#8878 Error during speech recognition stage[faster-whisper(Built-in)] Unable to open file 'model.bin' in model 'F:/softwares/p

5.125**5 Posted at: 10 hours ago

Error during speech recognition stage[faster-whisper(Built-in)] Unable to open file 'model.bin' in model 'F:/softwares/pyvideotrans-main/exe/models/models--mobiuslabsgmbh--faster-whisper-large-v3-turbo',Traceback (most recent call last):
File "videotrans\process\stt_faster.py", line 103, in faster_whisper
File "videotrans\process\stt_faster.py", line 73, in _create_model
File "faster_whisper\transcribe.py", line 689, in init
RuntimeError: Unable to open file 'model.bin' in model 'F:/softwares/pyvideotrans-main/exe/models/models--mobiuslabsgmbh--faster-whisper-large-v3-turbo'

Traceback (most recent call last):
File "videotrans\task\only_one.py", line 85, in run
File "videotrans\task\_stage_recogn.py", line 64, in recogn
File "videotrans\recognition\__init__.py", line 178, 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 141, in _faster
File "videotrans\configure\base.py", line 300, in _new_process
videotrans.configure.excepts.VideoTransError: Unable to open file 'model.bin' in model 'F:/softwares/pyvideotrans-main/exe/models/models--mobiuslabsgmbh--faster-whisper-large-v3-turbo',Traceback (most recent call last):
File "videotrans\process\stt_faster.py", line 103, in faster_whisper
File "videotrans\process\stt_faster.py", line 73, in _create_model
File "faster_whisper\transcribe.py", line 689, in init
RuntimeError: Unable to open file 'model.bin' in model 'F:/softwares/pyvideotrans-main/exe/models/models--mobiuslabsgmbh--faster-whisper-large-v3-turbo'

trk=Translation V/A 单视频模式
Select Media File: V:/pocoyo 02.mp4,
Output Directory: V:/_video_out/pocoyo 02-mp4,
self.cfg.cache_folder='F:/softwares/pyvideotrans-main/exe/tmp/13540/d8858037e9'
Selected Clear Output, Not-Selected Enable accelerator
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:Persian
Traditional Translation Batch Size (Lines): 5
Dont dubbing: self.cfg.voice_role='No'
Soft Subtitles
video duration:431480ms
video information:{'video_fps': 25.0, 'r_frame_rate': 25.0, 'video_codec_name': 'h264', 'audio_codec_name': 'aac', 'width': 640, 'height': 352, 'time': 431480, 'streams_len': 2, 'streams_audio': 1, 'video_streams': 1, 'color': 'yuv420p'}
self.cfg=TaskCfgVTT(uuid='d8858037e9', name='V:/pocoyo 02.mp4', dirname='V:/', noextname='pocoyo 02', basename='pocoyo 02.mp4', ext='mp4', target_dir='V:/_video_out/pocoyo 02-mp4', cache_folder='F:/softwares/pyvideotrans-main/exe/tmp/13540/d8858037e9', is_cuda=False, source_language='English', source_language_code='en', source_sub='V:/_video_out/pocoyo 02-mp4/en.srt', source_wav='F:/softwares/pyvideotrans-main/exe/tmp/13540/d8858037e9/en.wav', source_wav_output='V:/_video_out/pocoyo 02-mp4/en.m4a', target_language='Persian', target_language_code='fa', target_sub='V:/_video_out/pocoyo 02-mp4/fa.srt', target_wav='F:/softwares/pyvideotrans-main/exe/tmp/13540/d8858037e9/target.wav', target_wav_output='V:/_video_out/pocoyo 02-mp4/fa.m4a', 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, tts_model_name=None, 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='V:/_video_out/pocoyo 02-mp4/pocoyo 02.mp4', novoice_mp4='F:/softwares/pyvideotrans-main/exe/tmp/13540/d8858037e9/novoice.mp4', is_separate=False, embed_bgm=True, instrument='F:/softwares/pyvideotrans-main/exe/tmp/13540/d8858037e9/instrument.wav', vocal='F:/softwares/pyvideotrans-main/exe/tmp/13540/d8858037e9/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=431480


=
system:Windows-10-10.0.19045-SP0
version:v4.19
frozen:True
language:en_US
root_dir:F:/softwares/pyvideotrans-main/exe

1 Replies

#1 DeepSeek reply at 10 hours ago

The model file is incomplete or failed to download: the folder models--mobiuslabsgmbh--faster-whisper-large-v3-turbo exists, but model.bin is missing inside it or is only partially downloaded (this is the most common error caused by downloading models from huggingface.co in mainland China; the directory is created first, and the large files then fail mid-way).

Solution (manual download):

  1. Close pyVideoTrans.
  2. Open F:/softwares/pyvideotrans-main/exe/models/models--mobiuslabsgmbh--faster-whisper-large-v3-turbo and check whether model.bin is present and larger than ~1.5 GB. If it is absent or only a few hundred KB, delete the entire folder named models--mobiuslabsgmbh--faster-whisper-large-v3-turbo.
  3. With a VPN/proxy enabled, open https://huggingface.co/mobiuslabsgmbh/faster-whisper-large-v3-turbo/tree/main and download all files (config.json, model.bin, tokenizer.json, vocabulary.txt, preprocessor_config.json, etc.).
  4. Recreate the folder F:/softwares/pyvideotrans-main/exe/models/models--mobiuslabsgmbh--faster-whisper-large-v3-turbo and put all downloaded files directly in it, keeping their exact original names (if the browser renamed a file to model(2).bin, rename it back to model.bin).
  5. Restart the software and run the task again with Clear Output checked.

Alternative: let the software download it automatically
Clear the Proxy field only if no proxy is needed. On the main window, fill in the working proxy in the Proxy box (format http://127.0.0.1:7890); then delete the incomplete model folder and run again, so the software can download it itself. After a failed manual download, you can also create an empty file huggingface.txt in F:/softwares/pyvideotrans-main/exe to force downloads from huggingface.co instead of the domestic mirror (this requires a working proxy).

Quick check: if you have already downloaded large-v3 or small, switch the model to that one to confirm the rest of the pipeline works, then come back to large-v3-turbo once its files are complete.

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