processing framework

FeatureExtraction/audiopreprocessing.py

@@ -3,18 +3,31 @@ import pickle
 import os
 import numpy as np
 from pathlib import Path
+import logging
 
-DEBUG=True
+logger = logging.getLogger(__name__)
+
+def triggerlog():
+    logger.critical("Testing: info")
 
 def resample_load(input_path : Path, target_sr : int = 16000, mono_audio : bool = False) -> np.ndarray: # AI
-    """Resample audio to target sample rate and save to output directory"""
+    """Load and resamples the audio into `target_sr`.
+
+    Args:
+        input_path (Path): pathlib.Path object to audio file
+        target_sr (int, optional): Target Sample Rate to resample. Defaults to 16000.
+        mono_audio (bool, optional): Load the audio in mono mode. Defaults to False.
+
+    Returns:
+        np.ndarray: _description_
+    """
     # Load audio file with original sample rate
-    if DEBUG: print("[resample_load] Loading audio", input_path)
+    logger.info(f"[resample_load] Loading audio {input_path}")
     audio, orig_sr = librosa.load(input_path, sr=None, mono=mono_audio)
     
     # Resample if necessary
     if orig_sr != target_sr:
-        if DEBUG: print("[resample_load] Resampling to", target_sr)
+        logger.info(f"[resample_load] Resampling to {target_sr}")
         audio = librosa.resample(audio, orig_sr=orig_sr, target_sr=target_sr)
         
     return audio
@@ -24,7 +37,7 @@ def chunk_audio(audio : np.ndarray, sr: int, chunk_length: float = 10.0, overlap
     Chunks audio file into overlapping segments. Only pass in mono audio here.
     
     Args:
-        audio_file: Loaded audio ndarray
+        audio_file: Loaded audio ndarray (one channel only)
         sr: Sample rate for the given audio file
         chunk_length: Length of each chunk in seconds
         overlap: Overlap between chunks in seconds
@@ -32,7 +45,7 @@ def chunk_audio(audio : np.ndarray, sr: int, chunk_length: float = 10.0, overlap
     Returns:
         List of audio chunks, list of chunk positions, and given sample rate
     """
-    if DEBUG: print("[chunk_audio] Chunking audio")
+    logger.info(f"[chunk_audio] Chunking audio ({len(audio) / sr}s)")
     # Calculate chunk size and hop length in samples
     chunk_size = int(chunk_length * sr)
     hop_length = int((chunk_length - overlap) * sr)
@@ -46,10 +59,12 @@ def chunk_audio(audio : np.ndarray, sr: int, chunk_length: float = 10.0, overlap
         chunks.append(chunk)
         positions.append(i / sr)
         k += 1
-        if DEBUG: print("[chunk_audio] Chunked", k, end="\r")
     if k == 0: # The full audio length is less than chunk_length
         chunks = [audio]
         positions = [0.0]
+        logger.info(f"[chunk_audio] Audio less than chunk_length. Returning original audio as chunk\r")
+    else:
+        logger.info(f"[chunk_audio] Audio is split into {k} chunks")
     
     return chunks, positions, sr