#5601 NoneTraceback (most recent call last): File "videotrans\task\only_one.py", line 46, in run File "videotrans\task\trans

193.176* Posted at: 1 hour ago

None
Traceback (most recent call last):
File "videotrans\task\only_one.py", line 46, in run
File "videotrans\task\trans_create.py", line 319, in recogn
File "videotrans\recognition\__init__.py", line 191, in run
File "videotrans\recognition\_base.py", line 90, in run
File "videotrans\recognition\_qwenasrlocal.py", line 36, in _exec
File "videotrans\recognition\_base.py", line 194, in cut_audio
File "videotrans\recognition\_base.py", line 179, in _vad_split
File "videotrans\configure\base.py", line 272, in _new_process
videotrans.configure.excepts.VideoTransError: None

cfg=[TaskCfgVTT]当前工作模式: 翻译视频或音频 单视频模式
原始输入文件名: C:/Users/Son/Downloads/X2Twitter.com_ymJcTxhKP1PM-JVb_1920p.mp4,
输出结果保存到文件夹: C:/Users/Son/Downloads/_video_out/X2Twitter.com_ymJcTxhKP1PM-JVb_1920p-mp4,
临时文件夹: D:/win-pyvideotrans-v4.03-0619/tmp/13144/5877e34f13
已选 清理已存在
未选 启用CUDA加速
未选 降噪
ASR Channel:Qwen-ASR(LocalBuilt-in), model_name: 1.7B, 发音语言: English, 断句方式:默认断句
Trans Channel:Microsoft (Free),原始语言:English,目标语言:Russian, 已选 Send SRT
Dubb Channel:Edge-TTS(Free), 角色:Dmitry(Male/RU), 配音语言:Russian, 未选 二次语音识别
音量:+0%, 语速:+0%, 已选 音频加速, 已选 视频慢速
字幕: No Subs
代理地址:

=
system:Windows-10-10.0.19045-SP0
version:v4.03
frozen:True
language:en
root_dir:D:/win-pyvideotrans-v4.03-0619

1 Replies

Floor #1 DeepSeek reply at 1 hour ago

The error VideoTransError: None from Qwen-ASR (Local Built-in) usually indicates one of these underlying issues:

  1. The Qwen-ASR model (1.7B) failed to load or is incomplete.

    • On CPU (no CUDA), the 1.7B model requires >8GB RAM and may take a very long time to load.
    • The model may have been corrupted or only partially downloaded.
  2. VAD split or FFmpeg failed silently (likely due to insufficient memory or a hidden FFmpeg error).

Recommended fix steps:

  1. Switch to a reliable CPU‑friendly ASR channel – For English, faster-whisper(本地内置) with model base or small works well without GPU and is far more stable on CPU:

    • In the GUI, change ASR Channel to faster-whisper(本地内置) and set model to base or small (not large-v3 to avoid memory issues).
    • Ensure CUDA acceleration is unchecked (since you have no GPU).

  2. If you prefer to keep Qwen-ASR, try these checks:

    • Navigate to D:/win-pyvideotrans-v4.03-0619/models/ and verify a folder named something like models--Qwen--Qwen2-Audio-7B exists and is not empty. If it’s missing or only partially downloaded, delete it and re‑run the software – the model will be downloaded again.
    • Restart the software (kill any lingering sp.exe processes in Task Manager first) and try again without any other tasks running.

  3. Temporary workaround for this specific video:

    • Rename the video to a simple name like video.mp4 and place it in a shallow path (e.g., D:/video.mp4). Some path length issues can cause silent failures.

  4. Enable verbose logs for more details:

    • Add a file named debug.txt (empty) in the software root directory, then re-run the task. The logs/ folder will contain more detailed error messages. Share the relevant portion if the above steps don't resolve it.

If the problem persists, please attach the content of the latest log file from logs/ folder (the last 30 lines) and the software version number (visible in the top‑left corner of the window).

Related documentation:

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. Dondate: ko-fi.com/jianchang512

Related resource