{"data":{"slug":"meizhong986-whisperjav","name":"WhisperJAV","tagline":"ASR/STT subtitle generator using Qwen3-ASR and Whisper","github_url":"https://github.com/meizhong986/WhisperJAV","owner":"meizhong986","repo":"WhisperJAV","owner_avatar_url":"https://avatars.githubusercontent.com/u/148393222?v=4","primary_language":"Python","stars":2066,"forks":166,"topics":["aitranslate","hallucination","japanese","llm","modelscope","qwen3","qwen3-asr","speech-to-text","speechenhancement","subtitling","ten-vad","whisper","zipformer"],"archived":false,"github_pushed_at":"2026-05-10T17:16:11+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/meizhong986-whisperjav","markdown_url":"https://www.graphcanon.com/tools/meizhong986-whisperjav.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/meizhong986-whisperjav","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=meizhong986-whisperjav","description":"ASR/STT subtitle generator. Uses Qwen3-ASR, local LLM, Whisper, TEN-VAD. Noise-robust for JAV","homepage_url":"https://github.com/meizhong986/WhisperJAV/releases/latest","license":"MIT","open_issues":131,"watchers":9,"ai_summary":"WhisperJAV uses Qwen3-ASR, local LLMs, and Whisper for noise-robust subtitling of JAV content.","readme_excerpt":"## Installation\n\n> **Upgrading?** Run `whisperjav-upgrade` (works on Windows, Linux, and macOS). For code-only updates: `whisperjav-upgrade --wheel-only`. See the [Upgrade Guide](docs/en/UPGRADE.md) for details.\n\n---\n\n---\n\n### Which Installation Path Should I Follow?\n\n| Your Situation | Go To |\n|----------------|-------|\n| **New user on Windows** wanting GUI | [Windows Standalone Installer](#windows-standalone-installer) |\n| **Developer on Windows** | [Windows Source Install](#windows-source-install) |\n| **macOS user** | [macOS (Apple Silicon)](#macos-apple-silicon) |\n| **Linux user** | [Linux](#linux-ubuntu-debian-fedora-arch) |\n| **Colab or Kaggle** | [Cloud Notebooks](#google-colab--kaggle) |\n| **Developer or expert** wanting pip | [Expert Installation](#expert-installation) |\n\n---\n\n---\n\n### Windows Source Install\n\nFor people who manage their own Python environments.\n\n**Prerequisites:** Python 3.10-3.12, Git, FFmpeg in PATH.\n\n```batch\ngit clone https://github.com/meizhong986/whisperjav.git\ncd whisperjav\n\n:: Full automated install (auto-detects GPU)\ninstaller\\install_windows.bat\n\n:: Or with options:\ninstaller\\install_windows.bat --cpu-only        :: Force CPU\ninstaller\\install_windows.bat --cuda118         :: Force CUDA 11.8\ninstaller\\install_windows.bat --cuda128         :: Force CUDA 12.8\ninstaller\\install_windows.bat --local-llm       :: Include local LLM translation\n```\n\nThe installer runs in 5 phases: PyTorch first (with GPU detection), then scientific stack, Whisper packages, audio/CLI tools, and optional extras. This order matters — PyTorch must be installed before anything that depends on it, or you end up with CPU-only wheels.\n\nFor the full walkthrough, see [docs/en/guides/installation_windows_python.md](docs/en/guides/installation_windows_python.md).\n\n---\n\n---\n\n# Recommended: use the install script\nchmod +x installer/install_linux.sh\n./installer/install_linux.sh\n\n---\n\n### Expert Installation\n\nFor users comfortable with Python package management. Choose the components you need.\n\n#### Modular Installation\n\nWhisperJAV supports modular extras. Install only what you need:\n\n```bash\n\n---\n\n# Install in editable mode with dev dependencies\npip install -e \".[dev]\"\n\n---\n\n### System Requirements\n\n| Requirement | Minimum | Recommended |\n|-------------|---------|-------------|\n| **OS** | Windows 10, macOS 11, Ubuntu 20.04 | Windows 11, macOS 14, Ubuntu 22.04 |\n| **Python** | 3.10 | 3.11 |\n| **RAM** | 8 GB | 16 GB |\n| **Disk** | 8 GB | 15 GB (with models) |\n| **GPU** | None (CPU works) | NVIDIA RTX 2060+ or Apple Silicon |\n\n**GPU Support:**\n- NVIDIA: CUDA 11.8 or 12.8 (Windows, Linux)\n- Apple Silicon: MPS acceleration for Whisper (M1/M2/M3/M4/M5). Qwen pipeline is CPU-only on Mac for now.