处理数据的时候报这个问题

Traceback (most recent call last):
File "/mnt/d/workspace/DiffSinger-master/utils/multiprocess_utils.py", line 13, in chunked_worker
res = map_func(*arg)
File "/mnt/d/workspace/DiffSinger-master/data_gen/singing/binarize.py", line 382, in process_item
cls.get_pitch(wav_fn, wav, mel, ph, res)
File "/mnt/d/workspace/DiffSinger-master/data_gen/singing/binarize.py", line 364, in get_pitch
gt_f0, gt_pitch_coarse = get_pitch(wav, spec, hparams)
File "/mnt/d/workspace/DiffSinger-master/data_gen/tts/data_gen_utils.py", line 174, in get_pitch
f0 = np.pad(f0, [[lpad, rpad]], mode='constant')
File "<array_function internals>", line 200, in pad
File "/home/wjc/anaconda3/envs/svc/lib/python3.8/site-packages/numpy/lib/arraypad.py", line 744, in pad
pad_width = _as_pairs(pad_width, array.ndim, as_index=True)
File "/home/wjc/anaconda3/envs/svc/lib/python3.8/site-packages/numpy/lib/arraypad.py", line 510, in _as_pairs
raise ValueError("index can't contain negative values")
ValueError: index can't contain negative values

Start with data_gen/tts/data_gen_utils.py at get_pitch, where the traceback reaches np.pad, then trace the inputs from data_gen/singing/binarize.py. Reproduce the failure with the reported data and determine which padding calculation becomes negative; done means the failing case is explained and the correction is covered by a suitable regression test.