#5799 [F5-TTS] may not support VietnameseTraceback (most recent call last):

2405:4802* Posted at: 1 day ago

[F5-TTS] may not support Vietnamese
Traceback (most recent call last):
File "videotrans\task\only_one.py", line 86, in run
File "videotrans\task\_stage_dubbing.py", line 23, in dubbing
File "videotrans\task\_stage_dubbing.py", line 102, in _tts
File "videotrans\tts\__init__.py", line 207, in run
File "", line 18, in init
File "videotrans\tts\_f5tts.py", line 89, in post_init
videotrans.configure.excepts.DubbingSrtError: [F5-TTS] may not support Vietnamese

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/Admin/Downloads/video tai xuong/无球也能做上斯诺克楚霸王无语透了强哥坐收渔翁之利 #台球 #楚秉杰 #秦利文 #台球精彩时刻.mp4,
输出结果保存到文件夹: C:/Users/Admin/Downloads/âm thanh/无球也能做上斯诺克楚霸王无语透了强哥坐收渔翁之利 #台球 #楚秉杰 #秦利文 #台球精彩时刻-mp4,
临时文件夹: C:/Users/Admin/Downloads/taigame/win-pyvideotrans-v4.05-0711/tmp/13324/2df170eb97
已选 清理已存在
已选 启用CUDA加速
未选 降噪
ASR Channel:faster-whisper(LocalBuilt-in), model_name: large-v3, 发音语言: Traditional Chinese, 断句方式:默认断句
Trans Channel:Gemini AI,原始语言:Traditional Chinese,目标语言:Vietnamese, 已选 Send SRT
Dubb Channel:F5-TTS(LocalBuilt-in), 角色:clone, 配音语言:Vietnamese, 未选 二次语音识别
音量:+0%, 语速:+0%, 已选 音频加速, 未选 视频慢速
字幕: Embed Hard Subs
代理地址:


=
system:Windows-10-10.0.26200-SP0
version:v4.05
frozen:True
language:en
root_dir:C:/Users/Admin/Downloads/taigame/win-pyvideotrans-v4.05-0711

1 Replies

F5-TTS (Local Built-in) does not support Vietnamese. According to the official documentation, only the following languages are supported: Chinese, English, Japanese, French, German, Russian, Italian, Spanish, Hindi, and Arabic.

Solutions:

  1. Change dubbing channel to a one that supports Vietnamese and voice cloning:

    • OmniVoice (local built‑in, recommended)
    • Chatterbox (local built‑in, supports Vietnamese)
    • VoxCPM‑TTS (self‑deployed API, supports Vietnamese)
    • Confucius4‑TTS (self‑deployed API, supports Vietnamese)
  2. If you still want to use the clone voice role, ensure you also configure these advanced options (Menu → Tools → Advanced Options → Speech Recognition):

    • Set Minimum voice duration (ms) to 3000 or higher.
    • Set Maximum voice duration (s) to 6 ~ 10.
    • Enable Whisper pre‑segment audio and Merge short subtitle into adjacent.
  3. After switching, restart the task.

Please check the relevant 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 via ko-fi.com

Dondate via PayPal

Related resource