Error in speech recognition:paraformer-zh is not registered[FunASR-Chinese]:
Traceback (most recent call last):
File "/home/shapo/Git/pyvideotrans/videotrans/task/trans_create.py", line 375, in recogn
raw_subtitles = run_recogn(
recogn_type=self.cfg['recogn_type'],
......
target_code=self.cfg['target_language_code'] if self.shoud_trans else None,
inst=self)
File "/home/shapo/Git/pyvideotrans/videotrans/recognition/__init__.py", line 227, in run
return FunasrRecogn(kwargs).run()
~~~~~~~~~~~~~~~~~~~~~~~~~~^^
File "/home/shapo/Git/pyvideotrans/videotrans/recognition/_base.py", line 70, in run
return self._exec()
~~~~~~~~~~^^
File "/home/shapo/Git/pyvideotrans/videotrans/recognition/_funasr.py", line 64, in _exec
model = AutoModel(
model=self.model_name, model_revision="v2.0.4",
......
device=self.device
)
File "/home/shapo/.virtualenvs/whisper/lib/python3.13/site-packages/funasr/auto/auto_model.py", line 125, in __init__
model, kwargs = self.build_model(kwargs)
~~~~~~~~~~~~~~~~^^^^^^^^^^
File "/home/shapo/.virtualenvs/whisper/lib/python3.13/site-packages/funasr/auto/auto_model.py", line 264, in build_model
assert model_class is not None, f'{kwargs["model"]} is not registered'
^^^^^^^^^^^^^^^^^^^^^^^
AssertionError: paraformer-zh is not registered
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/home/shapo/Git/pyvideotrans/videotrans/task/job.py", line 97, in run
trk.recogn()
~~~~~~~~~~^^
File "/home/shapo/Git/pyvideotrans/videotrans/task/trans_create.py", line 411, in recogn
raise RuntimeError(msg)
RuntimeError: paraformer-zh is not registered
=====
Linux-6.16.7-arch1-1-x86_64-with-glibc2.42
version:v3.80
frozen:False
language:en