#3741 Could not parse response content as the length limit was reached - CompletionUsage(completion_tokens=4096, prompt_tokens

2408:844d* Posted at: 2 hours ago 👁8

Could not parse response content as the length limit was reached - CompletionUsage(completion_tokens=4096, prompt_tokens=2676, total_tokens=6772, completion_tokens_details=CompletionTokensDetails(accepted_prediction_tokens=None, audio_tokens=None, reasoning_tokens=0, rejected_prediction_tokens=None), prompt_tokens_details=None)


=
system:Windows-10-10.0.26200-SP0
version:v3.92
frozen:True
language:zh
root_dir:D:/win-pyvideotrans-v3.92

1 Replies

这是由于AI翻译渠道的响应内容过长,超出了模型的最大输出限制(4096个tokens)导致的。

解决方案:

  1. 在软件主界面,点击“菜单”->“工具”->“高级选项”。
  2. 找到【字幕翻译调整】区域。
  3. 将“AI翻译渠道每批字幕行数”的值减小,例如从默认的20改为10或5。
  4. 同时,取消勾选“发送完整字幕”和“AI翻译附带完整原字幕”这两个选项,以减少每次发送给AI的文本量。
  5. 保存设置后,重新尝试翻译任务。

如果问题仍然存在,请考虑更换为支持更长上下文的AI模型(如GPT-4o、DeepSeek-V3等),或者使用传统的翻译渠道(如Google翻译、DeepL)。

请查阅相关文档:

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.

Related resource

Similar issues already exist