#4479 TaskCfgSTT(is_cuda=True, uuid='92072a4d15', cache_folder='G:/win-pyvideotrans-v3.98-317/tmp/1532/92072a4d15', target_dir

5.83* Posted at: 4 hours ago 👁13

语音识别阶段出错 [faster-whisper(本地)] Traceback (most recent call last):
File "videotrans\process\stt_fun.py", line 346, in faster_whisper
File "faster_whisper\transcribe.py", line 689, in init
ValueError: Requested float16 compute type, but the target device or backend do not support efficient float16 computation.

Traceback (most recent call last):
File "videotrans\task\job.py", line 105, in run
File "videotrans\task\_speech2text.py", line 159, in recogn
File "videotrans\recognition\__init__.py", line 272, 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 289, in _new_process
RuntimeError: Traceback (most recent call last):
File "videotrans\process\stt_fun.py", line 346, in faster_whisper
File "faster_whisper\transcribe.py", line 689, in init
ValueError: Requested float16 compute type, but the target device or backend do not support efficient float16 computation.
TaskCfgSTT(is_cuda=True, uuid='92072a4d15', cache_folder='G:/win-pyvideotrans-v3.98-317/tmp/1532/92072a4d15', target_dir='G:/win-pyvideotrans-v3.98-317/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='G:/win-pyvideotrans-v3.98-317/output/recogn/The history and virtues of eating pigeon meat squab.srt', target_wav=None, target_wav_output=None, name='G:/YouTube/The history and virtues of eating pigeon meat squab/The history and virtues of eating pigeon meat squab.mp4', noextname='The history and virtues of eating pigeon meat squab', basename='The history and virtues of eating pigeon meat squab.mp4', ext='mp4', dirname='G:/YouTube/The history and virtues of eating pigeon meat squab', shound_del_name=None, detect_language='auto', recogn_type=0, model_name='large-v3-turbo', shibie_audio='G:/win-pyvideotrans-v3.98-317/tmp/1532/92072a4d15/The history and virtues of eating pigeon meat squab-1778239235.9625657.wav', remove_noise=False, enable_diariz=False, nums_diariz=0, rephrase=0, fix_punc=False)


=
system:Windows-10-10.0.19045-SP0
version:v3.98
frozen:True
language:zh
root_dir:G:/win-pyvideotrans-v3.98-317

1 Replies

这是由于CUDA数据类型设置为float16,但当前设备或后端不支持高效的float16运算。

解决方案:

  1. 打开菜单 工具/选项高级选项语音识别参数
  2. CUDA数据类型float16 改为 float32int8
  3. 保存设置后重新执行任务。

请查阅相关文档:

Post Your Reply
Open source and free maintenance is not easy. If this project is helpful to you, please consider making a small donation to help the project continue to maintain and update.

Related resource