utils.py 文件源码

def append_zeros_all(fls1, fls2, mode):
    lens1, lens2 = [], []
    for fl1, fl2 in zip(fls1, fls2):
        if mode == 'audio':
            lens1.append(fl1.shape[0]), lens2.append(fl2.shape[0])
        elif mode == 'specs':
            lens1.append(fl1.shape[0]), lens2.append(fl2.shape[0])
        else:
            raise ValueError('Whaaat?')

    inds1, lens1 = list(np.flip(np.argsort(lens1),0)), np.flip(np.sort(lens1),0)
    inds2, lens2 = list(np.flip(np.argsort(lens2),0)), np.flip(np.sort(lens2),0)
    fls1, fls2 = np.array(fls1)[inds1], np.array(fls2)[inds2]
    maxlen = max([max(lens1), max(lens2)])

    mixes = []
    for i, (fl1, fl2) in enumerate(zip(fls1, fls2)):
        if mode == 'audio':
            fls1[i] = np.pad(fl1, (0, maxlen - fl1.shape[0]), 'constant')
            fls2[i] = np.pad(fl2, (0, maxlen - fl2.shape[0]), 'constant')
            mixes.append(fls1[i] + fls2[i])
        elif mode == 'specs':
            fls1[i] = np.pad(fl1, ((0, maxlen - fl1.shape[0]), (0, 0)), 'constant')
            fls2[i] = np.pad(fl2, ((0, maxlen - fl2.shape[0]), (0, 0)), 'constant')
        else:
            raise ValueError('Whaaat?')

    return list(fls1), list(fls2), mixes, lens1, lens2