#4693 TaskCfgVTT(is_cuda=True, uuid='23308c65c2', cache_folder='C:/Users/Muhammed/Desktop/win-pyvideotrans-v3.99-418/tmp/10956

2a00:1d34* Posted at: 23 hours ago

ASR Error [faster-whisper (Local)] An error has occurred. There may be insufficient memory or video memory. 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\trans_create.py", line 361, 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: An error has occurred. There may be insufficient memory or video memory. 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.
TaskCfgVTT(is_cuda=True, uuid='23308c65c2', cache_folder='C:/Users/Muhammed/Desktop/win-pyvideotrans-v3.99-418/tmp/10956/23308c65c2', target_dir='M:/Tutorials/Houdini Helicopter Landing Simulation Course by Nexttut/_video_out/01. Introduction-mp4', source_language='English', source_language_code='en', source_sub='M:/Tutorials/Houdini Helicopter Landing Simulation Course by Nexttut/_video_out/01. Introduction-mp4/en.srt', source_wav='C:/Users/Muhammed/Desktop/win-pyvideotrans-v3.99-418/tmp/10956/23308c65c2/en.wav', source_wav_output='M:/Tutorials/Houdini Helicopter Landing Simulation Course by Nexttut/_video_out/01. Introduction-mp4/en.m4a', target_language='Turkish', target_language_code='tr', target_sub='M:/Tutorials/Houdini Helicopter Landing Simulation Course by Nexttut/_video_out/01. Introduction-mp4/tr.srt', target_wav='C:/Users/Muhammed/Desktop/win-pyvideotrans-v3.99-418/tmp/10956/23308c65c2/target.wav', target_wav_output='M:/Tutorials/Houdini Helicopter Landing Simulation Course by Nexttut/_video_out/01. Introduction-mp4/tr.m4a', name='M:/Tutorials/Houdini Helicopter Landing Simulation Course by Nexttut/01. Introduction.mp4', noextname='01. Introduction', basename='01. Introduction.mp4', ext='mp4', dirname='M:/Tutorials/Houdini Helicopter Landing Simulation Course by Nexttut', shound_del_name=None, translate_type=1, tts_type=0, volume='+0%', pitch='+0Hz', voice_rate='+0%', voice_role='Ahmet(Male/TR)', voice_autorate=True, 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=True, enable_diariz=False, nums_diariz=0, rephrase=0, fix_punc=False, subtitle_language=None, app_mode='biaozhun', subtitles='', targetdir_mp4='M:/Tutorials/Houdini Helicopter Landing Simulation Course by Nexttut/_video_out/01. Introduction-mp4/01. Introduction.mp4', novoice_mp4='C:/Users/Muhammed/Desktop/win-pyvideotrans-v3.99-418/tmp/10956/23308c65c2/novoice.mp4', is_separate=True, embed_bgm=True, instrument='C:/Users/Muhammed/Desktop/win-pyvideotrans-v3.99-418/tmp/10956/23308c65c2/instrument.wav', vocal='C:/Users/Muhammed/Desktop/win-pyvideotrans-v3.99-418/tmp/10956/23308c65c2/vocal.wav', back_audio='', clear_cache=True, background_music=None, subtitle_type=0, only_out_mp4=True, recogn2pass=True, output_srt=0, copysrt_rawvideo=False)

=
system:Windows-10-10.0.26200-SP0
version:v3.99
frozen:True
language:en
root_dir:C:/Users/Muhammed/Desktop/win-pyvideotrans-v3.99-418

1 Replies

Floor #1 DeepSeek reply at 23 hours ago

This is a GPU VRAM (video memory) exhaustion error. The large-v3-turbo model requires significant VRAM, and your GPU (GPU0) has run out of memory, causing the process to crash.

Solution Steps

  1. Switch to a smaller ASR model

    • Change your model from large-v3-turbo to medium, small, or base.
    • In the main interface, under faster-whisper(local), select a smaller model.

  2. Optimize GPU memory usage in Advanced Settings

    • Go to Menu -> Tools/Options -> Advanced Options -> Speech Recognition Parameters.
    • Set CUDA data type to float16 or int8 (lower precision saves VRAM).
    • Reduce beam_size and best_of from 5 to 1.
    • Set Enable context awareness to False.
    • Enable Whisper pre-segment audio (this splits audio before sending to the model, reducing peak VRAM usage).

  3. Disable other VRAM-intensive options

    • In the main interface, uncheck Remove noise and Secondary recognition (recogn2pass) if enabled, as these also consume significant VRAM during parallel tasks.
    • If you are using Separate vocals and background, this runs on CPU but may still affect memory; consider disabling it temporarily.

  4. Simplify file paths (best practice)

    • Your file path contains dots (e.g., 01. Introduction.mp4) and a nested folder _video_out. While not the direct cause, complex paths with special characters can sometimes trigger ffmpeg errors. Rename your video files to short names without dots or spaces (e.g., 01_intro.mp4) and move them to a shallow directory like M:\videos.

  5. If using multiple tasks, force serial processing

    • In Advanced Options, check Force serial when batch translating to prevent concurrent GPU tasks from exhausting VRAM.

Please consult the relevant documentation:

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