#3950 TaskCfgSTT(is_cuda=True, uuid='9311075a3a', cache_folder='D:/Program Files/win-pyvideotrans/tmp/5748/9311075a3a', target

103.196* Posted at: 8 hours ago 👁14

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:tiny 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 292, 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:tiny 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='9311075a3a', cache_folder='D:/Program Files/win-pyvideotrans/tmp/5748/9311075a3a', target_dir='D:/Program Files/win-pyvideotrans/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:/Program Files/win-pyvideotrans/output/recogn/3 -Create Unit Scene.srt', target_wav=None, target_wav_output=None, name='D:/Udemy教程/Udemy - Godot 2D Academy Create a Brotato style game with Godot 4/2 - Create Player/3 -Create Unit Scene.mp4', noextname='3 -Create Unit Scene', basename='3 -Create Unit Scene.mp4', ext='mp4', dirname='D:/Udemy教程/Udemy - Godot 2D Academy Create a Brotato style game with Godot 4/2 - Create Player', shound_del_name=None, detect_language='en', recogn_type=0, model_name='tiny', shibie_audio='D:/Program Files/win-pyvideotrans/tmp/5748/9311075a3a/3 -Create Unit Scene-1775542078.8228989.wav', remove_noise=False, enable_diariz=False, nums_diariz=0, rephrase=0, fix_punc=False)


=
system:Windows-10-10.0.26100-SP0
version:v3.98
frozen:True
language:zh
root_dir:D:/Program Files/win-pyvideotrans

1 Replies

这是由于内存或显存不足导致的,即使使用了最小的 tiny 模型。

解决方案:

  1. 检查文件路径:你的软件安装路径 D:/Program Files/win-pyvideotrans 和视频路径 D:/Udemy教程/... 都包含中文和空格。这可能导致程序在调用底层进程时出现问题。请将软件解压到纯英文、无空格的路径(如 D:\pyVideoTrans),并将待处理的视频文件也移动到类似路径下。
  2. 调整高级设置:如果路径问题解决后仍报错,请进入 菜单 -> 工具 -> 高级选项,在“语音识别参数”区域进行如下调整以降低资源消耗:

    • CUDA数据类型: 改为 int8
    • 识别准确度beam_size: 改为 1
    • 识别准确度best_of: 改为 1
    • 启用上下文感知: 取消勾选。
  3. 检查CUDA环境:确认你已正确安装 CUDA 12.8 和 cuDNN,并且勾选了主界面的“CUDA加速”。如果未安装或版本不匹配,GPU加速将无法工作,可能导致进程异常。
  4. 关闭其他程序:在处理视频时,关闭不必要的应用程序以释放更多内存。
  5. 使用更稳定的模型:如果以上步骤无效,可以尝试切换到 openai-whisper(本地) 渠道的 tiny 模型,或者考虑使用在线识别渠道(如 OpenAI API)。

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