#8813 Error during speech recognition stage[faster-whisper(Built-in)] The model download failed. Please click the button [Mode

2a02**8c64 Posted at: 1 day ago

Error during speech recognition stage[faster-whisper(Built-in)] The model download failed. Please click the button [Model Download URL] to manually download all files to:
C:/pyvideotrans/models/models--mobiuslabsgmbh--faster-whisper-large-v3-turbo

Traceback (most recent call last):
File "C:\pyvideotrans\videotrans\util\help_down.py", line 474, in check_and_down_ms

snapshot_download(model_id=model_id, local_files_only=True, progress_callbacks=[Pro], local_dir=local_dir)

File "C:\pyvideotrans.venv\lib\site-packages\modelscope\hub\snapshot_download.py", line 137, in snapshot_download

return _snapshot_download(

File "C:\pyvideotrans.venv\lib\site-packages\modelscope\hub\snapshot_download.py", line 283, in _snapshot_download

raise ValueError(

ValueError: Cannot find the requested files in the cached path and outgoing traffic has been disabled. To enable look-ups and downloads online, set 'local_files_only' to False.

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "C:\pyvideotrans\videotrans\util\help_down.py", line 485, in check_and_down_ms

snapshot_download(model_id=model_id, progress_callbacks=[Pro], local_dir=local_dir,

File "C:\pyvideotrans.venv\lib\site-packages\modelscope\hub\snapshot_download.py", line 137, in snapshot_download

return _snapshot_download(

File "C:\pyvideotrans.venv\lib\site-packages\modelscope\hub\snapshot_download.py", line 338, in _snapshot
......
tion was the direct cause of the following exception:

Traceback (most recent call last):
File "C:\pyvideotrans\videotrans\task\only_one.py", line 85, in run

trk.recogn()

File "C:\pyvideotrans\videotrans\task\_stage_recogn.py", line 64, in recogn

raw_subtitles = run_recogn(

File "C:\pyvideotrans\videotrans\recognition\__init__.py", line 180, in run

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

File "C:\pyvideotrans\videotrans\recognition\_base.py", line 99, in run

self._download()

File "C:\pyvideotrans\videotrans\recognition\_whisper.py", line 53, in _download

check_and_down_hf(self.model_name,repo_id,self.local_dir,callback=self._process_callback)

File "C:\pyvideotrans\videotrans\util\help_down.py", line 56, in check_and_down_hf

return check_and_down_ms(FASTER_MODELS_DICT[

File "C:\pyvideotrans\videotrans\util\help_down.py", line 491, in check_and_down_ms

raise DownloadModelsError(

videotrans.configure.excepts.DownloadModelsError: The model download failed. Please click the button [Model Download URL] to manually download all files to:
C:/pyvideotrans/models/models--mobiuslabsgmbh--faster-whisper-large-v3-turbo

