报错AssertionError: choose a window size 400 that is

在学习和测试cosyvoice和sensevoice模型时，无意发现用cosyvoice产生的a1.wav音频给sensevoice测试时，报错：
File "/root/anaconda3/envs/cosyvoice/lib/python3.8/site-packages/torchaudio/compliance/kaldi.py", line 591, in fbank
waveform, window_shift, window_size, padded_window_size = _get_waveform_and_window_properties(
File "/root/anaconda3/envs/cosyvoice/lib/python3.8/site-packages/torchaudio/compliance/kaldi.py", line 142, in _get_waveform_and_window_properties
assert 2 <= window_size <= len(waveform), "choose a window size {} that is [2, {}]".format(
AssertionError: choose a window size 400 that is [2, 160]
然后在sensevoice的webui页面里也看到错误，而没有得到转出来的文字。
一开始以为是音频时长超过30s，也确实用ffmpeg裁剪这个a1.wav 到30s内确实就可以正常转成文字了。但是我用其他的明显超过30秒的音频测试发现又没有这个问题。感觉跟奇怪。
如果需要我可以提供这个a1.wav。