refactor(audio): store all of the audio related functions in the infer.lib.audio

refactors previous commit to have singular functions for each task, all located in `infer.lib.audio`

infer/lib/audio.py

@@ -3,6 +3,7 @@ from pathlib import Path
 from typing import Dict
 import numpy as np
 import av
+import os
 from av.audio.resampler import AudioResampler
 
 video_format_dict: Dict[str, str] = {
@@ -54,6 +55,67 @@ def load_audio(file: str, sr: int) -> np.ndarray:
 
     return audio.flatten()
 
+def downsample_audio(input_path: str, output_path: str, format: str) -> None:
+    if not os.path.exists(input_path): return
+    
+    input_container = av.open(input_path)
+    output_container = av.open(output_path, 'w')
+
+    # Create a stream in the output container
+    input_stream = input_container.streams.audio[0]
+    output_stream = output_container.add_stream(format)
+
+    output_stream.bit_rate = 128_000 # 128kb/s (equivalent to -q:a 2)
+
+    # Copy packets from the input file to the output file
+    for packet in input_container.demux(input_stream):
+        for frame in packet.decode():
+            for out_packet in output_stream.encode(frame):
+                output_container.mux(out_packet)
+
+    for packet in output_stream.encode():
+        output_container.mux(packet)
+    
+    # Close the containers
+    input_container.close()
+    output_container.close()
+
+    try: # Remove the original file
+        os.remove(input_path)
+    except Exception as e:
+        print(f"Failed to remove the original file: {e}")
+
+def resample_audio(input_path: str, output_path: str, format: str, sr: int, layout: str) -> None:
+    if not os.path.exists(input_path): return
+    
+    input_container = av.open(input_path)
+    output_container = av.open(output_path, 'w')
+
+    # Create a stream in the output container
+    input_stream = input_container.streams.audio[0]
+    output_stream = output_container.add_stream(format, rate=sr, layout=layout)
+    
+    resampler = AudioResampler(format, layout, sr)
+
+    # Copy packets from the input file to the output file
+    for packet in input_container.demux(input_stream):
+        for frame in packet.decode():
+            frame.pts = None  # Clear presentation timestamp to avoid resampling issues
+            resampled = resampler.resample(frame)
+            for out_packet in output_stream.encode(resampled):
+                output_container.mux(out_packet)
+
+    for packet in output_stream.encode():
+        output_container.mux(packet)
+    
+    # Close the containers
+    input_container.close()
+    output_container.close()
+
+    try: # Remove the original file
+        os.remove(input_path)
+    except Exception as e:
+        print(f"Failed to remove the original file: {e}")
 
 def clean_path(path: str) -> Path:
     return Path(path.strip(' "\n')).resolve()