TTS输入

我按照语音识别的例子，将文字转换成梅尔声谱图，然后作为输入，输入进模型，准备做TTS，为什么显示无法将图片进行转换。求明白人告知 E UnicodeDecodeError: 'utf-8' codec can't decode byte 0x93 in position 0: invalid start byte


rknn.config(channel_mean_value='123.675 116.28 103.53 58.395', reorder_channel='0 1 2')
    print('done')

    # Load pytorch model
    print('--> Loading model')
    ret = rknn.load_pytorch(model=model, input_size_list=input_size_list)
    if ret != 0:
        print('Load pytorch model failed!')
        exit(ret)
    print('done')

    # Build model
    print('--> Building model')
    ret = rknn.build(dataset='./ljspeech-mel-00001.npy')
    if ret != 0:
        print('Build pytorch failed!')



   # Export rknn model
    print('--> Export RKNN model')
    ret = rknn.export_rknn('./checkpoint_2000.rknn')
    if ret != 0:
        print('Export resnet_18.rknn failed!')
        exit(ret)
    print('done')

    ret = rknn.load_rknn('./checkpoint_2000.rknn')

    # Set inputs
    img = cv2.imread('./ljspeech-mel-00002.npy')

    print('--> Init runtime environment')
    ret = rknn.init_runtime()
    if ret != 0:
        print('Init runtime environment failed')
        exit(ret)
    print('done')

    # Inference
    print('--> Running model')
    outputs = rknn.inference(inputs=[img])
    show_outputs(softmax(np.array(outputs[0][0])))
    print('done')