VideoLingo icon indicating copy to clipboard operation
VideoLingo copied to clipboard

[red]❌ Expressiveness translation of block 13 failed after 3 retries. 报错如何处理啊?

Open yyyyxxxx520 opened this issue 9 months ago • 2 comments

File "C:\Users\yx\Desktop\VideoLingobylicor250220全量包含中英日韩模型\VideoLingobylicor250220\miniconda\envs\videolingo\lib\site-packages\streamlit\runtime\scriptrunner\exec_code.py", line 88, in exec_func_with_error_handling result = func() File "C:\Users\yx\Desktop\VideoLingobylicor250220全量包含中英日韩模型\VideoLingobylicor250220\miniconda\envs\videolingo\lib\site-packages\streamlit\runtime\scriptrunner\script_runner.py", line 590, in code_to_exec exec(code, module.dict) File "C:\Users\yx\Desktop\VideoLingobylicor250220全量包含中英日韩模型\VideoLingobylicor250220\st.py", line 241, in main() File "C:\Users\yx\Desktop\VideoLingobylicor250220全量包含中英日韩模型\VideoLingobylicor250220\st.py", line 235, in main text_processing_section() File "C:\Users\yx\Desktop\VideoLingobylicor250220全量包含中英日韩模型\VideoLingobylicor250220\st.py", line 65, in text_processing_section process_text() File "C:\Users\yx\Desktop\VideoLingobylicor250220全量包含中英日韩模型\VideoLingobylicor250220\st.py", line 87, in process_text step4_2_translate_all.translate_all() File "C:\Users\yx\Desktop\VideoLingobylicor250220全量包含中英日韩模型\VideoLingobylicor250220\core\step4_2_translate_all.py", line 88, in translate_all results.append(future.result()) File "C:\Users\yx\Desktop\VideoLingobylicor250220全量包含中英日韩模型\VideoLingobylicor250220\miniconda\envs\videolingo\lib\concurrent\futures_base.py", line 451, in result return self.__get_result() File "C:\Users\yx\Desktop\VideoLingobylicor250220全量包含中英日韩模型\VideoLingobylicor250220\miniconda\envs\videolingo\lib\concurrent\futures_base.py", line 403, in __get_result raise self._exception File "C:\Users\yx\Desktop\VideoLingobylicor250220全量包含中英日韩模型\VideoLingobylicor250220\miniconda\envs\videolingo\lib\concurrent\futures\thread.py", line 58, in run result = self.fn(*self.args, **self.kwargs) File "C:\Users\yx\Desktop\VideoLingobylicor250220全量包含中英日韩模型\VideoLingobylicor250220\core\step4_2_translate_all.py", line 54, in translate_chunk translation, english_result = translate_lines(chunk, previous_content_prompt, after_content_prompt, things_to_note_prompt, theme_prompt, i) File "C:\Users\yx\Desktop\VideoLingobylicor250220全量包含中英日韩模型\VideoLingobylicor250220\core\translate_once.py", line 81, in translate_lines express_result = retry_translation(prompt2, 'expressiveness') File "C:\Users\yx\Desktop\VideoLingobylicor250220全量包含中英日韩模型\VideoLingobylicor250220\core\translate_once.py", line 46, in retry_translation raise ValueError(f'[red]❌ {step_name.capitalize()} translation of block {index} failed after 3 retries. Please check output/gpt_log/error.json for more details.[/red]')

yyyyxxxx520 avatar Mar 23 '25 06:03 yyyyxxxx520

error.json内容:

