#8326 This model is currently experiencing high demand. Spikes in demand are usually temporary. Please try again later.Traceba

2a01**9d3 Posted at: 2 hours ago

This model is currently experiencing high demand. Spikes in demand are usually temporary. Please try again later.
Traceback (most recent call last):
File "videotrans\translator\_base.py", line 71, in run
File "videotrans\translator\_base.py", line 206, in _run_srt
File "tenacity\__init__.py", line 338, in wrapped_f
File "tenacity\__init__.py", line 477, in call
File "tenacity\__init__.py", line 378, in iter
File "tenacity\__init__.py", line 421, in exc_check
tenacity.RetryError: RetryError[]

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "videotrans\task\only_one.py", line 73, in run
File "videotrans\task\_stage_translate.py", line 31, in trans
File "videotrans\translator\_runner.py", line 63, in run
File "videotrans\translator\_base.py", line 74, in run
File "tenacity\__init__.py", line 480, in call
File "videotrans\translator\_gemini.py", line 112, in _item_task
videotrans.configure.excepts.TranslateSrtError: This model is currently experiencing high demand. Spikes in demand are usually temporary. Please try again later.

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/Super/Downloads/ssstik.io_1792514567841.mp4,
输出结果保存到文件夹: C:/Users/Super/Downloads/_video_out/ssstik.io_1792514567841-mp4,
临时文件夹: C:/pyVideoTrans/tmp/17564/c642c4d09a
已选清理已存在
已选启用CUDA加速
未选降噪
ASR Channel:WhisperX(LocalAPI), model_name: large-v3-turbo, 发音语言: English, 断句方式:默认断句
Trans Channel:Gemini AI,原始语言:English,目标语言:French, 已选 SendSrt
Dubb Channel:Elevenlabs.io, 角色:Abdel - Warm and Steady, 配音语言:French, 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: No Subs
已选分离人声与背景声, 已选重新嵌入背景声, 背景音量0.8, 背景声音时长短于视频时长时: 拉长(降速播放),存在分离后的纯净人声文件,存在分离后的背景声音文件
代理地址:

=
system:Windows-10-10.0.26200-SP0
version:v4.07
frozen:True
language:en
root_dir:C:/pyVideoTrans

#1 DeepSeek reply at 2 hours ago

This is not a software bug — the error text This model is currently experiencing high demand. Spikes in demand are usually temporary. Please try again later. is a 503-level server response returned by Google's Gemini API (the model endpoint is overloaded). The task failed at the subtitle translation stage (_stage_translate.py → translator/_gemini.py), so your ASR, dubbing and alignment steps were never reached.

Solutions (in order of effectiveness)

Retry later with a lighter Gemini model
- Open Menu → Translation Settings → Gemini AI and switch the model from a gemini-...-pro variant to a flash/lite variant (e.g. gemini-flash-latest / gemini-2.5-flash). Pro-class models are hit hardest by 503 spikes.
- Then retry the task.
Switch the translation channel temporarily (fastest workaround)
- Use Google(free), Microsoft(free), DeepSeek, OpenRouter or SiliconFlow for the subtitle translation instead of Gemini. For English→French, any of these are perfectly adequate.
- If you keep Gemini, raise robustness: Menu → Tools/Options → Advanced Options → Translation → increase Pause (s) after each translation request, and lower Batch size (lines) for AI translation (e.g. 10), to reduce the chance of hitting the overload window.
Skip the expensive re-transcription when retrying
- Because ASR (WhisperX large-v3-turbo) already finished and Clear Output was checked in your run, retrying will redo the whole transcription.
- On retry, uncheck Clear Output so the existing _video_out/ssstik.io_1792514567841-mp4/en.srt (and separated vocal/BGM files) are reused, and processing jumps straight to translation.
Upgrade
- You are on v4.07; the current version is v4.16. Newer versions include improved retry/fallback logic for translation channels (e.g. automatic fallback when Google fails) — download the full package or the patch from the link below and overwrite.

Note: repeated automatic retries (via tenacity) will not fix a 503 — the upstream service must recover, or you must change channel/model.

#8326 This model is currently experiencing high demand. Spikes in demand are usually temporary. Please try again later.Traceba

1 Replies

Solutions (in order of effectiveness)

请查阅相关文档：

Post Your Reply

Related resource