Error

A clear and concise dTraceback (most recent call last):

File "E:\Audio\CosyVoice\test.py", line 7, in

cosyvoice = CosyVoice('pretrained_models/CosyVoice-300M')

File "E:\Audio\CosyVoice\cosyvoice\cli\cosyvoice.py", line 33, in init

self.frontend = CosyVoiceFrontEnd(configs['get_tokenizer'],

File "E:\Audio\CosyVoice\cosyvoice\cli\frontend.py", line 73, in init

self.zh_tn_model = ZhNormalizer(remove_erhua=False, full_to_half=False)

File "E:\anaconda\envs\CosyVoice\lib\site-packages\tn\chinese\normalizer.py", line 53, in init

self.build_fst('zh_tn', cache_dir, overwrite_cache)

File "E:\anaconda\envs\CosyVoice\lib\site-packages\tn\processor.py", line 85, in build_fst

os.makedirs(cache_dir, exist_ok=True)

File "E:\anaconda\envs\CosyVoice\lib\os.py", line 210, in makedirs

head, tail = path.split(name)

File "E:\anaconda\envs\CosyVoice\lib\ntpath.py", line 211, in split

p = os.fspath(p)

TypeError: expected str, bytes or os.PathLike object, not MultiplexedPathescription of what the bug is.

Solution

Reinstall wetextprocessing