#8009 Subprocess Error: Error no file named model.safetensors, or pytorch_model.bin, found in directory E:/AI/pyvideotrans/mod

240e**6bb8 Posted at: 2 hours ago

Subprocess Error: Error no file named model.safetensors, or pytorch_model.bin, found in directory E:/AI/pyvideotrans/models/models--k2-fsa--OmniVoice.:
{'text': '你好啊,我亲爱的朋友,希望你的每一天都是美好愉快的!', 'rate': '+0%', 'role': 'zh_male_bj.wav', 'filename': 'C:\Users\ADMINI~1\AppData\Local\Temp/pyvideotrans/3-1791809811.7565615.wav', 'tts_type': 3, 'language': 'zh-cn', 'volume': '+10%', 'pitch': '+0Hz'}
Traceback (most recent call last):
File "videotrans\util\ListenVoice.py", line 21, in run
File "videotrans\tts\__init__.py", line 122, in run
File "videotrans\tts\_base.py", line 98, in run
File "videotrans\tts\_omnivoice.py", line 42, in _exec
File "videotrans\configure\base.py", line 277, in _new_process
videotrans.configure.excepts.VideoTransError: Subprocess Error: Error no file named model.safetensors, or pytorch_model.bin, found in directory E:/AI/pyvideotrans/models/models--k2-fsa--OmniVoice.


=
system:Windows-10-10.0.19045-SP0
version:v4.15
frozen:True
language:zh_CN
root_dir:E:/AI/pyvideotrans

1 Replies

#1 DeepSeek reply at 1 hour ago

该报错是由于 OmniVoice-TTS 模型文件缺失或下载不完整所致。底层引擎在 E:/AI/pyvideotrans/models/models--k2-fsa--OmniVoice 目录下未找到 model.safetensors 或 pytorch_model.bin 文件,导致加载失败。

模型体积较大(GB级别),自动下载极易因网络波动、代理不稳定或国内访问 huggingface.co 失败而中断,从而出现目录存在但文件缺失或损坏的情况。

请按以下步骤操作:

  1. 彻底删除损坏/不完整的模型目录:删除整个 E:/AI/pyvideotrans/models/models--k2-fsa--OmniVoice 文件夹。
  2. 手动下载模型文件:

    • 访问官方模型地址:https://huggingface.co/k2-fsa/OmniVoice/tree/main
    • 将页面上的所有文件下载到刚刚删除的文件夹 E:/AI/pyvideotrans/models/models--k2-fsa--OmniVoice 内(若文件夹不存在,请新建)。
    • 注意:若浏览器自动将文件重命名(如 model(2).safetensors),务必改回原文件名(如 model.safetensors)后才能被软件识别。
  3. 确保文件完整:下载完成后,检查目录内各文件大小是否与网页标注一致,避免出现 0KB 或半截文件。
  4. 重启软件并重新尝试配音。
若无法直接访问 huggingface.co,可尝试使用国内镜像 https://hf-mirror.com/k2-fsa/OmniVoice/tree/main 下载,完成后同样放入上述目录。

请查阅相关文档:

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