#3544 TaskCfgSTT(is_cuda=True, uuid='e1dbb01d50', cache_folder='D:/Program Files/pyvideotrans/tmp/1468/e1dbb01d50', target_dir

61.8* Posted at: 1 hour ago 👁6

语音识别阶段出错 [faster-whisper(本地)] 出错了，可能内存或显存不足
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 284, 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 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 294, in _new_process
RuntimeError: 出错了，可能内存或显存不足
A process in the process pool was terminated abruptly while the future was running or pending.
TaskCfgSTT(is_cuda=True, uuid='e1dbb01d50', cache_folder='D:/Program Files/pyvideotrans/tmp/1468/e1dbb01d50', target_dir='D:/Program Files/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/pyvideotrans/output/recogn/14. Wind tornado VFX.srt', target_wav=None, target_wav_output=None, name='D:/Udemy教程/Udemy - Realistic Real-time VFX course in Unity - From Zero to Pro/14. Wind tornado VFX.mp4', noextname='14. Wind tornado VFX', basename='14. Wind tornado VFX.mp4', ext='mp4', dirname='D:/Udemy教程/Udemy - Realistic Real-time VFX course in Unity - From Zero to Pro', shound_del_name=None, detect_language='en', recogn_type=0, model_name='tiny', shibie_audio='D:/Program Files/pyvideotrans/tmp/1468/e1dbb01d50/14. Wind tornado VFX-1773136557.1748085.wav', remove_noise=False, enable_diariz=False, nums_diariz=0, rephrase=0, fix_punc=False)

=
system:Windows-10-10.0.26100-SP0
version:v3.97
frozen:True
language:zh
root_dir:D:/Program Files/pyvideotrans

1 Replies

Floor #1 DeepSeek AI reply at 1 hour ago

该错误是由于内存或显存不足，导致语音识别进程池中的进程被意外终止。

解决方案：

  1. 降低模型大小：你当前使用的是 tiny 模型。虽然它最小最快，但准确度很低，且此错误表明系统资源仍不足以稳定运行。请尝试以下操作：

    • 在语音识别渠道的下拉菜单中，将模型从 tiny 更换为 base 或 small。如果仍报错，请继续尝试更小的模型，直到能稳定运行。
    • 注意：.en结尾和distil-开头的模型仅支持英语发音。如果你的视频是英语，可以尝试 tiny.en 或 distil-small.en 等模型。

  2. 检查CUDA加速状态：错误日志显示 is_cuda=True，说明已启用CUDA加速。请确认：

    • 在CMD中输入 nvidia-smi，确认显卡驱动正常且显存充足。
    • 如果显存较小（例如小于4GB），即使使用 tiny 模型也可能因并发任务导致显存溢出。请进入 菜单 -> 工具 -> 高级选项，将 【GPU同时任务数[重启生效]】 设置为 1，然后重启软件。

  3. 调整软件安装/运行环境：

    • 路径问题：你的软件安装在 D:/Program Files/pyvideotrans。Program Files 是受保护的系统目录，可能引起权限问题。强烈建议将整个 pyvideotrans 文件夹移动到非系统盘根目录，例如 D:\pyVideoTrans，且路径中不要包含中文和空格。
    • 释放内存：关闭其他占用大量内存和显存的程序（如游戏、浏览器、其他AI软件），再重新尝试。

  4. 修改高级参数（如果以上步骤无效）：

    • 进入 菜单 -> 工具 -> 高级选项 -> 语音识别参数。
    • 将 识别准确度beam_size 和 识别准确度best_of 都设置为 1（最低精度，消耗资源最少）。
    • 将 CUDA数据类型 设置为 int8（消耗资源少，速度快，但精度略低）。

如果问题依旧，请提供更详细的系统配置信息（如显卡型号、显存大小、内存大小）以供进一步分析。

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