#5520 TaskCfgVTT(uuid='fb15c6d711', name='H:/115xiazai/05za2 (1)/CSPL-009 HD.wav', dirname='H:/115xiazai/05za2 (1)', noextname

147.90* Posted at: 2 hours ago

语音识别阶段出错[faster-whisper(本地内置)] No transcription results returned. Please check the original audio/video or model and try again.
Traceback (most recent call last):

File "videotrans\task\job.py", line 35, in run

File "videotrans\task\job.py", line 100, in process_task

File "videotrans\task\trans_create.py", line 322, in recogn

File "videotrans\recognition\__init__.py", line 190, in run

File "videotrans\recognition\_base.py", line 94, in run

File "videotrans\recognition\_whisper.py", line 37, in _exec

File "videotrans\recognition\_whisper.py", line 120, in _faster

File "videotrans\configure\base.py", line 258, in _new_process

videotrans.configure.excepts.VideoTransError: No transcription results returned. Please check the original audio/video or model and try again.
TaskCfgVTT(uuid='fb15c6d711', name='H:/115xiazai/05za2 (1)/CSPL-009 HD.wav', dirname='H:/115xiazai/05za2 (1)', noextname='CSPL-009 HD', basename='CSPL-009 HD.wav', ext='wav', target_dir='H:/115xiazai/05za2 (1)/_video_out/CSPL-009 HD-wav', cache_folder='D:/win-pyvideotrans-v3.99-420/tmp/8824/fb15c6d711', is_cuda=True, source_language='日语', source_language_code='ja', source_sub='H:/115xiazai/05za2 (1)/_video_out/CSPL-009 HD-wav/ja.srt', source_wav='D:/win-pyvideotrans-v3.99-420/tmp/8824/fb15c6d711/ja.wav', source_wav_output='H:/115xiazai/05za2 (1)/_video_out/CSPL-009 HD-wav/ja.m4a', target_language='简体中文', target_language_code='zh-cn', target_sub='H:/115xiazai/05za2 (1)/_video_out/CSPL-009 HD-wav/zh-cn.srt', target_wav='D:/win-pyvideotrans-v3.99-420/tmp/8824/fb15c6d711/target.wav', target_wav_output='H:/115xiazai/05za2 (1)/_video_out/CSPL-009 HD-wav/zh-cn.m4a', translate_type=0, tts_type=0, volume='+5%', pitch='+0Hz', voice_rate='+0%', voice_role='Xiaoyi(Female/CN)', voice_autorate=False, video_autorate=False, remove_silent_mid=False, align_sub_audio=False, detect_language='ja', recogn_type=0, model_name='large-v3-turbo', shibie_audio=None, remove_noise=False, enable_diariz=False, nums_diariz=0, rephrase=0, fix_punc=0, subtitle_language=None, app_mode='biaozhun', subtitles='', targetdir_mp4='H:/115xiazai/05za2 (1)/_video_out/CSPL-009 HD-wav/CSPL-009 HD.mp4', novoice_mp4='D:/win-pyvideotrans-v3.99-420/tmp/8824/fb15c6d711/novoice.mp4', is_separate=False, embed_bgm=False, instrument=None, vocal='D:/win-pyvideotrans-v3.99-420/tmp/8824/fb15c6d711/vocal.wav', clear_cache=False, background_music='', subtitle_type=0, only_out_mp4=False, recogn2pass=False, output_srt=0, copysrt_rawvideo=False, loop_backaudio=1, backaudio_volume=0.8)

=
system:Windows-10-10.0.22631-SP0
version:v4.02
frozen:True
language:zh
root_dir:D:/win-pyvideotrans-v3.99-420

1 Replies

Floor #1 DeepSeek reply at 2 hours ago

core error：No transcription results returned from faster-whisper. This usually means the recognizer either received no voice or crashed silently (GPU memory/CUDA issue, model corruption, or empty audio).

Diagnosis

Based on your log, you’re using:

  • Model: large-v3-turbo (~3GB)
  • CUDA: enabled (is_cuda=True)
  • Input file: H:/115xiazai/05za2 (1)/CSPL-009 HD.wav (contains spaces & parentheses)
  • Source language: 日语 (Japanese)

Most probable causes (ordered by likelihood):

  1. CUDA / GPU related silent crash – large-v3-turbo requires >4GB VRAM. With 8GB or less it may crash without error message. The subprocess returns empty.
  2. Audio has no detectable speech – file might be music/background noise or actual language is not Japanese.
  3. Model files missing or corrupted – especially if downloaded via proxy/huggingface before.
  4. Path containing spaces/parentheses – rare but possible when passing to subprocess.

Step-by-step fix

  1. Disable CUDA – uncheck CUDA加速 in main UI and try again. If it works, the problem is GPU memory.
  2. Switch to a smaller model – use small or tiny (Japanese works well with small) for a quick test.
  3. Verify input audio – play the file manually. Ensure it’s a clean human voice (Japanese) and not silent. Try a short test file.
  4. Move audio to simple path – rename file to something like test.wav and place it directly under D:\, then retry.
  5. Re-download the model – delete models/models--mobiuslabsgmbh--faster-whisper-large-v3-turbo/ folder and let the software re-download.

If none of the above works, try using openai-whisper(本地) instead of faster-whisper as a workaround.

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. Dondate: ko-fi.com/jianchang512

Related resource