Netflix-level subtitle cutting, translation, alignment, and even dubbing - one-click fully automated AI video subtitle team | Netflix级字幕切割、翻译、对齐、甚至加上配音,一键全自动视频搬运AI字幕组
This report presents the forensic synthetic code analysis of Huanshere/VideoLingo, a Python project with 18,287 GitHub stars. SynthScan v2.0 examined 17,153 lines of code across 122 source files, recording 258 pattern matches distributed across 14 syntactic categories. The overall adjusted score of 22.6 places this repository in the Moderate AI signal band.
The scanner applied 160+ deterministic lexical heuristics, multi-line block detectors, abstract syntax tree depth profilers, and a cross-file Jaccard similarity matrix to construct a statistically normalised synthetic code estimate. All matches are individually weighted by severity coefficient and contextual multiplier before summation, and the resulting headline score is temporally discounted to account for the repository's development history relative to the commercial emergence of large language model coding tooling (November 2022 onward).
Longitudinal tracking requires multiple scan runs. Once this repository is re-scanned after new commits land, this chart will visualise how the synthetic code signal evolves over time — enabling you to detect whether AI authorship is growing, stabilising, or being actively corrected by human engineers.
Classifies detected patterns by their diagnostic confidence and structural impact. CRITICAL patterns (coefficient 10) represent definitive synthetic signatures — hallucinated imports, explicit LLM attribution metadata — virtually never produced by human authors. HIGH (5) indicates strong structural tells such as cross-file repetition or cross-linguistic idioms. MEDIUM (2) covers recognisable conversational padding and AI-specific vocabulary. LOW (1) captures subtle indicators like tautological comments and generic boilerplate that require density to carry independent signal.
This horizontal bar chart decomposes the repository's raw synthetic code score by top-level directory, allowing you to pinpoint precisely which modules or components carry the highest AI authorship density. Directories with disproportionately high scores relative to their size warrant targeted manual review: concentrated AI signatures often trace back to mass-generated configuration layers, auto-ported test suites, LLM-scaffolded boilerplate classes, or entire subsystems authored under heavy copilot assistance. Use this view to prioritise your human code-review effort.
The scanner identified 258 distinct pattern matches across 14 syntactic categories. Each entry below represents a discrete location in the source code where the engine recorded a statistically significant AI authorship indicator. Expand any category row to inspect the individual file paths, line numbers, code snippets, and the lexical context (CODE, COMMENT, or STRING) in which each match was detected.
Reading the findings table: The Severity column indicates the diagnostic confidence level (CRITICAL / HIGH / MEDIUM / LOW). The Context column identifies whether the match occurred inside executable code, an inline comment, or a string literal — comment-context matches receive a ×1.5 weight because LLMs systematically over-annotate. The ⚡ bolt icon marks clustered matches: three or more patterns within a 10-line window, each receiving an additional ×1.5 density multiplier as dense clusters constitute far stronger evidence of synthetic authorship than isolated hits.
