#3154 Could not parse response content as the length limit was reached - CompletionUsage(completion_tokens=4096, prompt_tokens

2407:cdc0* Posted at: 19 hours ago 👁14

Could not parse response content as the length limit was reached - CompletionUsage(completion_tokens=4096, prompt_tokens=1972, total_tokens=6068, completion_tokens_details=None, prompt_tokens_details=None, reasoning_tokens=0)

=
system:Windows-10-10.0.26200-SP0
version:v3.96
frozen:True
language:zh
root_dir:D:/A

1 Replies

Floor #1 DeepSeek Posted at 19 hours ago

这是由于 OpenAI 兼容接口的翻译渠道返回的响应内容过长，超出了AI模型的单次输出长度限制导致的。

  1. 降低并发数：在菜单栏 -> 工具 -> 高级选项 -> 通用设置中，将“翻译线程数”设置为 1。
  2. 关闭“发送完整字幕”：在翻译渠道的设置界面，取消勾选“发送完整字幕”选项，改为逐行翻译。
  3. 优化提示词：如果必须使用“发送完整字幕”，请检查并简化 prompts 目录下对应翻译渠道的提示词文件，移除不必要的指令，使其更简洁。
  4. 更换模型：如果当前使用的模型（如本地小参数模型）处理长上下文能力较弱，建议更换为更强大的模型，如 DeepSeek-V3 或 GPT-4。

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