needs to be float type for load to work

.gitignore

@@ -1,5 +1,6 @@
 /data
 /logs
+src/paths.py
 
 # Python
 __pycache__/

src/capture_audio.py

@@ -4,6 +4,7 @@
 import time
 import sys
 
+from paths import AUDIO_PATH
 from logging_config import logger
 
 # duration in seconds
@@ -47,5 +48,5 @@ def capture_audio_to_file(output_file, duration=5, sample_rate=44100, channels=1
 # test
 if __name__ == "__main__":
     timestr = time.strftime("%Y%m%d_%H%M")
-    out_filename = f"../data/audio_samples/recorded_audio_{timestr}.wav"
+    out_filename = f"{AUDIO_PATH}/recorded_audio_{timestr}.wav"
     capture_audio_to_file(out_filename, duration=5)

src/logging_config.py

@@ -1,9 +1,10 @@
 import logging
 import sys
 import traceback
+from paths import DIR_PATH
 
 logging.basicConfig(
-    filename='./logs/error.log',
+    filename=f'{DIR_PATH}logs/error.log',
     level=logging.ERROR,
     format='%(asctime)s - %(levelname)s - %(message)s'
 )

src/process_audio.py

@@ -1,14 +1,14 @@
 import librosa
 import librosa.display
+import numpy as np
 import matplotlib.pyplot as plt
 from logging_config import logger
-
+from paths import AUDIO_PATH
 
 def process_audio_file(audio_file):
     try:
         # Load the audio file
-        y, sr = librosa.load(audio_file)
-
+        y, sr = librosa.load(audio_file, dtype=np.float32)
         # Extract audio features (e.g., MFCCs)
         mfccs = librosa.feature.mfcc(y=y, sr=sr, n_mfcc=40)
 
@@ -32,5 +32,5 @@ def process_audio_file(audio_file):
 
 
 if __name__ == "__main__":
-    recorded_audio_file = "../data/audio_samples/recorded_audio_20230911_1655.wav"
+    recorded_audio_file = f"{AUDIO_PATH}recorded_audio_20230911_1655.wav"
     process_audio_file(recorded_audio_file)