#4182 TaskCfgSTT(is_cuda=True, uuid='2bd16388bc', cache_folder='D:/win-pyvideotrans-v3.99-417/tmp/900/2bd16388bc', target_dir=

240e:44d* Posted at: 1 day ago 👁18

语音识别阶段出错 [faster-whisper(本地)] 出错了,可能内存或显存不足 Model:large-v3-turbo GPU0
Traceback (most recent call last):
File "videotrans\configure\_base.py", line 285, in _new_process
File "concurrent\futures\_base.py", line 458, in result
File "concurrent\futures\_base.py", line 403, in __get_result
concurrent.futures.process.BrokenProcessPool: A process in the process pool was terminated abruptly while the future was running or pending.

Traceback (most recent call last):
File "videotrans\configure\_base.py", line 285, in _new_process
File "concurrent\futures\_base.py", line 458, in result
File "concurrent\futures\_base.py", line 403, in __get_result
concurrent.futures.process.BrokenProcessPool: A process in the process pool was terminated abruptly while the future was running or pending.

During handling of the above exception, another exception occurred:

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 293, 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 303, in _new_process
RuntimeError: 出错了,可能内存或显存不足 Model:large-v3-turbo GPU0
Traceback (most recent call last):
File "videotrans\configure\_base.py", line 285, in _new_process
File "concurrent\futures\_base.py", line 458, in result
File "concurrent\futures\_base.py", line 403, in __get_result
concurrent.futures.process.BrokenProcessPool: A process in the process pool was terminated abruptly while the future was running or pending.
TaskCfgSTT(is_cuda=True, uuid='2bd16388bc', cache_folder='D:/win-pyvideotrans-v3.99-417/tmp/900/2bd16388bc', target_dir='D:/win-pyvideotrans-v3.99-417/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:/win-pyvideotrans-v3.99-417/output/recogn/We Can’t Be Late, Your Pa is Waiting – Mira Sangre.srt', target_wav=None, target_wav_output=None, name='E:/DownLoad/DCL/We Can’t Be Late, Your Pa is Waiting – Mira Sangre.mp4', noextname='We Can’t Be Late, Your Pa is Waiting – Mira Sangre', basename='We Can’t Be Late, Your Pa is Waiting – Mira Sangre.mp4', ext='mp4', dirname='E:/DownLoad/DCL', shound_del_name=None, detect_language='auto', recogn_type=0, model_name='large-v3-turbo', shibie_audio='D:/win-pyvideotrans-v3.99-417/tmp/900/2bd16388bc/remove_noise.wav', remove_noise=True, enable_diariz=False, nums_diariz=0, rephrase=0, fix_punc=False)


=
system:Windows-10-10.0.26100-SP0
version:v3.99
frozen:True
language:zh
root_dir:D:/win-pyvideotrans-v3.99-417

1 Replies

这是由于显存或内存不足导致的。使用 large-v3-turbo 模型进行语音识别时,对显存和内存需求较高,当资源不足时进程会被系统强制终止。

解决方案:

  1. 更换更小的模型:在主界面的语音识别渠道右侧,将模型从 large-v3-turbo 更换为 mediumsmallbase
  2. 调整高级设置:在菜单栏 工具/选项 -> 高级选项 的【语音识别参数】区域进行如下修改,以降低显存占用:

    • CUDA数据类型: 将 float32 改为 float16int8
    • beam_size: 将 5 改为 1
    • best_of: 将 5 改为 1
    • 上下文: 将 true 改为 false
  3. 启用预分割:在【语音识别参数】区域,选中 Whisper预分割音频?,这可以降低处理长音频时的显存峰值占用。
  4. 检查二次识别:如果主界面右上角勾选了“二次识别”,请取消勾选,尤其是在批量处理多个视频时,二次识别会显著增加显存需求。
  5. 简化文件名:您的视频文件名较长且包含特殊字符()。请将视频文件重命名为一个简短的英文或数字名称(如 video.mp4),并移动到较浅的目录(如 D:\video),以避免因路径过长或特殊字符导致的潜在问题。

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