#2125 TaskCfg(cache_folder='G:/AI/win-videotrans-v3.86/tmp29680/speech2text', target_dir='g:/ai/win-videotrans-v3.84/output/re

209.9* Posted at: 1 day ago 👁18

语音识别阶段出错:[faster-whisper(本地)] 网络连接失败:
Traceback (most recent call last):
File "videotrans\task\job.py", line 113, in run
File "videotrans\task\_speech2text.py", line 140, in recogn
File "videotrans\recognition\__init__.py", line 236, in run
File "videotrans\recognition\_base.py", line 78, in run
File "videotrans\recognition\_overall.py", line 193, in _exec
RuntimeError: 下载模型失败了，请确认网络稳定并能连接 huggingface.co
更多下载方法查看 https://pvt9.com/819

TaskCfg(cache_folder='G:/AI/win-videotrans-v3.86/tmp29680/speech2text', target_dir='g:/ai/win-videotrans-v3.84/output/recogn', remove_noise=False, is_separate=False, detect_language='en', subtitle_language=None, source_language=None, target_language=None, source_language_code=None, target_language_code=None, source_sub=None, target_sub='g:/ai/win-videotrans-v3.84/output/recogn/Create AI Animated Stories With Nano Banana Pro (AI Animation Tutorial).srt', source_wav=None, source_wav_output=None, target_wav=None, target_wav_output=None, subtitles=None, novoice_mp4=None, noextname='Create AI Animated Stories With Nano Banana Pro (AI Animation Tutorial)', shibie_audio='G:/AI/win-videotrans-v3.86/tmp29680/speech2text/Create AI Animated Stories With Nano Banana Pro (AI Animation Tutorial)-1766070921.859661.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='distil-large-v3', split_type=0, voice_autorate=False, video_autorate=False, cuda=True, name='D:/下载/视频分享/Create AI Animated Stories With Nano Banana Pro (AI Animation Tutorial)/Create AI Animated Stories With Nano Banana Pro (AI Animation Tutorial).mp4', basename='Create AI Animated Stories With Nano Banana Pro (AI Animation Tutorial).mp4', ext='mp4', dirname='D:/下载/视频分享/Create AI Animated Stories With Nano Banana Pro (AI Animation Tutorial)', shound_del_name=None, uuid='9beb7f9373', remove_silent_mid=False, align_sub_audio=True, enable_diariz=False, nums_diariz=0, auto_fix=True)

=
system:Windows-10-10.0.26200-SP0
version:v3.86
frozen:True
language:zh
root_dir:G:/AI/win-videotrans-v3.86

1 Replies

Floor #1 DeepSeek Posted at 1 day ago

这个错误是由于无法从 Hugging Face 下载 distil-large-v3 语音识别模型导致的。请按以下步骤解决：

  1. 手动下载模型（推荐）：

    • 访问官方提供的下载链接：https://pvt9.com/819。
    • 根据页面指引，下载 distil-large-v3 模型文件。
    • 将下载的模型文件夹（例如 distil-large-v3）放置到软件目录下的 models 文件夹中（路径示例：G:/AI/win-videotrans-v3.86/models/）。如果 models 文件夹不存在，请手动创建一个。

  2. 更换模型（临时方案）：

    • 在软件主界面的“语音识别”区域，将模型从 distil-large-v3 更换为软件内置的、可能已缓存的较小模型，例如 large-v3 或 medium。这些模型如果之前成功下载过，可以直接使用。

  3. 检查网络环境：

    • 确保你的网络可以正常访问 https://huggingface.co。如果网络受限，可能需要使用代理。你可以在软件主界面第5行的“网络代理”处填写你的代理地址（例如 http://127.0.0.1:10809）。

完成手动下载并放置模型后，重新启动软件再试。如果问题依旧，请提供 G:/AI/win-videotrans-v3.86/logs/ 目录下的最新日志文件。

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.

Donate: https://ko-fi.com/jianchang512

Trending Questions