#3657 TaskCfgVTT(is_cuda=True, uuid='5f6371c633', cache_folder='D:/win-pyvideotrans-v3.98-314/tmp/17912/5f6371c633', target_di

2400:8901* Posted at: 1 day ago 👁22

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 child process terminated abruptly, the process pool is not usable anymore
Traceback (most recent call last):
File "videotrans\configure\_base.py", line 280, in _new_process
File "videotrans\process\signelobj.py", line 81, 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\trans_create.py", line 353, 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 child process terminated abruptly, the process pool is not usable anymore
TaskCfgVTT(is_cuda=True, uuid='5f6371c633', cache_folder='D:/win-pyvideotrans-v3.98-314/tmp/17912/5f6371c633', target_dir='D:/yinyue_fanyi/Music Production Composition in FL Studio Complete Guide/5 - Lets Make a House Track/_video_out/28 - FL Studio Setup & Project Downloads-mp4', source_language='英语', source_language_code='en', source_sub='D:/yinyue_fanyi/Music Production Composition in FL Studio Complete Guide/5 - Lets Make a House Track/_video_out/28 - FL Studio Setup & Project Downloads-mp4/en.srt', source_wav='D:/win-pyvideotrans-v3.98-314/tmp/17912/5f6371c633/en.wav', source_wav_output='D:/yinyue_fanyi/Music Production Composition in FL Studio Complete Guide/5 - Lets Make a House Track/_video_out/28 - FL Studio Setup & Project Downloads-mp4/en.m4a', target_language='简体中文', target_language_code='zh-cn', target_sub='D:/yinyue_fanyi/Music Production Composition in FL Studio Complete Guide/5 - Lets Make a House Track/_video_out/28 - FL Studio Setup & Project Downloads-mp4/zh-cn.srt', target_wav='D:/win-pyvideotrans-v3.98-314/tmp/17912/5f6371c633/target.wav', target_wav_output='D:/yinyue_fanyi/Music Production Composition in FL Studio Complete Guide/5 - Lets Make a House Track/_video_out/28 - FL Studio Setup & Project Downloads-mp4/zh-cn.m4a', name='D:/yinyue_fanyi/Music Production Composition in FL Studio Complete Guide/5 - Lets Make a House Track/28 - FL Studio Setup & Project Downloads.mp4', noextname='28 - FL Studio Setup & Project Downloads', basename='28 - FL Studio Setup & Project Downloads.mp4', ext='mp4', dirname='D:/yinyue_fanyi/Music Production Composition in FL Studio Complete Guide/5 - Lets Make a House Track', shound_del_name=None, translate_type=0, tts_type=0, volume='+0%', pitch='+0Hz', voice_rate='+0%', voice_role='Yunyang(Male/CN)', voice_autorate=False, video_autorate=False, remove_silent_mid=False, align_sub_audio=True, detect_language='en', recogn_type=0, model_name='large-v3-turbo', shibie_audio=None, remove_noise=False, enable_diariz=False, nums_diariz=0, rephrase=0, fix_punc=False, subtitle_language=None, app_mode='biaozhun', subtitles='', targetdir_mp4='D:/yinyue_fanyi/Music Production Composition in FL Studio Complete Guide/5 - Lets Make a House Track/_video_out/28 - FL Studio Setup & Project Downloads-mp4/28 - FL Studio Setup & Project Downloads.mp4', novoice_mp4='D:/win-pyvideotrans-v3.98-314/tmp/17912/5f6371c633/novoice.mp4', is_separate=False, instrument=None, vocal=None, back_audio='', clear_cache=False, background_music=None, subtitle_type=1, only_out_mp4=False, recogn2pass=True, output_srt=0, copysrt_rawvideo=False)


=
system:Windows-10-10.0.26200-SP0
version:v3.98
frozen:True
language:zh
root_dir:D:/win-pyvideotrans-v3.98-314

1 Replies

这是由于内存或显存不足导致 faster-whisper 语音识别进程崩溃。

解决方案:

  1. 降低模型要求:在语音识别设置中,将模型从 large-v3-turbo 更换为更小的模型,例如 mediumsmall
  2. 优化CUDA设置:如果启用了CUDA加速,请前往 菜单-工具-高级选项-语音识别参数,将 CUDA数据类型float32float16 改为 int8,以降低显存消耗。
  3. 调整识别参数:在同一高级选项中,将 识别准确度beam_size识别准确度best_of 都设为 1,这能显著减少内存/显存使用,但可能略微降低识别精度。
  4. 关闭其他程序:确保在运行软件时,没有其他占用大量内存或显存的程序(如游戏、大型设计软件)同时运行。
  5. 检查硬件限制:确认你的系统内存和显卡显存容量。使用 large-v3 级别模型,建议内存不低于16G,使用CUDA加速时显存不低于10G。如果硬件不满足,必须使用更小的模型。

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