utils.py

import numpy as np
import pydub


def mp3_write(f: str, sr: int, x: np.ndarray, normalized: bool = False):
    channels = 2 if (x.ndim == 2 and x.shape[1] == 2) else 1
    if normalized:  # normalized array - each item should be a float in [-1, 1)
        y = np.int16(x * 2**15)
    else:
        y = np.int16(x)
    song = pydub.AudioSegment(y.tobytes(), frame_rate=sr, sample_width=2, channels=channels)
    song.export(f, format="mp3", bitrate="256k")


def normalize(audio: np.ndarray, min_y: float = -1.0, max_y: float = 1.0, eps: float = 1e-8):
    max_y -= eps
    min_y += eps
    amax = audio.max()
    amin = audio.min()
    audio = (max_y - min_y) * (audio - amin) / (amax - amin) + min_y
    return audio