#2057 TaskCfg(cache_folder=None, target_dir='E:/观察', remove_noise=False, is_separate=False, detect_language=None, subtitle_lan

219.134* Posted at: 10 hours ago 👁11

翻译字幕阶段出错:[DeepSeek] 运行时错误:[DeepSeek] content_filter:ChatCompletion(id='becd8dfc-7b37-4d27-b71e-914ecf284a11', choices=[Choice(finish_reason='content_filter', index=0, logprobs=None, message=ChatCompletionMessage(content='', refusal=None, role='assistant', annotations=None, audio=None, function_call=None, tool_calls=None))], created=1765823986, model='deepseek-chat', object='chat.completion', service_tier=None, system_fingerprint='fp_eaab8d114b_prod0820_fp8_kvcache', usage=CompletionUsage(completion_tokens=0, prompt_tokens=2595, total_tokens=2595, completion_tokens_details=None, prompt_tokens_details=PromptTokensDetails(audio_tokens=None, cached_tokens=2560), prompt_cache_hit_tokens=2560, prompt_cache_miss_tokens=35)):
Traceback (most recent call last):
File "videotrans\translator\_base.py", line 78, in run
File "videotrans\translator\_base.py", line 137, 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\job.py", line 184, in run
File "videotrans\task\_translate_srt.py", line 45, in trans
File "videotrans\translator\__init__.py", line 923, in run
File "videotrans\translator\_base.py", line 81, in run
File "tenacity\__init__.py", line 480, in call
File "videotrans\translator\_deepseek.py", line 72, in _item_task
RuntimeError: [DeepSeek] content_filter:ChatCompletion(id='becd8dfc-7b37-4d27-b71e-914ecf284a11', choices=[Choice(finish_reason='content_filter', index=0, logprobs=None, message=ChatCompletionMessage(content='', refusal=None, role='assistant', annotations=None, audio=None, function_call=None, tool_calls=None))], created=1765823986, model='deepseek-chat', object='chat.completion', service_tier=None, system_fingerprint='fp_eaab8d114b_prod0820_fp8_kvcache', usage=CompletionUsage(completion_tokens=0, prompt_tokens=2595, total_tokens=2595, completion_tokens_details=None, prompt_tokens_details=PromptTokensDetails(audio_tokens=None, cached_tokens=2560), prompt_cache_hit_tokens=2560, prompt_cache_miss_tokens=35))

TaskCfg(cache_folder=None, target_dir='E:/观察', remove_noise=False, is_separate=False, detect_language=None, subtitle_language=None, source_language=None, target_language=None, source_language_code='English', target_language_code='Simplified Chinese', source_sub='E:/观察/Bloomberg Surveillance 12_15_2025 EN.srt', target_sub='E:/观察/Bloomberg Surveillance 12_15_2025 EN.Simplified Chinese.srt', source_wav=None, source_wav_output=None, target_wav=None, target_wav_output=None, subtitles=None, novoice_mp4=None, noextname='Bloomberg Surveillance 12_15_2025 EN', shibie_audio=None, targetdir_mp4=None, instrument=None, vocal=None, back_audio=None, background_music=None, app_mode='biaozhun', subtitle_type=0, volume='+0%', pitch='+0Hz', voice_rate='+0%', voice_role=None, copysrt_rawvideo=False, clear_cache=False, translate_type=4, tts_type=None, recogn_type=None, model_name=None, split_type=0, voice_autorate=False, video_autorate=False, cuda=False, name='E:/观察/Bloomberg Surveillance 12_15_2025 EN.srt', basename='Bloomberg Surveillance 12_15_2025 EN.srt', ext='srt', dirname='E:/观察', shound_del_name=None, uuid='224571037a', remove_silent_mid=False, align_sub_audio=True, enable_diariz=False, nums_diariz=0, rephrase=2, only_out_mp4=False)


=
system:Windows-10-10.0.26200-SP0
version:v3.90
frozen:True
language:zh
root_dir:B:/win-videotrans

1 Replies

DeepSeek 翻译失败,原因是触发了其内容安全过滤器 (content_filter)。这通常是因为翻译的文本内容(可能是字幕内容本身,或者是系统提示词)被模型判定为包含敏感或不适宜内容。

请按以下步骤尝试解决:

  1. 检查字幕内容:打开你的字幕文件 E:/观察/Bloomberg Surveillance 12_15_2025 EN.srt,检查其中是否包含可能被误判为敏感的词句(如政治、暴力、金融欺诈等话题)。如果可能,尝试手动修改或删除这些片段后重新翻译。
  2. 调整翻译参数

    • 在 pyVideoTrans 主界面,点击 翻译设置 按钮。
    • 尝试 更换翻译渠道,例如切换到 Google、微软或 OpenAI 等其他模型。
    • 如果必须使用 DeepSeek,可以尝试在高级选项中减少 同时翻译字幕数(例如改为 1),以发送更小的文本块,降低触发过滤的概率。
  3. 使用其他翻译渠道:这是最直接的解决方案。DeepSeek 的内容过滤策略可能较为严格,对于新闻、财经类内容容易误判。建议更换为 Google翻译(需配置代理)或 微软翻译 等传统渠道,或者使用 OpenAI GPTGemini 等其他 AI 模型。

如果以上方法均无效,且你确认字幕内容无问题,可能需要联系 DeepSeek 官方咨询其内容过滤策略。

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.

Donate: https://ko-fi.com/jianchang512

Similar issues already exist

Trending Questions