#4519 Could not parse response content as the length limit was reached - CompletionUsage(completion_tokens=8206, prompt_tokens

111.53* Posted at: 2 hours ago 👁10

Could not parse response content as the length limit was reached - CompletionUsage(completion_tokens=8206, prompt_tokens=3817, total_tokens=12023, completion_tokens_details=CompletionTokensDetails(accepted_prediction_tokens=None, audio_tokens=None, reasoning_tokens=5960, rejected_prediction_tokens=None), prompt_tokens_details=PromptTokensDetails(audio_tokens=None, cached_tokens=896), prompt_cache_hit_tokens=896, prompt_cache_miss_tokens=2921)


=
system:Windows-10-10.0.22621-SP0
version:v3.90
frozen:True
language:zh
root_dir:I:/fanyi/win-pyvideotrans-v3.87

1 Replies

这是由于 AI 翻译返回的内容超出长度限制导致的,常见于选中了“发送完整字幕”而字幕内容过多,或模型本身上下文限制较小。

解决方案:

  1. 取消“发送完整字幕”选项:在主界面的翻译设置中,取消勾选“发送完整字幕”,将字幕按行分批发给 AI。
  2. 减少每批字幕行数:在“高级选项” → “字幕翻译调整” → “AI翻译渠道每批字幕行数”中,调低数值(如从 20 改为 10 或 5)。
  3. 升级软件版本:强烈建议升级到最新 v3.99,因为许多类似 bug 已在后续版本修复。下载地址:https://pyvideotrans.com/downpackage
  4. 更换更强的模型:如果使用本地小模型(如 7B),请改为在线模型(如 DeepSeek-V3、GPT-4o),它们上下文更大且更稳定。

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