#4433 TaskCfgVTT(is_cuda=True, uuid='5c79baddaa', cache_folder='E:/3.98/tmp/3020/5c79baddaa', target_dir='D:/Course/The High-D

2405:4802* Posted at: 1 hour ago 👁10

ASR Error [faster-whisper (Local)] Traceback (most recent call last):
File "videotrans\process\stt_fun.py", line 346, in faster_whisper
File "faster_whisper\transcribe.py", line 689, in init
RuntimeError: mkl_malloc: failed to allocate memory

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 288, in _new_process
RuntimeError: Traceback (most recent call last):
File "videotrans\process\stt_fun.py", line 346, in faster_whisper
File "faster_whisper\transcribe.py", line 689, in init
RuntimeError: mkl_malloc: failed to allocate memory
TaskCfgVTT(is_cuda=True, uuid='5c79baddaa', cache_folder='E:/3.98/tmp/3020/5c79baddaa', target_dir='D:/Course/The High-Density Coloring Guide to Bring Your Ideas to Life/SECTION 06. Practical Character Illustration 2 - Depicting Volume, Materials, and Coloring/_video_out/15-2. Coloring 1 Setting the Shadow Area-mp4', source_language='Korean', source_language_code='ko', source_sub='D:/Course/The High-Density Coloring Guide to Bring Your Ideas to Life/SECTION 06. Practical Character Illustration 2 - Depicting Volume, Materials, and Coloring/_video_out/15-2. Coloring 1 Setting the Shadow Area-mp4/ko.srt', source_wav='E:/3.98/tmp/3020/5c79baddaa/ko.wav', source_wav_output='D:/Course/The High-Density Coloring Guide to Bring Your Ideas to Life/SECTION 06. Practical Character Illustration 2 - Depicting Volume, Materials, and Coloring/_video_out/15-2. Coloring 1 Setting the Shadow Area-mp4/ko.m4a', target_language='-', target_language_code=None, target_sub='D:/Course/The High-Density Coloring Guide to Bring Your Ideas to Life/SECTION 06. Practical Character Illustration 2 - Depicting Volume, Materials, and Coloring/_video_out/15-2. Coloring 1 Setting the Shadow Area-mp4/None.srt', target_wav='E:/3.98/tmp/3020/5c79baddaa/target.wav', target_wav_output='D:/Course/The High-Density Coloring Guide to Bring Your Ideas to Life/SECTION 06. Practical Character Illustration 2 - Depicting Volume, Materials, and Coloring/_video_out/15-2. Coloring 1 Setting the Shadow Area-mp4/None.m4a', name='D:/Course/The High-Density Coloring Guide to Bring Your Ideas to Life/SECTION 06. Practical Character Illustration 2 - Depicting Volume, Materials, and Coloring/15-2. Coloring 1 Setting the Shadow Area.mp4', noextname='15-2. Coloring 1 Setting the Shadow Area', basename='15-2. Coloring 1 Setting the Shadow Area.mp4', ext='mp4', dirname='D:/Course/The High-Density Coloring Guide to Bring Your Ideas to Life/SECTION 06. Practical Character Illustration 2 - Depicting Volume, Materials, and Coloring', shound_del_name=None, translate_type=8, tts_type=0, volume='+0%', pitch='+0Hz', voice_rate='+0%', voice_role='No', voice_autorate=False, video_autorate=True, remove_silent_mid=False, align_sub_audio=True, detect_language='ko', recogn_type=0, model_name='large-v2', shibie_audio=None, remove_noise=False, enable_diariz=False, nums_diariz=0, rephrase=0, fix_punc=False, subtitle_language=None, app_mode='tiqu', subtitles='', targetdir_mp4='D:/Course/The High-Density Coloring Guide to Bring Your Ideas to Life/SECTION 06. Practical Character Illustration 2 - Depicting Volume, Materials, and Coloring/_video_out/15-2. Coloring 1 Setting the Shadow Area-mp4/15-2. Coloring 1 Setting the Shadow Area.mp4', novoice_mp4='E:/3.98/tmp/3020/5c79baddaa/novoice.mp4', is_separate=False, instrument=None, vocal=None, back_audio='', clear_cache=False, background_music=None, subtitle_type=0, only_out_mp4=False, recogn2pass=False, output_srt=0, copysrt_rawvideo=False)


=
system:Windows-10-10.0.26200-SP0
version:v3.98
frozen:True
language:en
root_dir:E:/3.98

1 Replies

This error indicates a memory allocation failure during the faster-whisper speech recognition step — either your system RAM or GPU VRAM is insufficient for the current model and settings.

How to fix (try these in order):

  1. Switch to a smaller model. You're using large-v2, which requires at least ~10 GB of GPU VRAM or ~16 GB of system RAM. Choose medium, small, or even base from the model dropdown.
  2. Tweak CUDA/Whisper settings in Advanced Options
    Go to Menu → Tools/Options → Advanced Options → Speech Recognition Parameters and lower the resource usage:

    • Set CUDA data type to int8 (or float16)
    • Set beam_size to 1
    • Set best_of to 1
    • Turn off Context Awareness
  3. Enable audio pre‑splitting. In the same Advanced Options, check Whisper pre‑split audio. This reduces peak memory by cutting the audio into shorter chunks before recognition.
  4. Disable “Secondary Recognition” (the checkbox in the main interface) if it is currently on — it doubles the load.
  5. Run on CPU only. Uncheck CUDA acceleration on the main interface. This will be slower but bypasses GPU VRAM limits, relying solely on your system RAM.

If the video is very long and all else fails, consider splitting it into smaller parts before processing.

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