ONNXRuntime inferece failed.

自己录制的ACC视频转码为wav ffmpeg切割为3s等份

from modelscope.tools import run_auto_label

input_wav = "./test_wavs/"
output_data = "./output_training_data/"

ret, report = run_auto_label(input_wav=input_wav, work_dir=output_data, resource_revision="v1.0.4")

执行报错

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
  File "/opt/conda/lib/python3.7/site-packages/tts_autolabel/audio2phone/rapid_paraformer/paraformer_onnx.py", line 58, in __call__
    am_scores, valid_token_lens = self.infer(feats, feats_len)
  File "/opt/conda/lib/python3.7/site-packages/tts_autolabel/audio2phone/rapid_paraformer/paraformer_onnx.py", line 112, in infer
    am_scores, token_nums = self.ort_infer([feats, feats_len])
  File "/opt/conda/lib/python3.7/site-packages/tts_autolabel/audio2phone/rapid_paraformer/utils/utils.py", line 189, in __call__
    raise ONNXRuntimeError('ONNXRuntime inferece failed.') from e
tts_autolabel.audio2phone.rapid_paraformer.utils.utils.ONNXRuntimeError: ONNXRuntime inferece failed.```