refactor: separate optional audioProcessing, add venv to installer

installer.sh

@@ -1,39 +1,47 @@
 #!/bin/bash
 
-# Dependency installation
+# Rotary Phone Audio Guestbook Installer
-echo "Installing dependencies..."
-sudo apt-get update
-if ! sudo apt-get install -y python3-pip python3-gpiozero; then
-    echo "Failed to install system packages."
-    exit 1
-fi
 
-# Use --user flag for pip installations
+echo "Starting the installation process..."
-if ! pip3 install --user pydub pyaudio PyYAML sounddevice; then
-    echo "Failed to install Python packages."
-    exit 1
-fi
 
-# Backup and modify PulseAudio configuration
+# Update and install system dependencies
-echo "Backing up and modifying PulseAudio configuration..."
+echo "Installing additional dependencies..."
+sudo apt-get install -y python3-pip python3-venv python3-gpiozero ffmpeg || {
+    echo "Failed to install required system packages."
+    exit 1
+}
+
+# Set up Python virtual environment for project dependencies
+echo "Setting up Python virtual environment..."
+python3 -m venv ~/rotary-phone-venv || {
+    echo "Failed to create Python virtual environment."
+    exit 1
+}
+source ~/rotary-phone-venv/bin/activate
+
+# Install Python dependencies in the virtual environment
+pip install pydub pyaudio PyYAML sounddevice || {
+    echo "Failed to install Python dependencies."
+    exit 1
+}
+
+# Modify PulseAudio configuration for improved audio handling
+echo "Configuring PulseAudio..."
 sudo cp /etc/pulse/default.pa /etc/pulse/default.pa.backup
-echo "default-fragments = 5" | sudo tee -a /etc/pulse/default.pa
+echo -e "default-fragments = 5\ndefault-fragment-size-msec = 2" | sudo tee -a /etc/pulse/default.pa
-echo "default-fragment-size-msec = 2" | sudo tee -a /etc/pulse/default.pa
 
-# Restart PulseAudio
+# Restart PulseAudio to apply changes
 pulseaudio -k
 pulseaudio --start
 
 # Display available sound cards and devices
-echo "Available sound cards and devices:"
+echo "Listing available sound cards and devices:"
 aplay -l
 
 # Prompt user for ALSA configuration values
 echo "Configuring ALSA..."
 read -p "Enter the card number for the default playback card (e.g., 0, 1): " playback_card
 read -p "Enter the card number for the default capture card (e.g., 0, 1): " capture_card
-
-# Use a consolidated prompt for sample rate to avoid duplication
 read -p "Enter the default sample rate (e.g., 44100): " sample_rate
 while ! [[ "$sample_rate" =~ ^[89][0-9]{3}$|^[1-9][0-9]{4}$|^[1][0-8][0-9]{4}$|192000$ ]]; do
     echo "Invalid sample rate. Please enter a value between 8000 and 192000."
@@ -46,8 +54,10 @@ while ! [[ "$bit_depth" =~ ^(16|24|32)$ ]]; do
     read -p "Enter the bit depth (16, 24, 32): " bit_depth
 done
 
-# Write ALSA configuration to /etc/asound.conf
+# Write ALSA configuration
+echo "Applying ALSA configuration..."
 sudo tee /etc/asound.conf >/dev/null <<EOF
+# Custom ALSA configuration for Rotary Phone Audio Guestbook
 defaults.pcm.rate_converter "samplerate"
 defaults.pcm.dmix.rate $sample_rate
 defaults.pcm.dmix.format S$bit_depth
@@ -67,6 +77,13 @@ ctl.!default {
 }
 EOF
 
+# Test recording and playback functionality
+echo "Testing recording and playback..."
+arecord -D hw:$capture_card,0 -d 5 -f cd test-mic.wav && aplay test-mic.wav || {
+    echo "Test failed. Check your microphone and speaker setup."
+    exit 1
+}
+
 # Get the directory of the currently executing script
 DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
 

src/audioGuestBook.py

@@ -11,7 +11,7 @@ import yaml
 from gpiozero import Button
 from pydub import AudioSegment, playback
 
-import src.audioInterface as audioInterface
+import audioInterface as audioInterface
 
