语音识别阶段出错[openai-whisper(本地)] Expected parameter logits (Tensor of shape (1, 51865)) of distribution Categorical(logits: torch.Size([1, 51865])) 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\process\stt_fun.py", line 102, 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, 51865)) of distribution Categorical(logits: torch.Size([1, 51865])) 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 54, in run
File "videotrans\task\job.py", line 119, in process_task
File "videotrans\task\speech2text.py", line 125, in recogn
File "videotrans\recognition\__init__.py", line 190, in run
File "videotrans\recognition\_base.py", line 93, in run
File "videotrans\recognition\_whisper.py", line 33, in _exec
File "videotrans\recognition\_whisper.py", line 76, in _openai
File "videotrans\configure\base.py", line 252, in _new_process
videotrans.configure.excepts.VideoTransError: Expected parameter logits (Tensor of shape (1, 51865)) of distribution Categorical(logits: torch.Size([1, 51865])) 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\process\stt_fun.py", line 102, 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, 51865)) of distribution Categorical(logits: torch.Size([1, 51865])) to satisfy the constraint IndependentConstraint(Real(), 1), but found invalid values:
tensor([[nan, nan, nan, ..., nan, nan, nan]], device='cuda:0')
TaskCfgSTT(uuid='1a66eb0958', name='C:/Users/ilove/Desktop/temp/animBot- Getting Started.mp4', dirname='C:/Users/ilove/Desktop/temp', noextname='animBot- Getting Started', basename='animBot- Getting Started.mp4', ext='mp4', target_dir='D:/Download/win-pyvideotrans-v4.00-528/output/recogn', cache_folder='D:/Programs/win-pyvideotrans-v4.00-528/tmp/7336/1a66eb0958', is_cuda=True, 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='D:/Download/win-pyvideotrans-v4.00-528/output/recogn/animBot- Getting Started.srt', target_wav=None, target_wav_output=None, detect_language='en', recogn_type=1, model_name='small', shibie_audio='D:/Programs/win-pyvideotrans-v4.00-528/tmp/7336/1a66eb0958/animBot- Getting Started-1780203873.804824.wav', remove_noise=False, enable_diariz=False, nums_diariz=0, rephrase=0, fix_punc=False)
=
system:Windows-10-10.0.22631-SP0
version:v4.00
frozen:True
language:zh
root_dir:D:/Programs/win-pyvideotrans-v4.00-528