#7928 'str' object has no attribute 'get'Traceback (most recent call last):

188.192**8 Posted at: 1 hour ago

'str' object has no attribute 'get'
Traceback (most recent call last):
File "videotrans\translator\_base.py", line 79, in run
File "videotrans\translator\_base.py", line 117, in _run_text
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 90, in run
File "videotrans\task\_stage_translate.py", line 31, in trans
File "videotrans\translator\_runner.py", line 71, in run
File "videotrans\translator\_base.py", line 85, in run
File "tenacity\__init__.py", line 480, in call
File "videotrans\translator\_openaicompat.py", line 100, in _item_task
AttributeError: 'str' object has no attribute 'get'

trk=[TransCreate]: uuid='
......
p4,
输出结果保存到文件夹: C:/Private Filez/Videoz/Zum Übertragen/Dubbing/Dubprogress/Mindbrowse com Interview Broadcast “Women In Porn A Discriminating Audience” HD (720p_30fps_H264-128kbit_AAC)-mp4,
临时文件夹: C:/vTrans/tmp/92288/7e32e5e8a6
未选 清理已存在
已启用CUDA加速
已选 降噪
已选 识别说话人，最大说话人数量不限制
STT Service:openai-whisper(Built-in), large-v3-turbo, 发音语言: English,
TranslateSrt:Local LLM (OpenAI-compatible),原始语言:English,目标语言:German, 未选 SendSRT
TTS Service:Confucius4(Built-in), 角色:clone, 配音语言:German, 未选 二次语音识别
音量:-1%, 语速:+0%, 已选 音频加速, 未选 视频慢速
已选 移除每条字幕配音开头和结尾静音缓冲
静音移除力度: default
字幕: No Subtitles
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, precent=12, hasend=False, should_recogn=True, should_trans=True, should_dubbing=True, should_hebing=True, is_copy_video=True, video_codec_num=264, ignore_align=False, is_audio_trans=False, clone_ref='C:/vTrans/tmp/92288/7e32e5e8a6/vocal.wav', should_recogn2=False, do_diarize=True
trk.cfg=[TaskCfgVTT]当前工作模式: 翻译视频 单视频模式
原始输入文件名: C:/Private Filez/Videoz/Zum Übertragen/Dubbing/Dubprogress/Mindbrowse com Interview Broadcast “Women In Porn A Discriminating Audience” HD (720p_30fps_H264-128kbit_AAC).mp4,
输出结果保存到文件夹: C:/Private Filez/Videoz/Zum Übertragen/Dubbing/Dubprogress/Mindbrowse com Interview Broadcast “Women In Porn A Discriminating Audience” HD (720p_30fps_H264-128kbit_AAC)-mp4,
临时文件夹: C:/vTrans/tmp/92288/7e32e5e8a6
未选 清理已存在
已启用CUDA加速
已选 降噪
已选 识别说话人，最大说话人数量不限制
STT Service:openai-whisper(Built-in), large-v3-turbo, 发音语言: English,
TranslateSrt:Local LLM (OpenAI-compatible),原始语言:English,目标语言:German, 未选 SendSRT
TTS Service:Confucius4(Built-in), 角色:clone, 配音语言:German, 未选 二次语音识别
音量:-1%, 语速:+0%, 已选 音频加速, 未选 视频慢速
已选 移除每条字幕配音开头和结尾静音缓冲
静音移除力度: default
字幕: No Subtitles
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
video_duration_ms=3866933

=
system:Windows-10-10.0.26300-SP0
version:v4.15
frozen:True
language:en_US
root_dir:C:/vTrans

1 Replies

#1 DeepSeek reply at 1 hour ago

This error is triggered by the Local LLM (OpenAI-compatible) translation channel: the software expects a standard OpenAI‑format JSON response (an object containing choices[0].message.content), but your local LLM service returned a plain string, so calling .get() on it failed → 'str' object has no attribute 'get' (see videotrans/translator/_openaicompat.py line 100). The problem is with the API/endpoint you filled in, not with the video itself.

Fix steps

  1. Verify the API URL is a true OpenAI‑compatible endpoint

    • It must be the Chat Completions API, usually ending with /v1/chat/completions (or /v1).
    • Do NOT fill in a WebUI address (e.g. 7860 / chat page / /chat HTML page). If you filled a WebUI or a proxy page, the software receives HTML/plain text instead of JSON, which produces exactly this error.

  2. Do not use 0.0.0.0

    • Replace any 0.0.0.0 with 127.0.0.1.

  3. Test the endpoint with curl before using it in the software

    curl http://127.0.0.1:端口/v1/chat/completions -H "Content-Type: application/json" -H "Authorization: Bearer 你的KEY" -d "{\"model\":\"你的模型名\",\"messages\":[{\"role\":\"user\",\"content\":\"hi\"}]}"
    • Must return JSON containing "choices":[{"message":{"content":"..."}}].
    • If it returns plain text / HTML / a JSON string, this channel cannot be used — switch the service or fix the endpoint.

  4. Confirm the loaded model

    • Must be a pure text chat model. Multimodal / ASR / embedding models, or ASR‑type model names, will not return chat completions and will break the pipeline.

  5. Small local models (≈7B) have weak instruction-following ability

    • They often return non-compliant output. Prefer larger/full models, or use DeepSeek / OpenAI / Gemini for translation.

  6. If the API is OpenAI-compatible, alternatively fill it into the OpenAI / OpenAI Compatible channel

    • The knowledge base explicitly notes: if a third party is OpenAI-compatible, use ChatGPT / OpenAI channel instead of the custom Local LLM entry.
  7. Also, since translation happened before dubbing and the process failed at the translate stage, re-run with 清理已生成 (Clear Output) unchecked only after fixing the API — otherwise it will reuse the cached faulty result. Delete tmp/translate_cache/ if needed.

If the endpoint already returns proper OpenAI JSON via curl but the software still errors, please provide the log bottom ~30 lines from logs/ (latest .log) — include the actual API URL used (mask the key).

请查阅相关文档：

Thinking...
Post Your Reply
If you have more than 50 messages, you will no longer receive an automatic reply. Please ask a new question!
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.

Dondate via ko-fi.com

Related resource