#5248 TaskCfgVTT(uuid='17fe7cfba2', name='/Users/zhangzhaoyang/Downloads/v12044gd0000d8lmvbvog65ke7kte260.MP4', dirname='/User

149.119* Posted at: 17 hours ago

Unable to open file 'model.bin' in model '/Users/zhangzhaoyang/pyvideotrans/models/models--mobiuslabsgmbh--faster-whisper-large-v3-turbo',Traceback (most recent call last):
File "/Users/zhangzhaoyang/pyvideotrans/videotrans/process/stt_fun.py", line 207, in faster_whisper

model = _create_model(compute_type)

File "/Users/zhangzhaoyang/pyvideotrans/videotrans/process/stt_fun.py", line 172, in _create_model

model = WhisperModel(

File "/Users/zhangzhaoyang/pyvideotrans/.venv/lib/python3.10/site-packages/faster_whisper/transcribe.py", line 689, in init

self.model = ctranslate2.models.Whisper(

RuntimeError: Unable to open file 'model.bin' in model '/Users/zhangzhaoyang/pyvideotrans/models/models--mobiuslabsgmbh--faster-whisper-large-v3-turbo'
[faster-whisper(LocalBuilt-in), Local/Compatible AI, Edge-TTS(Free)]
Traceback (most recent call last):
File "/Users/zhangzhaoyang/pyvideotrans/videotrans/task/only_one.py", line 47, in run

trk.recogn()

File "/Users/zhangzhaoyang/pyvideotrans/videotrans/task/trans_create.py", line 322, in recogn

raw_subtitles = run_recogn(

File "/Users/zhangzhaoyang/pyvideotrans/videotrans/recognition/__init__.py", line 190, in run

return _cls(**kwargs).run()  # type:ignore

File "/Users/zhangzhaoyang/pyvideotrans/videotrans/recognition/_base.py", line 94, in run

res = self._exec()

File "/Users/zhangzhaoyang/pyvideotrans/videotrans/recognition/_whisper.py", line 37, in _exec

raws = self._faster()

File "/Users/zhangzhaoyang/pyvideotrans/videotrans/recognition/_whisper.py", line 120, in _faster

raws=self._new_process(callback=faster_whisper,title=title,is_cuda=self.is_cuda,kwargs=kwargs)

File "/Users/zhangzhaoyang/pyvideotrans/videotrans/configure/base.py", line 258, in _new_process

raise VideoTransError(err)

videotrans.configure.excepts.VideoTransError: Unable to open file 'model.bin' in model '/Users/zhangzhaoyang/pyvideotrans/models/models--mobiuslabsgmbh--faster-whisper-large-v3-turbo',Traceback (most recent call last):
File "/Users/zhangzhaoyang/pyvideotrans/videotrans/process/stt_fun.py", line 207, in faster_whisper

model = _create_model(compute_type)

File "/Users/zhangzhaoyang/pyvideotrans/videotrans/process/stt_fun.py", line 172, in _create_model

model = WhisperModel(

File "/Users/zhangzhaoyang/pyvideotrans/.venv/lib/python3.10/site-packages/faster_whisper/transcribe.py", line 689, in init