[ { "model": "deepseek-ai/DeepSeek-V2.5", "prompt": "### Role\nYou are a professional Netflix subtitle splitter in en.\n\n### Task\nSplit the given subtitle text into 2 parts, each less than 20 words.\n\n### Instructions\n1. Maintain sentence meaning coherence according to Netflix subtitle standards\n2. Keep parts roughly equal in length (minimum 3 words each)\n3. Split at natural points like punctuation marks or conjunctions\n4. If provided text is repeated words, simply split at the middle of the repeated words.\n\n### Output Format in JSON\n{\n "analysis": "Brief analysis of the text structure",\n "split": "Complete sentence with [br] tags at split positions"\n}\n\n### Your Answer, Provide ONLY a valid JSON object,Don't give any other redundant explanations.\n\n### Given Text\n<split_this_sentence>\nand I'll compile and save just before we start doing anything so the first thing we want to do is if you go to the rig hierarchy tab you can just select the top bone scroll to the bottom\n</split_this_sentence>", "response": { "analysis": "The text is a continuous instruction without clear natural breaks. Split at 'so' to maintain coherence.", "split": "and I'll compile and save just before we start doing anything so the first thing we want to do is if you go to the rig hierarchy tab you can just select the top bone scroll to the bottom" }, "message": "Split failed, no [br] found" }, { "model": "deepseek-ai/DeepSeek-V2.5", "prompt": "### Role\nYou are a professional Netflix subtitle splitter in en.\n\n### Task\nSplit the given subtitle text into 2 parts, each less than 20 words.\n\n### Instructions\n1. Maintain sentence meaning coherence according to Netflix subtitle standards\n2. Keep parts roughly equal in length (minimum 3 words each)\n3. Split at natural points like punctuation marks or conjunctions\n4. If provided text is repeated words, simply split at the middle of the repeated words.\n\n### Output Format in JSON\n{\n "analysis": "Brief analysis of the text structure",\n "split": "Complete sentence with [br] tags at split positions"\n}\n\n### Your Answer, Provide ONLY a valid JSON object,Don't give any other redundant explanations.\n\n### Given Text\n<split_this_sentence>\nand I'll compile and save just before we start doing anything so the first thing we want to do is if you go to the rig hierarchy tab you can just select the top bone scroll to the bottom\n</split_this_sentence>", "response": "{\n "analysis": "The text is a continuous instruction without clear natural breaks. Split at 'so' to maintain coherence.",\n "split": "and I'll compile and save just before we start doing anything so the first thing we want to do is if you go to the rig hierarchy tab you can just select the top bone scroll to the bottom"\n}", "message": "json_repair parsing failed." }, { "model": "deepseek-ai/DeepSeek-V2.5", "prompt": "### Role\nYou are a professional Netflix subtitle splitter in en.\n\n### Task\nSplit the given subtitle text into 3 parts, each less than 20 words.\n\n### Instructions\n1. Maintain sentence meaning coherence according to Netflix subtitle standards\n2. Keep parts roughly equal in length (minimum 3 words each)\n3. Split at natural points like punctuation marks or conjunctions\n4. If provided text is repeated words, simply split at the middle of the repeated words.\n\n### Output Format in JSON\n{\n "analysis": "Brief analysis of the text structure",\n "split": "Complete sentence with [br] tags at split positions"\n}\n\n### Your Answer, Provide ONLY a valid JSON object,Don't give any other redundant explanations.\n\n### Given Text\n<split_this_sentence>\nwhere you created the control rig that you've been working on what we can do so in my case it's totescoping control rig i'm going to copy that over to the alternate monster mesh folder so i'm going to click on that\n</split_this_sentence>", "response": { "analysis": "The text is a technical explanation about creating and copying a control rig. It naturally splits at conjunctions and punctuation marks.", "split": "where you created the control rig that you've been working on. what we can do so in my case, it's totescoping control rig. i'm going to copy that over to the alternate monster mesh folder, so i'm going to click on that." }, "message": "Split failed, no [br] found" }, { "model": "deepseek-ai/DeepSeek-V2.5", "prompt": "### Role\nYou are a professional Netflix subtitle splitter in en.\n\n### Task\nSplit the given subtitle text into 3 parts, each less than 20 words.\n\n### Instructions\n1. Maintain sentence meaning coherence according to Netflix subtitle standards\n2. Keep parts roughly equal in length (minimum 3 words each)\n3. Split at natural points like punctuation marks or conjunctions\n4. If provided text is repeated words, simply split at the middle of the repeated words.\n\n### Output Format in JSON\n{\n "analysis": "Brief analysis of the text structure",\n "split": "Complete sentence with [br] tags at split positions"\n}\n\n### Your Answer, Provide ONLY a valid JSON object,Don't give any other redundant explanations.\n\n### Given Text\n<split_this_sentence>\nwhere you created the control rig that you've been working on what we can do so in my case it's totescoping control rig i'm going to copy that over to the alternate monster mesh folder so i'm going to click on that\n</split_this_sentence>", "response": "{\n "analysis": "The text is a technical explanation about creating and copying a control rig. It naturally splits at conjunctions and punctuation marks.",\n "split": "where you created the control rig that you've been working on. what we can do so in my case, it's totescoping control rig. i'm going to copy that over to the alternate monster mesh folder, so i'm going to click on that."\n}", "message": "json_repair parsing failed." } ]

yyyyxxxx520 avatar Mar 23 '25 06:03 yyyyxxxx520

感觉是模型或者网络的问题,可以换个别的模型试试,o4-mini 或者 claude3.5

linkwoodworking avatar Mar 25 '25 13:03 linkwoodworking