#8729 Error during speech recognition stage[faster-whisper(Built-in)] Unable to open file 'model.bin' in model 'C:/Users/QUASI

2a02**86f2 Posted at: 42 minutes ago

Error during speech recognition stage[faster-whisper(Built-in)] Unable to open file 'model.bin' in model 'C:/Users/QUASI/Downloads/win-pyvideotrans-v4.18-1106 - extracted/models/models--mobiuslabsgmbh--faster-whisper-large-v3-turbo',Traceback (most recent call last):
File "videotrans\process\stt_faster.py", line 84, in faster_whisper
File "videotrans\process\stt_faster.py", line 54, in _create_model
File "faster_whisper\transcribe.py", line 689, in init
RuntimeError: Unable to open file 'model.bin' in model 'C:/Users/QUASI/Downloads/win-pyvideotrans-v4.18-1106 - extracted/models/models--mobiuslabsgmbh--faster-whisper-large-v3-turbo'

Traceback (most recent call last):
File "videotrans\task\only_one.py", line 84, in run
File "videotrans\task\_stage_recogn.py", line 64, in recogn
File "videotrans\recognition\__init__.py", line 148, in run
File "videotrans\recognition\_base.py", line 101, in run
File "videotrans\recognition\_whisper.py", line 39, in _exec
File "videotrans\recognition\_whisper.py", line 136, in _faster
File "videotrans\configure\base.py", line 291, in _new_process
videotrans.configure.excepts.VideoTransError: Unable to open file 'model.bin' in model 'C:/Users/QUASI/Downloads/win-pyvideotrans-v4.18-1106 - extracted/models/models--mobiuslabsgmbh--faster-whisper-large-v3-turbo',Traceback (most recent call last):
File "videotrans\process\stt_faster.py", line 84, in faster_whisper
File "videotrans\process\stt_faster.py", line 54, in _create_model
File "faster_whisper\transcribe.py", line 689, in init
RuntimeError: Unable to open file 'model.bin' in model 'C:/Users/QUASI/Downloads/win-pyvideotrans-v4.18-1106 - extracted/models/models--mobiuslabsgmbh--faster-whisper-large-v3-turbo'

trk=Translation V/A 单视频模式
Select Media File: C:/Users/QUASI/iTubeGo/Download/Claude And New UE 5.8 MCP is Crazy Good (But I made it better).mp4,
Output Directory: C:/Users/QUASI/Downloads/مدبلج/Claude And New UE 5.8 MCP is Crazy Good (But I made it better)-mp4,
self.cfg.cache_folder='C:/Users/QUASI/Downloads/win-pyvideotrans-v4.18-1106 - extracted/tmp/18692/609a5e5a61'
Selected Clear Output, Selected Enable CUDA
STT Service:faster-whisper(Built-in), large-v3-turbo, Spoken: English
Max Speech Duration (s): 5s
Min Speech Duration (ms): 3000ms
Min Silence Duration for Split (ms): 600ms
VAD Speech Threshold: 0.45
VAD Engine: silero
Compute Type:default
Beam Size:5
Best Of:5
Condition on Previous Text:False
Repetition Penalty:1.0
Compression Ratio Threshold:2.4
TranslateSrt:Google Translate (Free),Spoken:English,Target:Arabic
Traditional Translation Batch Size (Lines): 5
TTS Service:Edge-TTS (Free), Voices:Abdullah(Male/OM), Target:Arabic
Volume:+0%, Speed:+0%, Selected TTS Speedup, Not-Selected Slow Video
Selected Trim Start/End Silence in Dubbed Segments
Silence Removal Intensity: default
Soft Subtitles
video duration:1005771ms
video information:{'video_fps': 29.97002997002997, 'r_frame_rate': 29.97002997002997, 'video_codec_name': 'h264', 'audio_codec_name': 'aac', 'width': 854, 'height': 480, 'time': 1005771, 'streams_len': 2, 'streams_audio': 1, 'video_streams': 1, 'color': 'yuv420p'}
self.cfg=TaskCfgVTT(uuid='609a5e5a61', name='C:/Users/QUASI/iTubeGo/Download/Claude And New UE 5.8 MCP is Crazy Good (But I made it better).mp4', dirname='C:/Users/QUASI/iTubeGo/Download', noextname='Claude And New UE 5.8 MCP is Crazy Good (But I made it better)', basename='Claude And New UE 5.8 MCP is Crazy Good (But I made it better).mp4', ext='mp4', target_dir='C:/Users/QUASI/Downloads/مدبلج/Claude And New UE 5.8 MCP is Crazy Good (But I made it better)-mp4', cache_folder='C:/Users/QUASI/Downloads/win-pyvideotrans-v4.18-1106 - extracted/tmp/18692/609a5e5a61', is_cuda=True, source_language='English', source_language_code='en', source_sub='C:/Users/QUASI/Downloads/مدبلج/Claude And New UE 5.8 MCP is Crazy Good (But I made it better)-mp4/en.srt', source_wav='C:/Users/QUASI/Downloads/win-pyvideotrans-v4.18-1106 - extracted/tmp/18692/609a5e5a61/en.wav', source_wav_output='C:/Users/QUASI/Downloads/مدبلج/Claude And New UE 5.8 MCP is Crazy Good (But I made it better)-mp4/en.m4a', target_language='Arabic', target_language_code='ar', target_sub='C:/Users/QUASI/Downloads/مدبلج/Claude And New UE 5.8 MCP is Crazy Good (But I made it better)-mp4/ar.srt', target_wav='C:/Users/QUASI/Downloads/win-pyvideotrans-v4.18-1106 - extracted/tmp/18692/609a5e5a61/target.wav', target_wav_output='C:/Users/QUASI/Downloads/مدبلج/Claude And New UE 5.8 MCP is Crazy Good (But I made it better)-mp4/ar.m4a', translate_type=0, tts_type=0, volume='+0%', pitch='+0Hz', voice_rate='+0%', voice_role='Abdullah(Male/OM)', 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=False, fix_punc=0, app_mode='biaozhun', subtitle_language=None, targetdir_mp4='C:/Users/QUASI/Downloads/مدبلج/Claude And New UE 5.8 MCP is Crazy Good (But I made it better)-mp4/Claude And New UE 5.8 MCP is Crazy Good (But I made it better).mp4', novoice_mp4='C:/Users/QUASI/Downloads/win-pyvideotrans-v4.18-1106 - extracted/tmp/18692/609a5e5a61/novoice.mp4', is_separate=False, embed_bgm=True, instrument='C:/Users/QUASI/Downloads/win-pyvideotrans-v4.18-1106 - extracted/tmp/18692/609a5e5a61/instrument.wav', vocal='C:/Users/QUASI/Downloads/win-pyvideotrans-v4.18-1106 - extracted/tmp/18692/609a5e5a61/vocal.wav', clear_cache=True, background_music='', subtitle_type=2, only_out_mp4=False, recogn2pass=False, output_srt=0, copysrt_rawvideo=False, loop_backaudio=1, backaudio_volume=0.8, batch=False)
video_duration_ms=1005771

