pyampact.alignmentUtils.load_audiofile

pyampact.alignmentUtils.load_audiofile(audio_file, mono_mode='mean')[source]
Parameters:

audio_file (str) – The path to the wav file to be loaded.

Returns:

  • audio_data (The loaded wav file as a numpy array.)

  • sr (The original sample rate of the audio file.)

  • Load WAV and (optionally) mix to mono while preserving loudness.

  • mono_mode

    • “mean”: average channels (librosa-style; safest headroom) - do librosa.to_mono()

    • ”equal_power”: sum channels and divide by sqrt(C) (~keeps perceived power)