语音识别阶段出错 [openai-whisper(本地)] Traceback (most recent call last):
File "videotrans\process\stt_fun.py", line 109, in openai_whisper
File "whisper\transcribe.py", line 295, in transcribe
File "whisper\transcribe.py", line 201, in decode_with_fallback
File "torch\utils\_contextlib.py", line 116, in decorate_context
return func(*args, **kwargs)File "whisper\decoding.py", line 824, in decode
File "torch\utils\_contextlib.py", line 116, in decorate_context
return func(*args, **kwargs)File "whisper\decoding.py", line 737, in run
File "whisper\decoding.py", line 703, in _main_loop
File "whisper\decoding.py", line 283, in update
File "torch\distributions\categorical.py", line 73, in init
super().__init__(batch_shape, validate_args=validate_args)File "torch\distributions\distribution.py", line 72, in init
raise ValueError(ValueError: Expected parameter logits (Tensor of shape (1, 51866)) of distribution Categorical(logits: torch.Size([1, 51866])) to satisfy the constraint IndependentConstraint(Real(), 1), but found invalid values:
tensor([[nan, nan, nan, ..., nan, nan, nan]], device='cuda:0')
Traceback (most recent call last):
File "videotrans\task\job.py", line 105, in run
File "videotrans\task\_speech2text.py", line 191, in recogn
File "videotrans\recognition\__init__.py", line 293, in run
File "videotrans\recognition\_base.py", line 143, in run
File "videotrans\recognition\_overall.py", line 31, in _exec
File "videotrans\recognition\_overall.py", line 74, in _openai
File "videotrans\configure\_base.py", line 289, in _new_process
RuntimeError: Traceback (most recent call last):
File "videotrans\process\stt_fun.py", line 109, in openai_whisper
File "whisper\transcribe.py", line 295, in transcribe
File "whisper\transcribe.py", line 201, in decode_with_fallback
File "torch\utils\_contextlib.py", line 116, in decorate_context
return func(*args, **kwargs)File "whisper\decoding.py", line 824, in decode
File "torch\utils\_contextlib.py", line 116, in decorate_context
return func(*args, **kwargs)File "whisper\decoding.py", line 737, in run
File "whisper\decoding.py", line 703, in _main_loop
File "whisper\decoding.py", line 283, in update
File "torch\distributions\categorical.py", line 73, in init
super().__init__(batch_shape, validate_args=validate_args)File "torch\distributions\distribution.py", line 72, in init
raise ValueError(ValueError: Expected parameter logits (Tensor of shape (1, 51866)) of distribution Categorical(logits: torch.Size([1, 51866])) to satisfy the constraint IndependentConstraint(Real(), 1), but found invalid values:
tensor([[nan, nan, nan, ..., nan, nan, nan]], device='cuda:0')
TaskCfgSTT(is_cuda=True, uuid='57da8ab8e2', cache_folder='J:/pyvideotrans-v3.99-0508/tmp/9564/57da8ab8e2', target_dir='J:/pyvideotrans-v3.99-0508/output/recogn', source_language=None, source_language_code=None, source_sub=None, source_wav=None, source_wav_output=None, target_language=None, target_language_code=None, target_sub='J:/pyvideotrans-v3.99-0508/output/recogn/第一次直播 (2).srt', target_wav=None, target_wav_output=None, name='J:/第一次直播 (2).mp4', noextname='第一次直播 (2)', basename='第一次直播 (2).mp4', ext='mp4', dirname='J:/', shound_del_name=None, detect_language='zh-cn', recogn_type=1, model_name='large-v3', shibie_audio='J:/pyvideotrans-v3.99-0508/tmp/9564/57da8ab8e2/第一次直播 (2)-1778356683.058531.wav', remove_noise=False, enable_diariz=False, nums_diariz=0, rephrase=0, fix_punc=False)
=
system:Windows-10-10.0.19041-SP0
version:v3.99
frozen:True
language:zh
root_dir:J:/pyvideotrans-v3.99-0508