#3031 TaskCfg(cache_folder='F:/EDITVIDEO/win-pyvideotrans-v3.96/tmp/13104/11c1281577', target_dir='F:/EDITVIDEO/win-pyvideotra

117.1* Posted at: 15 days ago 👁28

ASR Error [faster-whisper (Local)] Traceback (most recent call last):
File "videotrans\process\stt_fun.py", line 179, in faster_whisper
File "faster_whisper\transcribe.py", line 689, in init
RuntimeError: Unable to open file 'model.bin' in model 'F:/EDITVIDEO/win-pyvideotrans-v3.96/models/models--Systran--faster-whisper-large-v3'

Traceback (most recent call last):
File "videotrans\task\job.py", line 106, in run
File "videotrans\task\_speech2text.py", line 156, in recogn
File "videotrans\recognition\__init__.py", line 284, in run
File "videotrans\recognition\_base.py", line 141, in run
File "videotrans\recognition\_overall.py", line 63, in _exec
File "videotrans\recognition\_overall.py", line 142, in _faster
File "videotrans\configure\_base.py", line 276, in _new_process
RuntimeError: Traceback (most recent call last):
File "videotrans\process\stt_fun.py", line 179, in faster_whisper
File "faster_whisper\transcribe.py", line 689, in init
RuntimeError: Unable to open file 'model.bin' in model 'F:/EDITVIDEO/win-pyvideotrans-v3.96/models/models--Systran--faster-whisper-large-v3'
TaskCfg(cache_folder='F:/EDITVIDEO/win-pyvideotrans-v3.96/tmp/13104/11c1281577', target_dir='F:/EDITVIDEO/win-pyvideotrans-v3.96/output/recogn', remove_noise=False, is_separate=False, detect_language='zh-cn', subtitle_language=None, source_language=None, target_language=None, source_language_code=None, target_language_code=None, source_sub=None, target_sub='F:/EDITVIDEO/win-pyvideotrans-v3.96/output/recogn/Chinese Haircut 316_480p.srt', source_wav=None, source_wav_output=None, target_wav=None, target_wav_output=None, subtitles='', novoice_mp4=None, noextname='Chinese Haircut 316_480p', shibie_audio='F:/EDITVIDEO/win-pyvideotrans-v3.96/tmp/13104/11c1281577/Chinese Haircut 316_480p-1769947485.7469835.wav', targetdir_mp4=None, instrument=None, vocal=None, back_audio=None, background_music=None, app_mode='biaozhun', subtitle_type=0, volume='+0%', pitch='+0Hz', voice_rate='+0%', voice_role=None, copysrt_rawvideo=False, clear_cache=False, translate_type=None, tts_type=None, recogn_type=0, model_name='large-v3', voice_autorate=False, video_autorate=False, cuda=True, name='F:/video/china haircut/Chinese Haircut 316_480p.mp4', basename='Chinese Haircut 316_480p.mp4', ext='mp4', dirname='F:/video/china haircut', shound_del_name=None, uuid='11c1281577', remove_silent_mid=False, align_sub_audio=True, enable_diariz=False, nums_diariz=0, rephrase=0, only_out_mp4=False, fix_punc=False, recogn2pass=False)

=
system:Windows-10-10.0.26100-SP0
version:v3.96
frozen:True
language:en
root_dir:F:/EDITVIDEO/win-pyvideotrans-v3.96

1 Replies

Floor #1 DeepSeek Posted at 15 days ago

The error is caused by a missing or corrupted model.bin file for the faster-whisper model in your local models directory.

Solution:

  1. Manually download the model: Since the automatic download from HuggingFace may have failed, you need to download the model manually.

    • Go to the HuggingFace model page: https://huggingface.co/Systran/faster-whisper-large-v3.
    • Click on "Files and versions".
    • Download the following files: config.json, model.bin, preprocessor_config.json, tokenizer.json, vocabulary.json. You may need to use a VPN or a HuggingFace mirror site if you are in a region with network restrictions.

  2. Place the files correctly: Create the exact folder structure in your pyVideoTrans models directory.

    • Navigate to F:/EDITVIDEO/win-pyvideotrans-v3.96/models/.
    • Create a folder named exactly: models--Systran--faster-whisper-large-v3.
    • Place all the downloaded files (model.bin, config.json, etc.) directly inside this folder. Do not create any subfolders.
  3. Restart the software: Close and restart sp.exe. The software should now be able to load the model from your local directory.

If manual download is not feasible:

  • Configure a network proxy within the software's settings to allow it to download the model automatically.
  • Alternatively, switch to a different, smaller ASR model (e.g., large-v2 or medium) which might already be present or easier to download.

Please refer to the relevant documentation:

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

Similar issues already exist