Function normalize_alignment_word

tests/warmbench.py:1513–1514

(value: str)

    audio, sample_rate = librosa.load(source, sr=None, mono=False)
    audio = np.asarray(audio, dtype=np.float32)
    if audio.ndim == 2:
        if audio.shape[0] <= 8 and audio.shape[1] > audio.shape[0]:
            audio = audio.T
        audio = audio.mean(axis=-1).astype(np.float32)