Voice separation fails.

After 5.6/5.6 of separation processing got done this message was in the output information window.

50 min audiofile to have music removed.wav.reformatted.wav->Traceback (most recent call last):
File "E:\Voice apps\RVC1006Nvidia\runtime\lib\site-packages\librosa\core\audio.py", line 155, in load
context = sf.SoundFile(path)
File "E:\Voice apps\RVC1006Nvidia\runtime\lib\site-packages\soundfile.py", line 655, in init
self._file = self._open(file, mode_int, closefd)
File "E:\Voice apps\RVC1006Nvidia\runtime\lib\site-packages\soundfile.py", line 1213, in _open
raise LibsndfileError(err, prefix="Error opening {0!r}: ".format(self.name))
soundfile.LibsndfileError: Error opening 'E:\Voice apps\RVC1006Nvidia\TEMP/50 min audiofile to have music removed.wav.reformatted.wav': System error.

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "E:\Voice apps\RVC1006Nvidia\infer\modules\uvr5\modules.py", line 74, in uvr
pre_fun.path_audio(
File "E:\Voice apps\RVC1006Nvidia\infer\modules\uvr5\vr.py", line 63, in path_audio
) = librosa.core.load( # 理论上librosa读取可能对某些音频有bug，应该上ffmpeg读取，但是太麻烦了弃坑
File "E:\Voice apps\RVC1006Nvidia\runtime\lib\site-packages\librosa\util\decorators.py", line 104, in inner_f
return f(**kwargs)
File "E:\Voice apps\RVC1006Nvidia\runtime\lib\site-packages\librosa\core\audio.py", line 174, in load
y, sr_native = __audioread_load(path, offset, duration, dtype)
File "E:\Voice apps\RVC1006Nvidia\runtime\lib\site-packages\librosa\core\audio.py", line 198, in _audioread_load
with audioread.audio_open(path) as input_file:
File "E:\Voice apps\RVC1006Nvidia\runtime\lib\site-packages\audioread_init.py", line 111, in audio_open
return BackendClass(path)
File "E:\Voice apps\RVC1006Nvidia\runtime\lib\site-packages\audioread\rawread.py", line 62, in init
self._fh = open(filename, 'rb')
FileNotFoundError: [Errno 2] No such file or directory: 'E:\Voice apps\RVC1006Nvidia\TEMP/50 min audiofile to have music removed.wav.reformatted.wav'

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "E:\Voice apps\RVC1006Nvidia\runtime\lib\site-packages\librosa\core\audio.py", line 155, in load
context = sf.SoundFile(path)
File "E:\Voice apps\RVC1006Nvidia\runtime\lib\site-packages\soundfile.py", line 655, in init
self._file = self._open(file, mode_int, closefd)
File "E:\Voice apps\RVC1006Nvidia\runtime\lib\site-packages\soundfile.py", line 1213, in _open
raise LibsndfileError(err, prefix="Error opening {0!r}: ".format(self.name))
soundfile.LibsndfileError: Error opening 'E:\Voice apps\RVC1006Nvidia\TEMP/50 min audiofile to have music removed.wav.reformatted.wav': System error.

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "E:\Voice apps\RVC1006Nvidia\infer\modules\uvr5\modules.py", line 82, in uvr
pre_fun.path_audio(
File "E:\Voice apps\RVC1006Nvidia\infer\modules\uvr5\vr.py", line 63, in path_audio
) = librosa.core.load( # 理论上librosa读取可能对某些音频有bug，应该上ffmpeg读取，但是太麻烦了弃坑
File "E:\Voice apps\RVC1006Nvidia\runtime\lib\site-packages\librosa\util\decorators.py", line 104, in inner_f
return f(**kwargs)
File "E:\Voice apps\RVC1006Nvidia\runtime\lib\site-packages\librosa\core\audio.py", line 174, in load
y, sr_native = __audioread_load(path, offset, duration, dtype)
File "E:\Voice apps\RVC1006Nvidia\runtime\lib\site-packages\librosa\core\audio.py", line 198, in _audioread_load
with audioread.audio_open(path) as input_file:
File "E:\Voice apps\RVC1006Nvidia\runtime\lib\site-packages\audioread_init.py", line 111, in audio_open
return BackendClass(path)
File "E:\Voice apps\RVC1006Nvidia\runtime\lib\site-packages\audioread\rawread.py", line 62, in init
self._fh = open(filename, 'rb')
FileNotFoundError: [Errno 2] No such file or directory: 'E:\Voice apps\RVC1006Nvidia\TEMP/50 min audiofile to have music removed.wav.reformatted.wav'

Start with infer/modules/uvr5/modules.py at lines 74 and 82, then inspect infer/modules/uvr5/vr.py at line 63 where the reported TEMP path is loaded. Reproduce the failure with the reported Windows input and determine why the reformatted file is missing; done means voice separation no longer fails at that file-loading step.