trk=Translation V/A 单视频模式
Select Media File: C:/Users/RIFBrasov4/Downloads/videoplayback-mp4/videoplayback.mp4,
Output Directory: C:/Users/RIFBrasov4/Downloads/videoplayback-mp4/videoplayback-mp4,
self.cfg.cache_folder='C:/pyvideotrans/tmp/27600/94d4bb65e1'
Selected Clear Output, Not-Selected Enable accelerator
STT Service:faster-whisper(Built-in), large-v3-turbo, Spoken: Russian
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:Russian,Target:Romanian
Traditional Translation Batch Size (Lines): 5
Dont dubbing: self.cfg.voice_role='No'
Hard Subtitles
Max Line Length (CJK Characters):15, Max Line Length (Non-CJK):40
video duration:1968133ms
video information:{'video_fps': 30.0, 'r_frame_rate': 30.0, 'video_codec_name': 'h264', 'audio_codec_name': 'aac', 'width': 640, 'height': 360, 'time': 1968133, 'streams_len': 2, 'streams_audio': 1, 'video_streams': 1, 'color': 'yuv420p'}
self.cfg=TaskCfgVTT(uuid='94d4bb65e1', name='C:/Users/RIFBrasov4/Downloads/videoplayback-mp4/videoplayback.mp4', dirname='C:/Users/RIFBrasov4/Downloads/videoplayback-mp4', noextname='videoplayback', basename='videoplayback.mp4', ext='mp4', target_dir='C:/Users/RIFBrasov4/Downloads/videoplayback-mp4/videoplayback-mp4', cache_folder='C:/pyvideotrans/tmp/27600/94d4bb65e1', is_cuda=False, source_language='Russian', source_language_code='ru', source_sub='C:/Users/RIFBrasov4/Downloads/videoplayback-mp4/videoplayback-mp4/ru.srt', source_wav='C:/pyvideotrans/tmp/27600/94d4bb65e1/ru.wav', source_wav_output='C:/Users/RIFBrasov4/Downloads/videoplayback-mp4/videoplayback-mp4/ru.m4a', target_language='Romanian', target_language_code='ro', target_sub='C:/Users/RIFBrasov4/Downloads/videoplayback-mp4/videoplayback-mp4/ro.srt', target_wav='C:/pyvideotrans/tmp/27600/94d4bb65e1/target.wav', target_wav_output='C:/Users/RIFBrasov4/Downloads/videoplayback-mp4/videoplayback-mp4/ro.m4a', translate_type=0, tts_type=0, volume='+0%', pitch='+0Hz', voice_rate='+0%', voice_role='No', voice_autorate=False, video_autorate=False, remove_silent_mid=False, align_sub_audio=True, tts_model_name=None, detect_language='ru', 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/RIFBrasov4/Downloads/videoplayback-mp4/videoplayback-mp4/videoplayback.mp4', novoice_mp4='C:/pyvideotrans/tmp/27600/94d4bb65e1/novoice.mp4', is_separate=False, embed_bgm=True, instrument='C:/pyvideotrans/tmp/27600/94d4bb65e1/instrument.wav', vocal='C:/pyvideotrans/tmp/27600/94d4bb65e1/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, batch=False)
video_duration_ms=1968133


=
system:Windows-10-10.0.26300-SP0
version:v4.19
frozen:False
language:en_US
root_dir:C:/pyvideotrans
Python: 3.10.19 (main, Feb 12 2026, 00:37:08) [MSC v.1944 64 bit (AMD64)]

1 Replies

#1 DeepSeek reply at 1 day ago

The root cause: the automatic download failed. The software first tried the local cache (not found), then switched to the domestic ModelScope mirror, which does not host mobiuslabsgmbh/faster-whisper-large-v3-turbo — that is why it returned Authentication token does not exist ... may not exist or may be private. The model only exists on huggingface.co, which is unreachable without a proxy.

Fixes, in order of reliability:

Option 1: Manual download (recommended, always works)

  1. Open https://huggingface.co/mobiuslabsgmbh/faster-whisper-large-v3-turbo/tree/main (VPN/proxy required in mainland China).
  2. Download every file in the repo: config.json, model.bin (~1.6 GB), preprocessor_config.json, tokenizer.json, vocabulary.txt.
  3. Put them directly into C:/pyvideotrans/models/models--mobiuslabsgmbh--faster-whisper-large-v3-turbo/ (no extra subfolder, no model(1).bin-style renamed files — rename back to the original names).
  4. Re-run the task.

Option 2: Force download from huggingface.co instead of the mirror

  1. Create an empty text file named huggingface.txt in the software root directory C:/pyvideotrans/.
  2. Make sure a working proxy is filled into the proxy box on the main window (format http://127.0.0.1:7890).
  3. Re-run the task.

Option 3: Use a model that exists on the mirror
Switch the Model dropdown to large-v3, medium or small — these do download through ModelScope without authentication.

Note: your environment is a source deployment (frozen:False, Python 3.10.19, v4.19) in C:/pyvideotrans, so the paths above are correct as they stand; also confirm there is no netoffline.txt in C:/pyvideotrans/, which would force offline mode and block all downloads.

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