audioread.exceptions.NoBackendError 明明安装了FFmpeg 但是一直报错

\MockingBird-main\synthesizer\preprocess.py", line 74, in preprocess_dataset
for speaker_metadata in tqdm(job, dataset, len(speaker_dirs), unit="speakers"):
File "C:\Users\Administrator\anaconda3\lib\site-packages\tqdm\std.py", line 1195, in __iter__
for obj in iterable:
File "C:\Users\Administrator\anaconda3\lib\multiprocessing\pool.py", line 870, in next
raise value
audioread.exceptions.NoBackendError

Start at synthesizer/preprocess.py line 74 and trace the audioread.exceptions.NoBackendError raised during dataset preprocessing. Check the reported FFmpeg installation and the Python environment used by audioread; the issue is done when preprocessing completes without this backend error.

Written by the indexing model from the issue text.