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| MEDIUM⚡ | config.yaml | 3 | # ------------------- | COMMENT |
| MEDIUM⚡ | config.yaml | 6 | # ------------------- | COMMENT |
| MEDIUM | core/prompts.py | 4 | ## ================================================================ | COMMENT |
| MEDIUM | core/prompts.py | 51 | ## ================================================================ | COMMENT |
| MEDIUM | core/prompts.py | 126 | ## ================================================================ | STRING |
| MEDIUM | core/prompts.py | 250 | ## ================================================================ | STRING |
| MEDIUM | core/prompts.py | 300 | ## ================================================================ | STRING |
| MEDIUM | core/prompts.py | 341 | ## ================================================================ | STRING |
| MEDIUM | core/spacy_utils/load_nlp_model.py | 28 | # -------------------- | COMMENT |
| MEDIUM | core/spacy_utils/load_nlp_model.py | 30 | # -------------------- | COMMENT |
| MEDIUM | core/utils/models.py | 1 | # ------------------------------------------ | COMMENT |
| MEDIUM | core/utils/models.py | 3 | # ------------------------------------------ | COMMENT |
| MEDIUM⚡ | core/utils/models.py | 16 | # ------------------------------------------ | COMMENT |
| MEDIUM⚡ | core/utils/models.py | 18 | # ------------------------------------------ | COMMENT |
| MEDIUM⚡ | core/utils/models.py | 28 | # ------------------------------------------ | COMMENT |
| MEDIUM⚡ | core/utils/models.py | 31 | # ------------------------------------------ | COMMENT |
| MEDIUM⚡ | core/utils/models.py | 35 | # ------------------------------------------ | COMMENT |
| MEDIUM⚡ | core/utils/models.py | 37 | # ------------------------------------------ | COMMENT |
| MEDIUM⚡ | core/utils/decorator.py | 6 | # ------------------------------ | COMMENT |
| MEDIUM⚡ | core/utils/decorator.py | 8 | # ------------------------------ | COMMENT |
| MEDIUM | core/utils/decorator.py | 30 | # ------------------------------ | COMMENT |
| MEDIUM | core/utils/decorator.py | 32 | # ------------------------------ | COMMENT |
| MEDIUM | core/utils/ask_gpt.py | 10 | # ------------ | COMMENT |
| MEDIUM | core/utils/ask_gpt.py | 12 | # ------------ | COMMENT |
| MEDIUM | core/utils/ask_gpt.py | 39 | # ------------ | COMMENT |
| MEDIUM | core/utils/ask_gpt.py | 41 | # ------------ | COMMENT |
| MEDIUM | core/utils/config_utils.py | 10 | # ----------------------- | COMMENT |
| MEDIUM | core/utils/config_utils.py | 12 | # ----------------------- | COMMENT |
| MEDIUM | core/asr_backend/elevenlabs_asr.py | 11 | # ---------------------------------------- | COMMENT |
| MEDIUM | core/asr_backend/elevenlabs_asr.py | 13 | # ---------------------------------------- | COMMENT |
| MEDIUM | core/asr_backend/elevenlabs_asr.py | 28 | # ---------------------------- | COMMENT |
| MEDIUM | core/asr_backend/elevenlabs_asr.py | 30 | # ---------------------------- | COMMENT |
| MEDIUM | core/asr_backend/whisperX_local.py | 11 | # ============================================================================= | COMMENT |
| MEDIUM | core/asr_backend/whisperX_local.py | 13 | # ============================================================================= | COMMENT |
| MEDIUM | core/asr_backend/whisperX_local.py | 29 | # ============================================================================= | COMMENT |
