#3489 TaskCfgVTT(is_cuda=True, uuid='86d7239a1d', cache_folder='D:/Program Files/win-pyvideotrans-v3.97-0303/tmp/3512/86d7239a

82.152* Posted at: 1 hour ago 👁5

语音识别阶段出错 [openai-whisper(本地)] Traceback (most recent call last):
File "videotrans\process\stt_fun.py", line 63, in openai_whisper
File "whisper\__init__.py", line 143, in load_model
RuntimeError: Model distil-large-v3 not found; available models = ['tiny.en', 'tiny', 'base.en', 'base', 'small.en', 'small', 'medium.en', 'medium', 'large-v1', 'large-v2', 'large-v3', 'large', 'large-v3-turbo', 'turbo']

Traceback (most recent call last):
File "videotrans\task\job.py", line 105, in run
File "videotrans\task\trans_create.py", line 353, in recogn
File "videotrans\recognition\__init__.py", line 265, in run
File "videotrans\recognition\_base.py", line 143, in run
File "videotrans\recognition\_overall.py", line 31, in _exec
File "videotrans\recognition\_overall.py", line 73, in _openai
File "videotrans\configure\_base.py", line 288, in _new_process
RuntimeError: Traceback (most recent call last):
File "videotrans\process\stt_fun.py", line 63, in openai_whisper
File "whisper\__init__.py", line 143, in load_model
RuntimeError: Model distil-large-v3 not found; available models = ['tiny.en', 'tiny', 'base.en', 'base', 'small.en', 'small', 'medium.en', 'medium', 'large-v1', 'large-v2', 'large-v3', 'large', 'large-v3-turbo', 'turbo']
TaskCfgVTT(is_cuda=True, uuid='86d7239a1d', cache_folder='D:/Program Files/win-pyvideotrans-v3.97-0303/tmp/3512/86d7239a1d', target_dir='C:/Users/47632/Desktop/_video_out/RCMP DEA FLATTEN Quebec BIKER NETWORK Financing Ryan Weddings DRUG EMPIRE 6 KILLED_vocals-mp3', source_language='英语', source_language_code='en', source_sub='C:/Users/47632/Desktop/_video_out/RCMP DEA FLATTEN Quebec BIKER NETWORK Financing Ryan Weddings DRUG EMPIRE 6 KILLED_vocals-mp3/en.srt', source_wav='D:/Program Files/win-pyvideotrans-v3.97-0303/tmp/3512/86d7239a1d/en.wav', source_wav_output='C:/Users/47632/Desktop/_video_out/RCMP DEA FLATTEN Quebec BIKER NETWORK Financing Ryan Weddings DRUG EMPIRE 6 KILLED_vocals-mp3/en.m4a', target_language='简体中文', target_language_code='zh-cn', target_sub='C:/Users/47632/Desktop/_video_out/RCMP DEA FLATTEN Quebec BIKER NETWORK Financing Ryan Weddings DRUG EMPIRE 6 KILLED_vocals-mp3/zh-cn.srt', target_wav='D:/Program Files/win-pyvideotrans-v3.97-0303/tmp/3512/86d7239a1d/target.wav', target_wav_output='C:/Users/47632/Desktop/_video_out/RCMP DEA FLATTEN Quebec BIKER NETWORK Financing Ryan Weddings DRUG EMPIRE 6 KILLED_vocals-mp3/zh-cn.m4a', name='C:/Users/47632/Desktop/RCMP DEA FLATTEN Quebec BIKER NETWORK Financing Ryan Weddings DRUG EMPIRE 6 KILLED_vocals.mp3', noextname='RCMP DEA FLATTEN Quebec BIKER NETWORK Financing Ryan Weddings DRUG EMPIRE 6 KILLED_vocals', basename='RCMP DEA FLATTEN Quebec BIKER NETWORK Financing Ryan Weddings DRUG EMPIRE 6 KILLED_vocals.mp3', ext='mp3', dirname='C:/Users/47632/Desktop', shound_del_name=None, translate_type=4, 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, detect_language='en', recogn_type=1, model_name='distil-large-v3', shibie_audio=None, remove_noise=False, enable_diariz=False, nums_diariz=0, rephrase=1, fix_punc=False, subtitle_language=None, app_mode='tiqu', subtitles='', targetdir_mp4='C:/Users/47632/Desktop/_video_out/RCMP DEA FLATTEN Quebec BIKER NETWORK Financing Ryan Weddings DRUG EMPIRE 6 KILLED_vocals-mp3/RCMP DEA FLATTEN Quebec BIKER NETWORK Financing Ryan Weddings DRUG EMPIRE 6 KILLED_vocals.mp4', novoice_mp4='D:/Program Files/win-pyvideotrans-v3.97-0303/tmp/3512/86d7239a1d/novoice.mp4', is_separate=False, instrument=None, vocal=None, back_audio='', clear_cache=True, background_music=None, subtitle_type=0, only_out_mp4=False, recogn2pass=True, output_srt=0, copysrt_rawvideo=False)


=
system:Windows-10-10.0.26200-SP0
version:v3.97
frozen:True
language:zh
root_dir:D:/Program Files/win-pyvideotrans-v3.97-0303

1 Replies

错误原因是 openai-whisper(本地) 语音识别渠道无法找到你指定的模型 distil-large-v3。该模型是 faster-whisper 格式的,不兼容 openai-whisper 渠道。

解决方案:

  1. 更换语音识别渠道:在软件主界面的“语音识别”行,将渠道从 openai-whisper(本地) 切换为 faster-whisper(本地)distil-large-v3 模型专为 faster-whisper 优化。
  2. 或更换模型:如果坚持使用 openai-whisper(本地) 渠道,请在右侧模型下拉列表中,选择一个可用的模型,例如 large-v3large-v3-turbo

操作步骤:

  1. 停止当前任务。
  2. 在主界面“语音识别”行,点击下拉菜单。
  3. 选择 faster-whisper(本地)
  4. 确保右侧模型选择为 distil-large-v3(或根据你的需求选择其他模型,如 large-v3)。
  5. 重新开始任务。

注意: distil-large-v3 是蒸馏模型,根据知识库第11节说明,它仅可用于识别转录英语发音的音视频。你的源语言是英语(source_language_code='en'),使用此模型是合适的。

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