=
system:Windows-10-10.0.26200-SP0
version:v4.18
frozen:True
language:en_US
root_dir:C:/Users/QUASI/Downloads/win-pyvideotrans-v4.18-1106 - extracted

1 Replies

#1 DeepSeek reply at 42 minutes ago

This is because the large-v3-turbo model file was not fully downloaded: the folder models/models--mobiuslabsgmbh--faster-whisper-large-v3-turbo exists, but the core weights file model.bin is missing (the download was interrupted or failed). It is not an issue with CUDA or speech recognition itself.

Solution (choose one):

  1. Re-download automatically: delete the entire folder C:/Users/QUASI/Downloads/win-pyvideotrans-v4.18-1106 - extracted/models/models--mobiuslabsgmbh--faster-whisper-large-v3-turbo, make sure the proxy/VPN is working, then run the task again and let the software download it again.

  2. Manual download (most reliable):

    • Open https://huggingface.co/mobiuslabsgmbh/faster-whisper-large-v3-turbo/tree/main
    • Download all files in the repository (at least model.bin, config.json, tokenizer.json, vocabulary.txt, preprocessor_config.json, etc.)
    • Put them all into C:/Users/QUASI/Downloads/win-pyvideotrans-v4.18-1106 - extracted/models/models--mobiuslabsgmbh--faster-whisper-large-v3-turbo
    • Note: if the browser saves a file as model(2).bin, you must rename it back to model.bin, otherwise the software still cannot find it.
  3. Temporary workaround: change the model to large-v3 (or medium/small) and run again; the problem is specific to this model folder.

Additional suggestions (to avoid other errors later), please adjust:

  1. Move the software to a short path that contains only English letters and digits, for example D:\pyVideoTrans. The current path contains spaces and - extracted, which easily causes ffmpeg failures.
  2. The output directory contains Arabic characters (C:/Users/QUASI/Downloads/مدبلج/...). Change it to an English-only path, otherwise the video assembly step is very likely to report an error.

Please refer to the related documentation:

Thinking...
Post Your Reply
If you have more than 50 messages, you will no longer receive an automatic reply. Please ask a new question!
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 via ko-fi.com

Related resource