| MEDIUM | core/asr_backend/whisperX_local.py | 31 | # ============================================================================= | COMMENT |
| MEDIUM | core/asr_backend/whisperX_local.py | 147 | # ------------------------- | COMMENT |
| MEDIUM | core/asr_backend/whisperX_local.py | 149 | # ------------------------- | COMMENT |
| MEDIUM | core/asr_backend/whisperX_local.py | 165 | # ------------------------- | COMMENT |
| MEDIUM | core/asr_backend/whisperX_local.py | 167 | # ------------------------- | COMMENT |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | setup_env.py | 8 | CODE | |
| LOW | st.py | 14 | CODE | |
| LOW | st.py | 16 | CODE | |
| LOW | installer.py | 13 | CODE | |
| LOW | install.py | 8 | CODE | |
| LOW | core/_3_1_split_nlp.py | 1 | CODE | |
| LOW | core/_11_merge_audio.py | 7 | CODE | |
| LOW | core/_11_merge_audio.py | 8 | CODE | |
| LOW | core/translate_lines.py | 6 | CODE | |
| LOW | core/_9_refer_audio.py | 5 | CODE | |
| LOW | core/_9_refer_audio.py | 6 | CODE | |
| LOW | core/_9_refer_audio.py | 11 | CODE | |
| LOW | core/_8_1_audio_task.py | 8 | CODE | |
| LOW | core/_8_1_audio_task.py | 9 | CODE | |
| LOW | core/__init__.py | 3 | CODE | |
| LOW | core/__init__.py | 3 | CODE | |
| LOW | core/__init__.py | 3 | CODE | |
| LOW | core/__init__.py | 3 | CODE | |
| LOW | core/__init__.py | 3 | CODE | |
| LOW | core/__init__.py | 3 | CODE | |
| LOW | core/__init__.py | 3 | CODE | |
| LOW | core/__init__.py | 3 | CODE | |
| LOW | core/__init__.py | 3 | CODE | |
| LOW | core/__init__.py | 3 | CODE | |
| LOW | core/__init__.py | 3 | CODE | |
| LOW | core/__init__.py | 3 | CODE | |
| LOW | core/__init__.py | 3 | CODE | |
| LOW | core/__init__.py | 3 | CODE | |
| LOW | core/__init__.py | 3 | CODE | |
| LOW | core/__init__.py | 20 | CODE | |
| LOW | core/__init__.py | 21 | CODE | |
| LOW | core/__init__.py | 22 | CODE | |
| LOW | core/_7_sub_into_vid.py | 6 | CODE | |
| LOW | core/_6_gen_sub.py | 7 | CODE | |
| LOW | core/_6_gen_sub.py | 8 | CODE | |
| LOW | core/_4_2_translate.py | 8 | CODE | |
| LOW | core/_4_2_translate.py | 12 | CODE | |
| LOW | core/_1_ytdlp.py | 6 | CODE | |
| LOW | core/prompts.py | 2 | CODE | |
| LOW | core/_5_split_sub.py | 10 | CODE | |
| LOW | core/_5_split_sub.py | 11 | CODE | |
| LOW | core/_3_2_split_meaning.py | 6 | CODE | |
| LOW | core/_10_gen_audio.py | 13 | CODE | |
| LOW | core/_10_gen_audio.py | 14 | CODE | |
| LOW | core/_2_asr.py | 1 | CODE | |
| LOW | core/_2_asr.py | 5 | CODE | |
| LOW | core/_8_2_dub_chunks.py | 7 | CODE | |
| LOW | core/_8_2_dub_chunks.py | 8 | CODE | |
| LOW | core/_4_1_summarize.py | 4 | CODE | |
| LOW | core/_12_dub_to_vid.py | 10 | CODE | |
| LOW | core/_12_dub_to_vid.py | 11 | CODE | |
| LOW | core/spacy_utils/__init__.py | 1 | CODE | |
| LOW | core/spacy_utils/__init__.py | 2 | CODE | |
| LOW | core/spacy_utils/__init__.py | 3 | CODE | |
| LOW | core/spacy_utils/__init__.py | 4 | CODE | |
| LOW | core/spacy_utils/__init__.py | 5 | CODE | |
| LOW | core/spacy_utils/split_by_comma.py | 4 | CODE | |
| LOW | core/spacy_utils/split_long_by_root.py | 5 | CODE | |
| LOW | core/utils/__init__.py | 3 | CODE | |
| LOW | core/utils/__init__.py | 4 | CODE | |
| 29 more matches not shown… | ||||
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | installer.py | 81 | except Exception as exc: | CODE |
