#3181 TaskCfg(cache_folder='D:/HuaweiMoveData/Users/domoto/Desktop/win-pyvideotrans-v3.96-24/tmp/17532/25c5968c39', target_dir

2409:8a62* Posted at: 15 hours ago 👁12

语音识别阶段出错 [openai-whisper(本地)] Traceback (most recent call last):
File "videotrans\process\stt_fun.py", line 61, in openai_whisper
File "whisper\__init__.py", line 143, in load_model
RuntimeError: Model distil-large-v3.5 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 106, in run
File "videotrans\task\trans_create.py", line 358, in recogn
File "videotrans\recognition\__init__.py", line 282, in run
File "videotrans\recognition\_base.py", line 141, in run
File "videotrans\recognition\_overall.py", line 61, in _exec
File "videotrans\recognition\_overall.py", line 106, in _openai
File "videotrans\configure\_base.py", line 276, in _new_process
RuntimeError: Traceback (most recent call last):
File "videotrans\process\stt_fun.py", line 61, in openai_whisper
File "whisper\__init__.py", line 143, in load_model
RuntimeError: Model distil-large-v3.5 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']
TaskCfg(cache_folder='D:/HuaweiMoveData/Users/domoto/Desktop/win-pyvideotrans-v3.96-24/tmp/17532/25c5968c39', target_dir='D:/HuaweiMoveData/Users/domoto/Desktop/烤肉/短片合集/1/_video_out/Hudson_Williams短片合集.The_Interview.35549086384-mp4', remove_noise=False, is_separate=False, detect_language='en', subtitle_language=None, source_language='英语', target_language='简体中文', source_language_code='en', target_language_code='zh-cn', source_sub='D:/HuaweiMoveData/Users/domoto/Desktop/烤肉/短片合集/1/_video_out/Hudson_Williams短片合集.The_Interview.35549086384-mp4/en.srt', target_sub='D:/HuaweiMoveData/Users/domoto/Desktop/烤肉/短片合集/1/_video_out/Hudson_Williams短片合集.The_Interview.35549086384-mp4/zh-cn.srt', source_wav='D:/HuaweiMoveData/Users/domoto/Desktop/win-pyvideotrans-v3.96-24/tmp/17532/25c5968c39/en.wav', source_wav_output='D:/HuaweiMoveData/Users/domoto/Desktop/烤肉/短片合集/1/_video_out/Hudson_Williams短片合集.The_Interview.35549086384-mp4/en.m4a', target_wav='D:/HuaweiMoveData/Users/domoto/Desktop/win-pyvideotrans-v3.96-24/tmp/17532/25c5968c39/target.wav', target_wav_output='D:/HuaweiMoveData/Users/domoto/Desktop/烤肉/短片合集/1/_video_out/Hudson_Williams短片合集.The_Interview.35549086384-mp4/zh-cn.m4a', subtitles='', novoice_mp4='D:/HuaweiMoveData/Users/domoto/Desktop/win-pyvideotrans-v3.96-24/tmp/17532/25c5968c39/novoice.mp4', noextname='Hudson_Williams短片合集.The_Interview.35549086384', shibie_audio=None, targetdir_mp4='D:/HuaweiMoveData/Users/domoto/Desktop/烤肉/短片合集/1/_video_out/Hudson_Williams短片合集.The_Interview.35549086384-mp4/Hudson_Williams短片合集.The_Interview.35549086384.mp4', instrument=None, vocal=None, back_audio='', background_music=None, app_mode='tiqu', subtitle_type=0, volume='+0%', pitch='+0Hz', voice_rate='+0%', voice_role='No', copysrt_rawvideo=False, clear_cache=False, translate_type=0, tts_type=0, recogn_type=1, model_name='distil-large-v3.5', voice_autorate=False, video_autorate=False, cuda=False, name='D:/HuaweiMoveData/Users/domoto/Desktop/烤肉/短片合集/1/Hudson_Williams短片合集.The_Interview.35549086384.mp4', basename='Hudson_Williams短片合集.The_Interview.35549086384.mp4', ext='mp4', dirname='D:/HuaweiMoveData/Users/domoto/Desktop/烤肉/短片合集/1', shound_del_name=None, uuid='25c5968c39', remove_silent_mid=False, align_sub_audio=True, enable_diariz=False, nums_diariz=0, rephrase=0, only_out_mp4=False, fix_punc=False, recogn2pass=True)


=
system:Windows-10-10.0.26100-SP0
version:v3.96
frozen:True
language:zh
root_dir:D:/HuaweiMoveData/Users/domoto/Desktop/win-pyvideotrans-v3.96-24

1 Replies

错误原因是 openai-whisper(本地) 语音识别渠道尝试加载一个不存在的模型 distil-large-v3.5。该模型不在 OpenAI Whisper 官方支持的模型列表中。

解决方案:

  1. 检查并更改模型名称:在软件主界面的“语音识别渠道”设置中,确认你选择的模型是 openai-whisper(本地)。在旁边的模型选择下拉框中,选择一个官方支持的模型,例如 large-v3large-v3-turbolarge-v2distil-large-v3.5 不是有效的 Whisper 模型名。
  2. 手动下载模型(可选):如果你确实需要使用 distil-large-v3.5 这类非官方模型,你需要手动将其下载并放置到正确的目录。根据知识库,模型应放置在 models/ 目录下,且文件夹命名需严格遵循规则(例如 models--Systran--faster-whisper-large-v3)。对于 openai-whisper,模型文件通常为 .pt 格式,需放置在 models/whisper/ 目录下。但请注意,distil-large-v3.5 可能是一个社区蒸馏模型,并非官方发布,你需要确保其文件格式与 Whisper 兼容。
  3. 使用 faster-whisper 替代:如果目的是使用 large-v3 模型并希望获得更快的速度,建议直接切换到 faster-whisper(本地) 渠道,它同样支持 large-v3 模型,且效率更高。

根本原因分析:

  • 模型列表 ['tiny.en', 'tiny', 'base.en', 'base', 'small.en', 'small', 'medium.en', 'medium', 'large-v1', 'large-v2', 'large-v3', 'large', 'large-v3-turbo', 'turbo'] 是 OpenAI Whisper 官方提供的所有模型。distil-large-v3.5 不在其中,因此软件无法加载。

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