#8322 Subprocess Error: Error no file named model.safetensors, or pytorch_model.bin, found in directory D:/pyVideoTrans/models

185.252**4 Posted at: 2 hours ago

Subprocess Error: Error no file named model.safetensors, or pytorch_model.bin, found in directory D:/pyVideoTrans/models/models--k2-fsa--OmniVoice.
Traceback (most recent call last):
File "videotrans\task\only_one.py", line 108, in run
File "videotrans\task\_stage_dubbing.py", line 24, in dubbing
File "videotrans\task\_stage_dubbing.py", line 101, in _tts
File "videotrans\tts\__init__.py", line 132, 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 D:/pyVideoTrans/models/models--k2-fsa--OmniVoice.

trk=[TransCreate]: uuid='8b61a6cfbc', proxy_str='http://127.0.0.1:10809', cfg=[TaskCfgVTT]当前工作模式: 翻译视频单视频模式
原始输入文件名: D:/videos/Практика редактирования изображений 2 Диапазон яркости.mp4,
输出结果保存到文件夹: D:/videos/RU/Практика редактирования изображений 2 Диапазон яркости-mp4,
临时文件夹: D:/pyVideoTrans/tmp/19276/8b61a6cfbc
已选清理已存在
已启用CUDA加速
未选降噪
已选识别说话人，最大说话人数量不限制
Сервис STT (распознавание):faster-whisper(Built-in), large-v3-turbo, 发音语言: en, LLM纠错
Канал перевода:DeepSeek,原始语言:en,目标语言:ru, 已选 Отправить полный SRT
Канал озвучки (TTS):OmniVoice(Built-in), 角色:clone, 配音语言:ru, 未选二次语音识别
音量:+100%, 语速:+0%, 未选音频加速, 已选视频慢速
已选移除每条字幕配音开头和结尾静音缓冲
静音移除力度: default
字幕: nosubtitle
代理地址: http://127.0.0.1:10809, precent=18, hasend=False, should_recogn=True, should_trans=True, should_dubbing=True, should_hebing=True, is_copy_video=True, video_codec_num=264, ignore_align=False, is_audio_trans=False, clone_ref='', should_recogn2=False, do_diarize=True
video_duration_ms=18900

=
system:Windows-10-10.0.19045-SP0
version:v4.16
frozen:True
language:ru
root_dir:D:/pyVideoTrans

#1 DeepSeek reply at 2 hours ago

This is a model download failure, not a software bug. The OmniVoice model folder models/models--k2-fsa--OmniVoice exists but is missing the core weight files (model.safetensors / pytorch_model.bin) — i.e. the automatic download from huggingface.co was interrupted/incomplete.

Solution

1. Delete the broken folder
Fully delete D:/pyVideoTrans/models/models--k2-fsa--OmniVoice.

2. Re-download automatically
Re-run the task with a stable proxy enabled (your log shows http://127.0.0.1:10809; verify the proxy service is actually running and can reach huggingface.co). The software will re-download on first use.

3. If auto-download keeps failing, download manually

Open: https://huggingface.co/k2-fsa/OmniVoice/tree/main
Download all files in that repo.
Place them into: D:/pyVideoTrans/models/models--k2-fsa--OmniVoice

Important notes

Browser may auto-rename duplicate files (e.g. model(2).safetensors) — you must rename them back to their original names.
Verify model.safetensors exists directly inside D:/pyVideoTrans/models/models--k2-fsa--OmniVoice (not nested in an extra subfolder).
If you don't need voice cloning with OmniVoice, you can simply switch the TTS channel to Edge-TTS(免费) to proceed immediately.

#8322 Subprocess Error: Error no file named model.safetensors, or pytorch_model.bin, found in directory D:/pyVideoTrans/models

1 Replies

Solution

请查阅相关文档：

Post Your Reply

Related resource