| LOW | installer.py | 104 | except Exception: | CODE |
| LOW | installer.py | 121 | except Exception: | CODE |
| LOW⚡ | installer.py | 164 | except Exception: | CODE |
| LOW⚡ | installer.py | 174 | except Exception: | CODE |
| LOW | installer.py | 211 | except Exception as exc: | CODE |
| LOW | installer.py | 346 | except Exception as exc: | CODE |
| MEDIUM | installer.py | 168 | def detect_cuda_version_from_smi() -> tuple[int, int] | None: | CODE |
| LOW | core/_8_1_audio_task.py | 38 | except Exception: | CODE |
| LOW | core/_7_sub_into_vid.py | 105 | except Exception as e: | CODE |
| MEDIUM | core/_7_sub_into_vid.py | 36 | def check_gpu_available(): | CODE |
| LOW | core/_1_ytdlp.py | 134 | except Exception: | CODE |
| MEDIUM | core/_1_ytdlp.py | 20 | def update_ytdlp(): | CODE |
| LOW | core/_10_gen_audio.py | 92 | except Exception as e: | CODE |
| LOW | core/_10_gen_audio.py | 114 | except Exception as e: | CODE |
| LOW⚡ | core/utils/delete_retry_dubbing.py | 15 | except Exception as e: | CODE |
| MEDIUM⚡ | core/utils/delete_retry_dubbing.py | 16 | print(f"Error deleting {file_path}: {str(e)}") | CODE |
| LOW⚡ | core/utils/delete_retry_dubbing.py | 25 | except Exception as e: | CODE |
| MEDIUM⚡ | core/utils/delete_retry_dubbing.py | 26 | print(f"Error deleting folder {segs_folder}: {str(e)}") | CODE |
| LOW⚡ | core/utils/decorator.py | 18 | except Exception as e: | CODE |
| LOW | core/utils/__init__.py | 19 | except Exception: | CODE |
| LOW | core/utils/pypi_autochoose.py | 81 | except Exception as exc: | CODE |
| LOW⚡ | core/utils/onekeycleanup.py | 64 | except Exception as e: | CODE |
| MEDIUM⚡ | core/utils/onekeycleanup.py | 66 | print(f"Error message: {str(e)}") | CODE |
| LOW⚡ | core/utils/onekeycleanup.py | 67 | except Exception as e: | CODE |
| MEDIUM⚡ | core/utils/onekeycleanup.py | 69 | print(f"Error message: {str(e)}") | CODE |
| MEDIUM | core/utils/onekeycleanup.py | 41 | def move_file(src, dst): | CODE |
| LOW | core/tts_backend/sf_cosyvoice2.py | 28 | except Exception as e: | CODE |
| LOW | core/tts_backend/tts_main.py | 82 | except Exception as e: | CODE |
| MEDIUM | core/tts_backend/openai_tts.py | 35 | print(f"Error: {response.status_code}") | CODE |
| LOW | core/tts_backend/gpt_sovits_tts.py | 96 | except Exception as e: | CODE |
| LOW | core/tts_backend/_302_f5tts.py | 74 | except Exception as e: | CODE |
| LOW | core/tts_backend/_302_f5tts.py | 133 | except Exception as e: | CODE |
| MEDIUM | core/tts_backend/_302_f5tts.py | 134 | print(f"Error in f5_tts_for_videolingo: {str(e)}") | CODE |
| LOW | core/tts_backend/custom_tts.py | 29 | except Exception as e: | CODE |
| MEDIUM | core/tts_backend/custom_tts.py | 30 | print(f"Error occurred during TTS conversion: {str(e)}") | CODE |
| LOW | core/st_utils/download_video_section.py | 91 | except Exception: | STRING |
| LOW | core/st_utils/download_video_section.py | 123 | except Exception: | STRING |
| LOW | core/st_utils/sidebar_setting.py | 30 | except Exception: | CODE |
| LOW | core/st_utils/sidebar_setting.py | 352 | except Exception: | CODE |
| MEDIUM | core/st_utils/sidebar_setting.py | 344 | def check_api(): | CODE |
| LOW | core/st_utils/task_runner.py | 170 | except Exception as e: | CODE |
| LOW | core/asr_backend/audio_preprocess.py | 19 | except Exception: | CODE |
| LOW | core/asr_backend/audio_preprocess.py | 87 | except Exception as e: | CODE |