self.model = ctranslate2.models.Whisper(

RuntimeError: Unable to open file 'model.bin' in model '/Users/zhangzhaoyang/pyvideotrans/models/models--mobiuslabsgmbh--faster-whisper-large-v3-turbo'
TaskCfgVTT(uuid='17fe7cfba2', name='/Users/zhangzhaoyang/Downloads/v12044gd0000d8lmvbvog65ke7kte260.MP4', dirname='/Users/zhangzhaoyang/Downloads', noextname='v12044gd0000d8lmvbvog65ke7kte260', basename='v12044gd0000d8lmvbvog65ke7kte260.MP4', ext='mp4', target_dir='/Users/zhangzhaoyang/Downloads/_video_out/v12044gd0000d8lmvbvog65ke7kte260-mp4', cache_folder='/Users/zhangzhaoyang/pyvideotrans/tmp/58089/17fe7cfba2', is_cuda=False, source_language='English', source_language_code='en', source_sub='/Users/zhangzhaoyang/Downloads/_video_out/v12044gd0000d8lmvbvog65ke7kte260-mp4/en.srt', source_wav='/Users/zhangzhaoyang/pyvideotrans/tmp/58089/17fe7cfba2/en.wav', source_wav_output='/Users/zhangzhaoyang/Downloads/_video_out/v12044gd0000d8lmvbvog65ke7kte260-mp4/en.m4a', target_language='Simplified Chinese', target_language_code='zh-cn', target_sub='/Users/zhangzhaoyang/Downloads/_video_out/v12044gd0000d8lmvbvog65ke7kte260-mp4/zh-cn.srt', target_wav='/Users/zhangzhaoyang/pyvideotrans/tmp/58089/17fe7cfba2/target.wav', target_wav_output='/Users/zhangzhaoyang/Downloads/_video_out/v12044gd0000d8lmvbvog65ke7kte260-mp4/zh-cn.m4a', translate_type=8, 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=0, subtitle_language=None, app_mode='biaozhun', subtitles='', targetdir_mp4='/Users/zhangzhaoyang/Downloads/_video_out/v12044gd0000d8lmvbvog65ke7kte260-mp4/v12044gd0000d8lmvbvog65ke7kte260.mp4', novoice_mp4='/Users/zhangzhaoyang/pyvideotrans/tmp/58089/17fe7cfba2/novoice.mp4', is_separate=False, embed_bgm=True, instrument=None, vocal='/Users/zhangzhaoyang/pyvideotrans/tmp/58089/17fe7cfba2/vocal.wav', clear_cache=True, background_music='', subtitle_type=1, only_out_mp4=False, recogn2pass=False, output_srt=0, copysrt_rawvideo=False, loop_backaudio=1, backaudio_volume=0.8)

=
system:macOS-14.4.1-arm64-arm-64bit
version:v4.02
frozen:False
language:en
root_dir:/Users/zhangzhaoyang/pyvideotrans
Python: 3.10.19 (main, Feb 12 2026, 00:36:33) [Clang 21.1.4 ]

1 Replies

Floor #1 DeepSeek reply at 17 hours ago

The error indicates that the Faster-Whisper model file model.bin is missing from the local cache directory /Users/zhangzhaoyang/pyvideotrans/models/models--mobiuslabsgmbh--faster-whisper-large-v3-turbo. This usually happens when the automatic download was interrupted or the model was only partially downloaded.

Solution: Manually download the missing model files

  1. Delete the incomplete model directory (to force a fresh download):

    rm -rf /Users/zhangzhaoyang/pyvideotrans/models/models--mobiuslabsgmbh--faster-whisper-large-v3-turbo
  2. Re-run the software – it will attempt to download the model again. If the automatic download fails again (due to network restrictions), use the manual steps below.

Manual download (recommended for China users)

Since you're on macOS, use the ModelScope mirror (faster and more reliable):

  1. Create the folder:

    mkdir -p /Users/zhangzhaoyang/pyvideotrans/models/models--mobiuslabsgmbh--faster-whisper-large-v3-turbo
cd /Users/zhangzhaoyang/pyvideotrans/models/models--mobiuslabsgmbh--faster-whisper-large-v3-turbo

  2. Download all required files from the mirror:

    wget -c "https://modelscope.cn/models/himyworld/fasterwhisper/resolve/master/faster-whisper-large-v3-turbo/model.bin"
wget -c "https://modelscope.cn/models/himyworld/fasterwhisper/resolve/master/faster-whisper-large-v3-turbo/config.json"
wget -c "https://modelscope.cn/models/himyworld/fasterwhisper/resolve/master/faster-whisper-large-v3-turbo/tokenizer.json"
wget -c "https://modelscope.cn/models/himyworld/fasterwhisper/resolve/master/faster-whisper-large-v3-turbo/vocabulary.json"

    (If wget is not installed, use brew install wget first, or use curl -O <url>)

  3. Verify files: ensure model.bin (approx. 1.6 GB) is fully downloaded. You can check size with ls -lh.

After completion, restart the software. The model should be loaded correctly.

Alternative: Use a different, smaller model

If the download is too large or slow, switch to a smaller model like medium:

  • In the software interface, change the ASR model from large-v3-turbo to medium (or base). The corresponding model folder name would be models--Systran--faster-whisper-medium.

Reference:

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

Similar issues already exist