 # Set up logging
 logging.basicConfig(level=logging.INFO)

src/audioInterface.py

@@ -5,9 +5,6 @@ import time
 import wave
 
 import pyaudio
-from pydub import AudioSegment
-from pydub.effects import compress_dynamic_range, normalize
-from pydub.scipy_effects import band_pass_filter
 
 logging.basicConfig(level=logging.INFO)
 logger = logging.getLogger(__name__)
@@ -227,67 +224,3 @@ class AudioInterface:
             logger.info(f"Recording saved to {output_file}")
         except OSError as e:
             logger.error(f"Error writing to file {output_file}. Error: {e}")
-
-    def post_process(self, output_file):
-        """
-        Applies post-processing to the recorded audio and saves the processed files.
-
-        The post-processing includes filtering, normalization, and dynamic range compression.
-        The processed audio is saved in both WAV and MP3 formats.
-
-        Args:
-            output_file (str): The base path for the output files.
-
-        Raises:
-            Exception: If there is an error during post-processing.
-        """
-        try:
-            source = AudioSegment.from_wav(output_file + ".wav")
-            filtered = self.filter_audio(source)
-            normalized = self.normalize_audio(filtered)
-            compressed = self.compress_audio(normalized)
-
-            normalized.export(output_file + "normalized.wav", format="wav")
-            compressed.export(output_file + "compressed.mp3", format="mp3")
-            logger.info("Post-processing completed successfully.")
-        except Exception as e:
-            logger.error(f"Post-processing error: {e}")
-
-    def filter_audio(self, audio):
-        """
-        Applies a band-pass filter to the given audio.
-
-        Args:
-            audio (AudioSegment): The audio segment to be filtered.
-
-        Returns:
-            AudioSegment: The filtered audio segment.
-        """
-        logger.info("Filtering audio.")
-        return band_pass_filter(audio, self.filter_low_freq, self.filter_high_freq)
-
-    def normalize_audio(self, audio):
-        """
-        Normalizes the given audio segment.
-
-        Args:
-            audio (AudioSegment): The audio segment to be normalized.
-
-        Returns:
-            AudioSegment: The normalized audio segment.
-        """
-        logger.info("Normalizing audio.")
-        return normalize(audio)
-
-    def compress_audio(self, audio):
-        """
-        Compresses the dynamic range of the given audio segment.
-
-        Args:
-            audio (AudioSegment): The audio segment to be compressed.
-
-        Returns:
-            AudioSegment: The audio segment with compressed dynamic range.
-        """
-        logger.info("Compressing dynamic range of audio.")
-        return compress_dynamic_range(audio)

src/audioProcessing.py

@@ -0,0 +1,74 @@
+import logging
+from pydub import AudioSegment
+from pydub.effects import compress_dynamic_range, normalize
+from pydub.scipy_effects import band_pass_filter
+
+logging.basicConfig(level=logging.INFO)
+logger = logging.getLogger(__name__)
+
+
+class AudioProcessing:
+
+    def post_process(self, output_file):
+        """
+        Applies post-processing to the recorded audio and saves the processed files.
+
+        The post-processing includes filtering, normalization, and dynamic range compression.
+        The processed audio is saved in both WAV and MP3 formats.
+
+        Args:
+            output_file (str): The base path for the output files.
+
+        Raises:
+            Exception: If there is an error during post-processing.
+        """
+        try:
+            source = AudioSegment.from_wav(output_file + ".wav")
+            filtered = self.filter_audio(source)
+            normalized = self.normalize_audio(filtered)
+            compressed = self.compress_audio(normalized)
+
+            normalized.export(output_file + "normalized.wav", format="wav")
+            compressed.export(output_file + "compressed.mp3", format="mp3")
+            logger.info("Post-processing completed successfully.")
+        except Exception as e:
+            logger.error(f"Post-processing error: {e}")
+
+    def filter_audio(self, audio):
+        """
+        Applies a band-pass filter to the given audio.
+
+        Args:
+            audio (AudioSegment): The audio segment to be filtered.
+
+        Returns:
+            AudioSegment: The filtered audio segment.
+        """
+        logger.info("Filtering audio.")
+        return band_pass_filter(audio, self.filter_low_freq, self.filter_high_freq)
+
+    def normalize_audio(self, audio):
+        """
+        Normalizes the given audio segment.
+
+        Args:
+            audio (AudioSegment): The audio segment to be normalized.
+
+        Returns:
+            AudioSegment: The normalized audio segment.
+        """
+        logger.info("Normalizing audio.")
+        return normalize(audio)
+
+    def compress_audio(self, audio):
+        """
+        Compresses the dynamic range of the given audio segment.
+
+        Args:
+            audio (AudioSegment): The audio segment to be compressed.
+
+        Returns:
+            AudioSegment: The audio segment with compressed dynamic range.
+        """
+        logger.info("Compressing dynamic range of audio.")
+        return compress_dynamic_range(audio)