import ffmpeg,numpy as np def load_audio(file,sr): 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. out, _ = ( ffmpeg.input(file, threads=0) .output("-", format="s16le", acodec="pcm_s16le", ac=1, ar=sr) .run(cmd=["./ffmpeg", "-nostdin"], capture_stdout=True, capture_stderr=True) ) except ffmpeg.Error as e: raise RuntimeError(f"Failed to load audio: {e.stderr.decode()}") from e return np.frombuffer(out, np.int16).flatten().astype(np.float32) / 32768.0 if __name__=='__main__' : print(load_audio(r"C:\CloudMusic\宮野幸子,森下唯 - 月夜に謳う君 -LUNA-.mp3",16000).shape)