\n- AMD ROCm: Experimental (Linux only)\n- CPU fallback: Works on all platforms, 5-10x slower\n\n**Processing Time Estimates (per hour of video):**\n\n| Hardware | Time |\n|----------|------|\n| NVIDIA RTX GPU | 5-10 minutes |\n| Apple Silicon | 8-15 minutes |\n| CPU | 30-60 minutes |\n\n---\n\n---\n\n## License\n\nMIT License. See [LICENSE](LICENSE) file.\n\n---","github_created_at":"2023-10-18T20:37:14+00:00","created_at":"2026-07-11T12:18:06.436031+00:00","updated_at":"2026-07-30T18:00:19.593677+00:00","categories":[{"slug":"llm-frameworks","name":"LLM Frameworks","url":"https://www.graphcanon.com/categories/llm-frameworks","markdown_url":"https://www.graphcanon.com/categories/llm-frameworks.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/llm-frameworks"},{"slug":"speech-audio","name":"Speech & Audio","url":"https://www.graphcanon.com/categories/speech-audio","markdown_url":"https://www.graphcanon.com/categories/speech-audio.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/speech-audio"}],"tags":[{"slug":"noise-robustness","name":"noise-robustness"},{"slug":"qwen3-asr","name":"qwen3-asr"},{"slug":"speech-to-text","name":"speech-to-text"},{"slug":"subtitling","name":"subtitling"},{"slug":"ten-vad","name":"ten-vad"},{"slug":"whisper","name":"whisper"}],"trust":{"provenance":{"is_fork":false,"github_id":706895820,"owner_type":"User","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-07-30T18:00:18.164Z","maintenance":{"label":"Steady","score":60,"methodology":"github_public_v1","releases_90d":2,"days_since_push":81,"last_release_at":"2026-05-10T17:27:27Z"},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T12:18:11.691Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-07-30T18:00:19.267Z"},"has_cli":{"value":true,"source":"pyproject.toml:[project.scripts]","observed_at":"2026-07-30T18:00:19.267Z"},"languages":{"value":["python"],"source":"github.language+pyproject.toml","observed_at":"2026-07-30T18:00:19.267Z"},"license_spdx":{"value":"MIT","source":"github.license","observed_at":"2026-07-30T18:00:19.267Z"}},"decision_facts":{"hosting":null,"pricing":{"model":"freemium","summary":"The tool itself is free under MIT license, but users may incur costs related to required hardware, especially if using it extensively with high-performance GPU setups."},"requirements":{"notes":["Operating systems supported are Windows 10+, macOS 11+, and Ubuntu 20.04+.","Requires Python version between 3.10 and 3.12; recommended Python versions vary by platform but generally aim for the latest within this range."],"min_ram_gb":8,"requires_docker":false},"constraints":{"min_ram_gb":8,"pricing_model":"freemium","requires_docker":false},"when_to_use":["When you need specialized noise-robust subtitling specifically designed for JAV content.","For users who require the integration of local language models (LLMs) with ASR functionalities.","If your project requires the use of Qwen3-ASR, Whisper, and TEN-VAD for high-quality speech-to-text conversion."],"when_not_to_use":["Avoid if you are working on non-JAV content which does not benefit from specific noise handling optimized for JAV.","Not suitable if your project is solely focused on real-time ASR without the need for extensive offline processing and noise correction provided by WhisperJAV."],"source":"enrich:decision_facts","observed_at":"2026-07-17T02:06:17.379Z"},"constraint_facets":{"min_ram_gb":8,"pricing_model":"freemium","requires_docker":false},"decision_summary":[{"label":"Pricing","value":"freemium - The tool itself is free under MIT license, but users may incur costs related to required hardware, especially if using it extensively with high-performance GPU setups."},{"label":"Requirements","value":"Min 8 GB RAM; Operating systems supported are Windows 10+, macOS 11+, and Ubuntu 20.04+.; Requires Python version between 3.10 and 3.12; recommended Python versions vary by platform but generally aim for the latest within this range."},{"label":"Adopt for","value":"WhisperJAV employs Qwen3-ASR and Whisper for automatic speech recognition tailored specifically to JAV content, offering robust noise handling."}]}}