feat(audio): use PyAV instead of ffmpeg

replaced usage of ffmpeg in favor of PyAV (`av`)

infer/lib/audio.py

@@ -1,9 +1,9 @@
 from io import BufferedWriter, BytesIO
 from pathlib import Path
 from typing import Dict
-import ffmpeg
 import numpy as np
 import av
+from av.audio.resampler import AudioResampler
 
 video_format_dict: Dict[str, str] = {
     "m4a": "mp4",
@@ -38,19 +38,20 @@ def load_audio(file: str, sr: int) -> np.ndarray:
         raise FileNotFoundError(f"File not found: {file}")
 
     try:
-        # https://github.com/openai/whisper/blob/main/whisper/audio.py#L26
-        # This launches a subprocess to decode audio while down-mixing and resampling as necessary.
-        # Requires the ffmpeg CLI and `ffmpeg-python` package to be installed.
-        file = str(clean_path(file))  # 防止小白拷路径头尾带了空格和"和回车
-        out, _ = (
-            ffmpeg.input(file, threads=0)
-            .output("-", format="f32le", acodec="pcm_f32le", ac=1, ar=sr)
-            .run(cmd=["ffmpeg", "-nostdin"], capture_stdout=True, capture_stderr=True)
-        )
+        container = av.open(file)
+        resampler = AudioResampler(format='fltp', layout='mono', rate=sr)
+        decoded_audio = []
+
+        for frame in container.decode(audio=0):
+            frame.pts = None  # Clear presentation timestamp to avoid resampling issues
+            resampled = resampler.resample(frame)
+            decoded_audio.append(resampled.to_ndarray())
+
+        audio = np.concatenate(decoded_audio)
     except Exception as e:
         raise RuntimeError(f"Failed to load audio: {e}")
 
-    return np.frombuffer(out, np.float32).flatten()
+    return audio.flatten()
 
 
 def clean_path(path: str) -> Path: