语音识别阶段出错 [faster-whisper(本地)] Traceback (most recent call last):
File "videotrans\process\stt_fun.py", line 452, in faster_whisper
File "faster_whisper\transcribe.py", line 1851, in restore_speech_timestamps
File "faster_whisper\transcribe.py", line 1279, in generate_segments
File "faster_whisper\transcribe.py", line 1590, in add_word_timestamps
File "faster_whisper\transcribe.py", line 1709, in find_alignment
RuntimeError: cuBLAS failed with status CUBLAS_STATUS_NOT_SUPPORTED
Traceback (most recent call last):
File "videotrans\task\job.py", line 105, in run
File "videotrans\task\_speech2text.py", line 152, in recogn
File "videotrans\recognition\__init__.py", line 265, in run
File "videotrans\recognition\_base.py", line 143, in run
File "videotrans\recognition\_overall.py", line 33, in _exec
File "videotrans\recognition\_overall.py", line 105, in _faster
File "videotrans\configure\_base.py", line 288, in _new_process
RuntimeError: Traceback (most recent call last):
File "videotrans\process\stt_fun.py", line 452, in faster_whisper
File "faster_whisper\transcribe.py", line 1851, in restore_speech_timestamps
File "faster_whisper\transcribe.py", line 1279, in generate_segments
File "faster_whisper\transcribe.py", line 1590, in add_word_timestamps
File "faster_whisper\transcribe.py", line 1709, in find_alignment
RuntimeError: cuBLAS failed with status CUBLAS_STATUS_NOT_SUPPORTED
TaskCfgSTT(is_cuda=True, uuid='795b5f7da7', cache_folder='D:/soft/AI/win-pyvideotrans-v3.98-314/tmp/14548/795b5f7da7', target_dir='D:/soft/AI/win-pyvideotrans-v3.98-314/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='D:/soft/AI/win-pyvideotrans-v3.98-314/output/recogn/1.srt', target_wav=None, target_wav_output=None, name='D:/1.mp4', noextname='1', basename='1.mp4', ext='mp4', dirname='D:/', shound_del_name=None, detect_language='zh-cn', recogn_type=0, model_name='large-v3', shibie_audio='D:/soft/AI/win-pyvideotrans-v3.98-314/tmp/14548/795b5f7da7/1-1773576552.4368925.wav', remove_noise=False, enable_diariz=False, nums_diariz=0, rephrase=0, fix_punc=False)