(+), 22 deletions(-)

diff --git a/.gitignore b/.gitignore
index cbc5353..9d8ab3a 100644
--- a/.gitignore
+++ b/.gitignore
@@ -87,4 +87,6 @@ site/
 # Python
 __pycache__/
 *.py[cod]
-*$py.class
\ No newline at end of file
+*$py.class
+
+models/
\ No newline at end of file
diff --git a/docker/speech/Dockerfile b/docker/speech/Dockerfile
index c28de94..80e50bc 100644
--- a/docker/speech/Dockerfile
+++ b/docker/speech/Dockerfile
@@ -33,36 +33,35 @@ RUN apt-get update && apt-get install -y \
     libasound2 \
     libasound2-plugins \
     pulseaudio \
-    && rm -rf /var/lib/apt/lists/*
+    pulseaudio-utils \
+    libpulse0 \
+    libportaudio2 \
+    && rm -rf /var/lib/apt/lists/* \
+    && mkdir -p /var/run/pulse /var/lib/pulse
 
 # Create necessary directories
-RUN mkdir -p /models/wake_word /audio
+RUN mkdir -p /models/wake_word /audio && \
+    chown -R 1000:1000 /models /audio && \
+    mkdir -p /home/user/.config/pulse && \
+    chown -R 1000:1000 /home/user
 
 # Set working directory
 WORKDIR /app
 
-# Copy the wake word detection script
+# Copy the wake word detection script and audio setup script
 COPY wake_word_detector.py .
+COPY setup-audio.sh /setup-audio.sh
+RUN chmod +x /setup-audio.sh
 
 # Set environment variables
 ENV WHISPER_MODEL_PATH=/models \
     WAKEWORD_MODEL_PATH=/models/wake_word \
     PYTHONUNBUFFERED=1 \
-    ASR_MODEL=base.en \
-    ASR_MODEL_PATH=/models
+    PULSE_SERVER=unix:/run/user/1000/pulse/native \
+    HOME=/home/user
 
-# Add resource limits to Python
-ENV PYTHONMALLOC=malloc \
-    MALLOC_TRIM_THRESHOLD_=100000 \
-    PYTHONDEVMODE=1
+# Run as the host user
+USER 1000:1000
 
-# Add healthcheck
-HEALTHCHECK --interval=30s --timeout=10s --start-period=5s --retries=3 \
-    CMD ps aux | grep '[p]ython' || exit 1
-
-# Copy audio setup script
-COPY setup-audio.sh /setup-audio.sh
-RUN chmod +x /setup-audio.sh
-
-# Start command
-CMD ["/bin/bash", "-c", "/setup-audio.sh && python -u wake_word_detector.py"] 
\ No newline at end of file
+# Start the application
+CMD ["/setup-audio.sh"] 
\ No newline at end of file
diff --git a/docker/speech/setup-audio.sh b/docker/speech/setup-audio.sh
index e50466d..dc5c033 100755
--- a/docker/speech/setup-audio.sh
+++ b/docker/speech/setup-audio.sh
@@ -1,7 +1,25 @@
 #!/bin/bash
 
-# Wait for PulseAudio to be ready
-sleep 2
+# Wait for PulseAudio socket to be available
+while [ ! -e /run/user/1000/pulse/native ]; do
+    echo "Waiting for PulseAudio socket..."
+    sleep 1
+done
+
+# Test PulseAudio connection
+pactl info || {
+    echo "Failed to connect to PulseAudio server"
+    exit 1
+}
+
+# List audio devices
+pactl list sources || {
+    echo "Failed to list audio devices"
+    exit 1
+}
+
+# Start the wake word detector
+python /app/wake_word_detector.py
 
 # Mute the monitor to prevent feedback
 pactl set-source-mute alsa_output.pci-0000_00_1b.0.analog-stereo.monitor 1