drumscript.audio_processor.audio_loader.load_audio

load_audio(audio_path: str, sr: int | None = None) → tuple[ndarray, int][source]

Load an audio file and optionally resample it.

Parameters:

  • audio_path (str) – Path to the audio file (.wav, .mp3, .flac, .ogg, etc.).

  • sr (int or None) – Target sample rate in Hz. - None (default): load at the file’s native sample rate (no resampling). - An integer (e.g. 44100): resample to that rate.

Returns:

Tuple of (audio_data, sample_rate).

Return type:

tuple[np.ndarray, int]

Raises:

FileNotFoundError – If the file does not exist.

Examples:

Load at native sample rate (for exploration / notebooks):

import drumscript as ds
audio, sr = ds.load_audio("my_drum_loop.wav")
print(f"Native rate: {sr} Hz")

Load and resample to 44100 Hz (for the transcription pipeline):

from drumscript.notation_generator.constants import SAMPLE_RATE
audio, sr = ds.load_audio("my_drum_loop.wav", sr=SAMPLE_RATE)