#3685 语音识别阶段出错 [faster-whisper(本地)] 出错了，可能内存或显存不足 [GPU0]Traceback (most recent call last): File "videotrans\configure\_base.p

202.8* Posted at: 2 hours ago 👁9

语音识别阶段出错 [faster-whisper(本地)] 出错了，可能内存或显存不足 [GPU0]
Traceback (most recent call last):
File "videotrans\configure\_base.py", line 281, in _new_process
File "videotrans\process\signelobj.py", line 80, in submit_task_gpu
File "concurrent\futures\process.py", line 720, in submit
concurrent.futures.process.BrokenProcessPool: A child process terminated abruptly, the process pool is not usable anymore

Traceback (most recent call last):
File "videotrans\configure\_base.py", line 281, in _new_process
File "videotrans\process\signelobj.py", line 80, in submit_task_gpu
File "concurrent\futures\process.py", line 720, in submit
concurrent.futures.process.BrokenProcessPool: A child process terminated abruptly, the process pool is not usable anymore

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 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 299, in _new_process
RuntimeError: 出错了，可能内存或显存不足 [GPU0]
Traceback (most recent call last):
File "videotrans\configure\_base.py", line 281, in _new_process
File "videotrans\process\signelobj.py", line 80, in submit_task_gpu
File "concurrent\futures\process.py", line 720, in submit
concurrent.futures.process.BrokenProcessPool: A child process terminated abruptly, the process pool is not usable anymore
TaskCfgSTT(is_cuda=True, uuid='c9f91f18cf', cache_folder='D:/vid/tmp/21568/c9f91f18cf', target_dir='D:/下载/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:/下载/recogn/21. Asking For Advice Is Keeping You Unsuccessful (Here's Why).srt", target_wav=None, target_wav_output=None, name="D:/下载/21. Asking For Advice Is Keeping You Unsuccessful (Here's Why).mp3", noextname="21. Asking For Advice Is Keeping You Unsuccessful (Here's Why)", basename="21. Asking For Advice Is Keeping You Unsuccessful (Here's Why).mp3", ext='mp3', dirname='D:/下载', shound_del_name=None, detect_language='en', recogn_type=0, model_name='large-v3', shibie_audio="D:/vid/tmp/21568/c9f91f18cf/21. Asking For Advice Is Keeping You Unsuccessful (Here's Why)-1773897544.621547.wav", remove_noise=False, enable_diariz=False, nums_diariz=0, rephrase=0, fix_punc=False)

=
system:Windows-10-10.0.26200-SP0
version:v3.98
frozen:True
language:zh
root_dir:D:/vid

1 Replies

Floor #1 DeepSeek AI reply at 2 hours ago

这是由于显存或内存不足导致的。错误信息明确提示“可能内存或显存不足 [GPU0]”，并且进程池因子进程意外终止而损坏。这通常在使用大型语音识别模型（如 large-v3）时发生。

解决方案：

  1. 使用更小的模型：在语音识别渠道的下拉菜单中，将模型从 large-v3 更换为 medium、small 或 base。large-v3 模型对显存和内存要求很高。

  2. 调整高级设置以降低资源消耗：

    • 点击顶部菜单 工具/选项 -> 高级选项。

    • 在 【语音识别参数】 区域进行以下修改：

      • CUDA数据类型：将 float32 改为 float16 或 int8。
      • 识别准确度beam_size：将 5 改为 1。
      • 识别准确度best_of：将 5 改为 1。
      • 启用上下文感知：确保此项为 false（不勾选）。
  3. 检查文件路径：您的输入文件路径 D:/下载/21. Asking For Advice Is Keeping You Unsuccessful (Here's Why).mp3 名称较长且包含空格和括号。虽然错误直接原因是资源不足，但长路径和特殊字符也可能在Windows上引发其他问题。建议将文件重命名为简短英文名（如 advice.mp3）并移动到浅层目录（如 D:/video/）再尝试。
  4. 关闭其他占用显存/内存的程序：确保没有其他大型软件（如游戏、浏览器）同时运行，以释放更多资源给 pyVideoTrans。
  5. 验证CUDA环境：如果您已安装CUDA但仍出现此错误，请确认CUDA版本为12.8，并已正确安装匹配的cuDNN。在CMD中输入 nvcc -V 和 nvidia-smi 进行验证。

如果以上步骤仍无法解决问题，可能是您的硬件（显卡显存或系统内存）确实无法满足当前任务需求，请考虑使用在线语音识别API（如OpenAI、Gemini）替代本地模型。

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