| LOW | batch/utils/batch_processor.py | 77 | except Exception as e: | CODE |
| LOW | batch/utils/video_processor.py | 56 | except Exception as e: | CODE |
| LOW | translations/translations.py | 45 | except Exception: | CODE |
| LOW | translations/translations.py | 64 | except Exception: | CODE |
| LOW | translations/translations.py | 78 | except Exception: | CODE |
| LOW | translations/translations.py | 90 | except Exception: | CODE |
| LOW | translations/translations.py | 96 | except Exception: | CODE |
| MEDIUM | translations/translations.py | 40 | def _config_language(): | CODE |
| MEDIUM | translations/translations.py | 49 | def _streamlit_language(): | CODE |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | st.py | 35 | CODE | |
| LOW | st.py | 224 | CODE | |
| LOW | st.py | 302 | CODE | |
| LOW | installer.py | 316 | CODE | |
| LOW | core/_11_merge_audio.py | 54 | CODE | |
| LOW | core/_8_1_audio_task.py | 52 | CODE | |
| LOW | core/_4_2_translate.py | 55 | CODE | |
| LOW | core/_5_split_sub.py | 16 | CODE | |
| LOW | core/_5_split_sub.py | 18 | CODE | |
| LOW | core/_10_gen_audio.py | 30 | CODE | |
| LOW | core/_10_gen_audio.py | 76 | CODE | |
| LOW | core/_10_gen_audio.py | 148 | CODE | |
| LOW | core/spacy_utils/split_by_connector.py | 8 | CODE | |
| LOW | core/spacy_utils/split_by_connector.py | 84 | CODE | |
| LOW | core/spacy_utils/split_long_by_root.py | 10 | CODE | |
| LOW | core/spacy_utils/split_long_by_root.py | 64 | CODE | |
| LOW | core/utils/decorator.py | 10 | CODE | |
| LOW | core/utils/decorator.py | 11 | CODE | |
| LOW | core/utils/decorator.py | 13 | CODE | |
| LOW | core/utils/ask_gpt.py | 29 | CODE | |
| LOW | core/utils/pypi_autochoose.py | 60 | CODE | |
| LOW | core/tts_backend/tts_main.py | 25 | CODE | |
| LOW | core/tts_backend/sf_fishtts.py | 23 | CODE | |
| LOW | core/tts_backend/sf_fishtts.py | 180 | CODE | |
| LOW | core/tts_backend/estimate_duration.py | 24 | CODE | |
| LOW | core/tts_backend/estimate_duration.py | 64 | CODE | |
| LOW | core/tts_backend/gpt_sovits_tts.py | 56 | CODE | |
| LOW | core/tts_backend/gpt_sovits_tts.py | 125 | CODE | |
| LOW | core/st_utils/imports_and_utils.py | 8 | CODE | |
| LOW | core/st_utils/download_video_section.py | 65 | CODE | |
| LOW | core/st_utils/sidebar_setting.py | 47 | CODE | |
| LOW | core/asr_backend/whisperX_302.py | 13 | CODE | |
| LOW | core/asr_backend/elevenlabs_asr.py | 67 | CODE | |
| LOW | core/asr_backend/audio_preprocess.py | 130 | CODE | |
| LOW | batch/utils/batch_processor.py | 25 | CODE | |
| LOW | batch/utils/video_processor.py | 19 | CODE |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | st.py | 156 | def _subtitle_length_controls(): | CODE |
| LOW⚡ | installer.py | 168 | def detect_cuda_version_from_smi() -> tuple[int, int] | None: | CODE |
| LOW | installer.py | 230 | def install_base_requirements(force: bool = False) -> None: | CODE |
| LOW | core/prompts.py | 190 | def get_prompt_expressiveness(faithfulness_result, lines, shared_prompt): | STRING |
| LOW | core/_3_2_split_meaning.py | 111 | def split_sentences_by_meaning(): | CODE |
| LOW | core/_8_2_dub_chunks.py | 58 | def analyze_subtitle_timing_and_speed(df): | CODE |
| LOW | core/_4_1_summarize.py | 17 | def search_things_to_note_in_prompt(sentence): | CODE |
| LOW | core/spacy_utils/split_long_by_root.py | 43 | def split_extremely_long_sentence(doc): | CODE |
