#4420 TaskCfgVTT(is_cuda=True, uuid='63c1aba50c', cache_folder='D:/Downloads D/Tools/tmp/21924/63c1aba50c', target_dir='D:/Dow

117.2* Posted at: 2 hours ago 👁8

ASR Error [faster-whisper (Local)] Traceback (most recent call last):
File "videotrans\process\stt_fun.py", line 347, in faster_whisper
File "faster_whisper\transcribe.py", line 689, in init
RuntimeError: Unable to open file 'model.bin' in model 'D:/Downloads D/Tools/models/models--mobiuslabsgmbh--faster-whisper-large-v3-turbo'

Traceback (most recent call last):
File "videotrans\task\job.py", line 105, in run
File "videotrans\task\trans_create.py", line 380, 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 289, in _new_process
RuntimeError: Traceback (most recent call last):
File "videotrans\process\stt_fun.py", line 347, in faster_whisper
File "faster_whisper\transcribe.py", line 689, in init
RuntimeError: Unable to open file 'model.bin' in model 'D:/Downloads D/Tools/models/models--mobiuslabsgmbh--faster-whisper-large-v3-turbo'
TaskCfgVTT(is_cuda=True, uuid='63c1aba50c', cache_folder='D:/Downloads D/Tools/tmp/21924/63c1aba50c', target_dir='D:/Downloads D/Video/_video_out/如何花 1小时 让你 每月赚 3000 美元 - 抖音_3-mp4', source_language='English', source_language_code='en', source_sub='D:/Downloads D/Video/_video_out/如何花 1小时 让你 每月赚 3000 美元 - 抖音_3-mp4/en.srt', source_wav='D:/Downloads D/Tools/tmp/21924/63c1aba50c/en.wav', source_wav_output='D:/Downloads D/Video/_video_out/如何花 1小时 让你 每月赚 3000 美元 - 抖音_3-mp4/en.m4a', target_language='Vietnamese', target_language_code='vi', target_sub='D:/Downloads D/Video/_video_out/如何花 1小时 让你 每月赚 3000 美元 - 抖音_3-mp4/vi.srt', target_wav='D:/Downloads D/Tools/tmp/21924/63c1aba50c/target.wav', target_wav_output='D:/Downloads D/Video/_video_out/如何花 1小时 让你 每月赚 3000 美元 - 抖音_3-mp4/vi.m4a', name='D:/Downloads D/Video/如何花 1小时 让你 每月赚 3000 美元 - 抖音_3.mp4', noextname='如何花 1小时 让你 每月赚 3000 美元 - 抖音_3', basename='如何花 1小时 让你 每月赚 3000 美元 - 抖音_3.mp4', ext='mp4', dirname='D:/Downloads D/Video', shound_del_name=None, translate_type=0, tts_type=0, volume='+0%', pitch='+0Hz', voice_rate='+0%', voice_role='No', 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=False, enable_diariz=False, nums_diariz=0, rephrase=0, fix_punc=False, subtitle_language=None, app_mode='biaozhun', subtitles='', targetdir_mp4='D:/Downloads D/Video/_video_out/如何花 1小时 让你 每月赚 3000 美元 - 抖音_3-mp4/如何花 1小时 让你 每月赚 3000 美元 - 抖音_3.mp4', novoice_mp4='D:/Downloads D/Tools/tmp/21924/63c1aba50c/novoice.mp4', is_separate=False, embed_bgm=True, instrument=None, vocal='D:/Downloads D/Tools/tmp/21924/63c1aba50c/vocal.wav', 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:v3.99
frozen:True
language:en
root_dir:D:/Downloads D/Tools

1 Replies

Floor #1 DeepSeek AI reply at 2 hours ago

The error Unable to open file 'model.bin' indicates that the large-v3-turbo model for faster-whisper is incomplete or missing. Usually this happens because the automatic download from HuggingFace failed or was interrupted. The directory models--mobiuslabsgmbh--faster-whisper-large-v3-turbo exists but lacks the required model.bin file.

To fix this, you need to manually download the missing model files.

Steps to resolve:

  1. Delete the incomplete folder: Navigate to D:/Downloads D/Tools/models/ and remove the folder models--mobiuslabsgmbh--faster-whisper-large-v3-turbo (or keep it as a backup, but ensure a clean download).
  2. Create the folder again: Create a new empty folder with exactly the name models--mobiuslabsgmbh--faster-whisper-large-v3-turbo inside the models directory.
  3. Download the model files: Go to https://huggingface.co/mobiuslabsgmbh/faster-whisper-large-v3-turbo/tree/main and download all .json, .bin, and .txt files from that page.
  4. Place the files: Put all downloaded files into the folder you created in step 2. After this, the folder should contain files like config.json, model.bin, tokenizer.json, vocabulary.txt, etc.
  5. Restart the software and run the translation again.

Important: Because your software is installed under D:/Downloads D/, which contains a space, and you are processing a file with Chinese characters and spaces in its name, you may encounter unexpected issues on Windows (e.g., path length limits or special character errors). For best results, move the software to a path like D:\pyVideoTrans and your video to a simple, short path (e.g., D:\videos\video1.mp4) with no special symbols.

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