#4697 TaskCfgVTT(uuid='979b3b4544', name='D:/Oracle_SQL_Join_Paradox.mp4', dirname='D:/', noextname='Oracle_SQL_Join_Paradox',

2605:52c0* Posted at: 21 hours ago

下载模型失败,你可以打开以下网址,将所有文件下载到
D:/pyVideoTrans/win-pyvideotrans-v4.00-523/models/models--mobiuslabsgmbh--faster-whisper-large-v3-turbo 文件夹内

[https://huggingface.co/mobiuslabsgmbh/faster-whisper-large-v3-turbo/tree/main]
('Connection broken: IncompleteRead(985627428 bytes read, 632257501 more expected)', IncompleteRead(985627428 bytes read, 632257501 more expected))
Traceback (most recent call last):
File "urllib3\response.py", line 779, in _error_catcher
File "urllib3\response.py", line 925, in _raw_read
urllib3.exceptions.IncompleteRead: IncompleteRead(985627428 bytes read, 632257501 more expected)

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
File "requests\models.py", line 820, in generate
File "urllib3\response.py", line 1091, in stream
File "urllib3\response.py", line 1008, in read
File "urllib3\response.py", line 903, in _raw_read
File "contextlib.py", line 153, in exit
File "urllib3\response.py", line 803, in _error_catcher
urllib3.exceptions.ProtocolError: ('Connection broken: IncompleteRead(985627428 bytes read, 632257501 more expected)', IncompleteRead(985627428 bytes read, 632257501 more expected))

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "videotrans\util\help_down.py", line 59, in check_and_down_hf
File "videotrans\util\help_down.py", line 182, in down_file_from_ms
File "requests\models.py", line 822, in generate
requests.exceptions.ChunkedEncodingError: ('Connection broken: IncompleteRead(985627428 bytes read, 632257501 more expected)', IncompleteRead(985627428 bytes read, 632257501 more expected))

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "videotrans\task\only_one.py", line 47, in run
File "videotrans\task\trans_create.py", line 316, in recogn
File "videotrans\recognition\__init__.py", line 188, in run
File "videotrans\recognition\_base.py", line 90, in run
File "videotrans\recognition\_whisper.py", line 44, in _download
File "videotrans\util\help_down.py", line 97, in check_and_down_hf
RuntimeError: 下载模型失败,你可以打开以下网址,将所有文件下载到
D:/pyVideoTrans/win-pyvideotrans-v4.00-523/models/models--mobiuslabsgmbh--faster-whisper-large-v3-turbo 文件夹内

[https://huggingface.co/mobiuslabsgmbh/faster-whisper-large-v3-turbo/tree/main]
('Connection broken: IncompleteRead(985627428 bytes read, 632257501 more expected)', IncompleteRead(985627428 bytes read, 632257501 more expected))
TaskCfgVTT(uuid='979b3b4544', name='D:/Oracle_SQL_Join_Paradox.mp4', dirname='D:/', noextname='Oracle_SQL_Join_Paradox', basename='Oracle_SQL_Join_Paradox.mp4', ext='mp4', target_dir='D:/pyVideoTrans/win-pyvideotrans-v4.00-523/output/translate/Oracle_SQL_Join_Paradox-mp4', cache_folder='D:/pyVideoTrans/win-pyvideotrans-v4.00-523/tmp/4064/979b3b4544', is_cuda=False, source_language='英语', source_language_code='en', source_sub='D:/pyVideoTrans/win-pyvideotrans-v4.00-523/output/translate/Oracle_SQL_Join_Paradox-mp4/en.srt', source_wav='D:/pyVideoTrans/win-pyvideotrans-v4.00-523/tmp/4064/979b3b4544/en.wav', source_wav_output='D:/pyVideoTrans/win-pyvideotrans-v4.00-523/output/translate/Oracle_SQL_Join_Paradox-mp4/en.m4a', target_language='简体中文', target_language_code='zh-cn', target_sub='D:/pyVideoTrans/win-pyvideotrans-v4.00-523/output/translate/Oracle_SQL_Join_Paradox-mp4/zh-cn.srt', target_wav='D:/pyVideoTrans/win-pyvideotrans-v4.00-523/tmp/4064/979b3b4544/target.wav', target_wav_output='D:/pyVideoTrans/win-pyvideotrans-v4.00-523/output/translate/Oracle_SQL_Join_Paradox-mp4/zh-cn.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, 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=False, subtitle_language=None, app_mode='biaozhun', subtitles='', targetdir_mp4='D:/pyVideoTrans/win-pyvideotrans-v4.00-523/output/translate/Oracle_SQL_Join_Paradox-mp4/Oracle_SQL_Join_Paradox.mp4', novoice_mp4='D:/pyVideoTrans/win-pyvideotrans-v4.00-523/tmp/4064/979b3b4544/novoice.mp4', is_separate=False, embed_bgm=True, instrument=None, vocal='D:/pyVideoTrans/win-pyvideotrans-v4.00-523/tmp/4064/979b3b4544/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:Windows-10-10.0.26200-SP0
version:v4.00
frozen:True
language:zh
root_dir:D:/pyVideoTrans/win-pyvideotrans-v4.00-523

1 Replies

该错误是由于网络连接中断导致自动从 HuggingFace 下载 faster-whisper-large-v3-turbo 模型失败。国内访问 HuggingFace 时常出现断连或超时,需要手动下载模型文件并放置到正确路径。

解决方法:

  1. 打开以下镜像链接(或原链接),下载该模型的所有文件:

    • 镜像站: https://hf-mirror.com/mobiuslabsgmbh/faster-whisper-large-v3-turbo/tree/main
    • 原站: https://huggingface.co/mobiuslabsgmbh/faster-whisper-large-v3-turbo/tree/main
  2. 将下载的所有文件(如 model.safetensorsconfig.jsontokenizer.jsonvocabulary.json 等)放入以下文件夹(如果文件夹不存在请手动创建):

    D:/pyVideoTrans/win-pyvideotrans-v4.00-523/models/models--mobiuslabsgmbh--faster-whisper-large-v3-turbo

    注意:文件夹名称必须完全一致,不能改动。

  3. 确保文件完整,尤其是大文件(model.safetensorsmodel.bin)已完整下载(文件大小约 3GB)。可以在分区中查看属性确认。
  4. 完成放置后,重新打开软件并运行任务。

如果你希望避免频繁下载大模型,可以:

  • 改用更小的模型(mediumsmallbase),在主界面 ASR 渠道选择 faster-whisper(本地) 后,在模型下拉列表中选择较小模型。
  • 或者使用在线 ASR 渠道(如 OpenAI语音识别API字节语音大模型极速版 等),无需下载本地模型。

请查阅相关文档:

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