| LOW | core/tts_backend/sf_cosyvoice2.py | 13 | def cosyvoice_tts_for_videolingo(text, save_as, number, task_df): | CODE |
| LOW | core/tts_backend/sf_fishtts.py | 180 | def siliconflow_fish_tts_for_videolingo(text, save_as, number, task_df): | CODE |
| LOW | core/tts_backend/gpt_sovits_tts.py | 56 | def gpt_sovits_tts_for_videolingo(text, save_as, number, task_df): | CODE |
| LOW | core/tts_backend/gpt_sovits_tts.py | 109 | def find_and_check_config_path(dubbing_character): | CODE |
| LOW | core/st_utils/imports_and_utils.py | 8 | def download_subtitle_zip_button(text: str): | CODE |
| LOW | core/asr_backend/elevenlabs_asr.py | 67 | def transcribe_audio_elevenlabs(raw_audio_path, vocal_audio_path, start = None, end = None): | CODE |
| LOW | core/asr_backend/whisperX_local.py | 43 | def _has_complete_hf_snapshot(cache_root, repo_id): | CODE |
| LOW | batch/utils/video_processor.py | 98 | def process_and_align_subtitles(): | CODE |
| LOW | translations/translations.py | 32 | def _language_from_accept_language(header): | CODE |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| HIGH⚡ | config.yaml | 14 | key: 'YOUR_API_KEY' | CODE |
| HIGH | config.yaml | 79 | api_key: 'YOUR_API_KEY' | CODE |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| MEDIUM | core/_7_sub_into_vid.py | 56 | # Create a black frame | COMMENT |
| MEDIUM | core/_12_dub_to_vid.py | 44 | # Create a black frame | COMMENT |
| MEDIUM | core/tts_backend/sf_fishtts.py | 103 | # Create an empty audio segment | COMMENT |
| MEDIUM | core/tts_backend/_302_f5tts.py | 56 | # Create an empty audio segment | COMMENT |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | core/__init__.py | 26 | __all__ = [ | CODE |
| LOW | core/spacy_utils/__init__.py | 7 | __all__ = [ | CODE |
| LOW⚡ | core/utils/models.py | 39 | __all__ = [ | CODE |
| LOW | core/utils/__init__.py | 24 | __all__ = [ | CODE |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | core/tts_backend/tts_main.py | 27 | # Check if text is empty or single character, single character voiceovers are prone to bugs | COMMENT |
| LOW | core/tts_backend/gpt_sovits_tts.py | 88 | # Check if the reference audio file exists | COMMENT |
| LOW | core/tts_backend/gpt_sovits_tts.py | 127 | # Check if port 9880 is already in use | COMMENT |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | core/spacy_utils/split_long_by_root.py | 101 | # nlp = init_nlp() | COMMENT |
| LOW | core/tts_backend/sf_fishtts.py | 221 | # siliconflow_fish_tts("使用动态音色测试", "dynamic_test.wav", mode="dynamic", ref_audio="output/audio/refers/1.wav", ref_te | COMMENT |
| LOW | core/tts_backend/edge_tts.py | 1 | from pathlib import Path | COMMENT |
| LOW | docs/next-env.d.ts | 1 | /// <reference types="next" /> | COMMENT |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | core/translate_lines.py | 42 | ## Step 1: Faithful to the Original Text | COMMENT |
| LOW | core/translate_lines.py | 66 | ## Step 2: Express Smoothly | COMMENT |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | core/translate_lines.py | 42 | ## Step 1: Faithful to the Original Text | COMMENT |
| LOW | core/translate_lines.py | 66 | ## Step 2: Express Smoothly | COMMENT |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | core/_1_ytdlp.py | 138 | # Example usage | COMMENT |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | core/utils/decorator.py | 47 | def test_function(): | CODE |