wav2lip 模型训练报错：ValueError: setting an array element with a sequence. The requested array has an inhomogeneous shape after 1 dimensions. The detected shape was (16,) + inhomogeneous part

[Ikaros-521]

Traceback (most recent call last):
  File "D:\AI-20240726\metahuman-stream\metahuman-stream\wav2lip\genavatar.py", line 114, in <module>
    face_det_results = face_detect(frames)
  File "D:\AI-20240726\metahuman-stream\metahuman-stream\wav2lip\genavatar.py", line 71, in face_detect
    predictions.extend(detector.get_detections_for_batch(np.array(images[i:i + batch_size])))
ValueError: setting an array element with a sequence. The requested array has an inhomogeneous shape after 1 dimensions. The detected shape was (16,) + inhomogeneous part.