#7626 ASR Error [faster-whisper (Local)] Traceback (most recent call last): File

202.150**5 Posted at: 2 hours ago

ASR Error [faster-whisper (Local)] Traceback (most recent call last):
File "videotrans\process\stt_fun.py", line 257, in faster_whisper
File "faster_whisper\transcribe.py", line 586, in _batched_segments_generator
File "faster_whisper\transcribe.py", line 120, in forward
File "faster_whisper\transcribe.py", line 209, in generate_segment_batched
File "faster_whisper\transcribe.py", line 1400, in encode
RuntimeError: CUDA failed with error out of memory

Traceback (most recent call last):
File "videotrans\task\job.py", line 106, in run
File "videotrans\task\_speech2text.py", line 153, in recogn
File "videotrans\recognition\__init__.py", line 266, in run
File "videotrans\recognition\_base.py", line 142, in run
File "videotrans\recognition\_overall.py", line 63, in _exec
File "videotrans\recognition\_overall.py", line 136, in _faster
File "videotrans\configure\_base.py", line 290, in _new_process
RuntimeError: Traceback (most recent call last):
File "videotrans\process\stt_fun.py", line 257, in faster_whisper
File "faster_whisper\transcribe.py", line 586, in _batched_segments_generator
File "faster_whisper\transcribe.py", line 120, in forward
File "faster_whisper\transcribe.py", line 209, in generate_segment_batched
File "faster_whisper\transcribe.py", line 1400, in encode
RuntimeError: CUDA failed with error out of memory
TaskCfgSTT(is_cuda=True, uuid='b057fedd6d', cache_folder='E:/ytrans/tmp/5344/b057fedd6d', target_dir='E:/ytrans/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='E:/ytrans/output/recogn/24-2 Series Illustration 07 Working on the Series Illustration.srt', target_wav=None, target_wav_output=None, name='E:/2023/personal/inspo2/ZQ/updated subs/24-2 Series Illustration 07 Working on the Series Illustration.m4a', noextname='24-2 Series Illustration 07 Working on the Series Illustration', basename='24-2 Series Illustration 07 Working on the Series Illustration.m4a', ext='m4a', dirname='E:/2023/personal/inspo2/ZQ/updated subs', shound_del_name=None, detect_language='ko', recogn_type=0, model_name='large-v3', shibie_audio='E:/ytrans/tmp/5344/b057fedd6d/24-2 Series Illustration 07 Working on the Series Illustration-1790393798.1857996.wav', remove_noise=False, enable_diariz=False, nums_diariz=0, rephrase=1, fix_punc=False)

=
system:Windows-10-10.0.26200-SP0
version:v3.97
frozen:True
language:en
root_dir:E:/ytrans

#1 DeepSeek reply at 2 hours ago

This is caused by insufficient GPU VRAM.

The large-v3 model requires roughly 8GB+ of free VRAM, and your GPU ran out of memory during Whisper encoding.

Solutions (apply in order):

Use a smaller model: change model_name from large-v3 to medium, small, or base.
Reduce compute resource usage in Menu -> Tools/Options -> Advanced Options -> ASR Settings:
- Set Compute data type (计算数据类型) to int8 (lowest resource) or float16 (best for GPU).
- Lower Recognition accuracy (beam_size) and best_of from 5 to 1.
- Set Enable context awareness (启用上下文感知) to False.
Ensure Menu -> Tools/Options -> Advanced Options -> Common -> Number of GPU tasks is set to 1.
If VRAM is still insufficient, uncheck Enable CUDA acceleration to run on CPU (slower).

Note: your version is v3.97.

It is recommended to upgrade to the latest version, which includes improved adaptive GPU detection (selecting the GPU with the most free VRAM).

#7626 ASR Error [faster-whisper (Local)] Traceback (most recent call last): File

1 Replies

Post Your Reply

Related resource