{"data":{"slug":"purfview-whisper-standalone-win","name":"whisper-standalone-win","tagline":"Standalone executables for Whisper and Faster-Whisper speech recognition on Windows, Linux, macOS","github_url":"https://github.com/Purfview/whisper-standalone-win","owner":"Purfview","repo":"whisper-standalone-win","owner_avatar_url":"https://avatars.githubusercontent.com/u/69023953?v=4","primary_language":null,"stars":3135,"forks":165,"topics":["asr","ctranslate2","diarization","faster-whisper","openai","speaker-diarization","speech-recognition","speech-to-text","subtitles","transcriber","uvr","vocal-extractor","whisper","whisper-faster","whisperx"],"archived":false,"github_pushed_at":"2025-11-07T19:21:55+00:00","maintenance_label":"Slowing","url":"https://www.graphcanon.com/tools/purfview-whisper-standalone-win","markdown_url":"https://www.graphcanon.com/tools/purfview-whisper-standalone-win.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/purfview-whisper-standalone-win","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=purfview-whisper-standalone-win","description":"Whisper & Faster-Whisper standalone executables for those who don't want to bother with Python. ","homepage_url":null,"license":null,"open_issues":8,"watchers":56,"ai_summary":"Offers executable files of Whisper and Faster-Whisper models designed to run without Python dependency across different operating systems.","readme_excerpt":"[Standalone executables](https://github.com/Purfview/whisper-standalone-win/releases) of [OpenAI's Whisper](https://github.com/openai/whisper) & [Faster-Whisper](https://github.com/guillaumekln/faster-whisper) for those who don't want to bother with Python.\n\n**Faster-Whisper** - executables are x86-64 compatible with Windows 7, Linux v5.4, macOS v10.15 and above.   \n**Faster-Whisper-XXL** - the last executables are x86-64 compatible with Windows 10, Linux v5.15 and above.       \n[**Faster-Whisper-XXL Pro**](https://github.com/Purfview/whisper-standalone-win/discussions/456) - as above. Special non-public version for the donators.           \n**Whisper** - executables are x86-64 compatible with Windows 10 and above.   \n     \nMeant to be used in command-line interface or in programs like:   \n[Subtitle Edit](https://github.com/SubtitleEdit/subtitleedit), [Tero Subtitler](https://github.com/URUWorks/TeroSubtitler), [FFAStrans](https://ffastrans.com/wp/), [AviUtl](https://github.com/oov/aviutl_subtitler), [PotPlayer](https://potplayer.daum.net)           \nFaster-Whisper is much faster & better than OpenAI's Whisper, and it requires less RAM/VRAM.\n\n## Usage examples:\n* `faster-whisper-xxl.exe \"D:\\videofile.mkv\" --language English --model medium --output_dir source`\n* `faster-whisper-xxl.exe \"D:\\Folder\" -l en -m turbo --sentence --batch_recursive`\n* `faster-whisper-xxl.exe \"D:\\videofile.mkv\" -l ja -m medium --task translate --standard -o source`      \n* `faster-whisper-xxl.exe --help`\n\n## Notes:\n\nExecutables & libs can be downloaded from `Releases`. [at the right side of this page]    \nDon't copy programs to the Windows' folders! [run as Administrator if you did]       \nPrograms automatically will choose to work on GPU if CUDA is detected.   \nFor decent transcription use not smaller than `medium` model.   \nGuide how to run the command line programs: https://www.youtube.com/watch?v=A3nwRCV-bTU     \n\n## Standalone Whisper info:\n\nVanilla Whisper, compiled as is - no changes to the original code.   \nA reference implementation, stagnant development, atm maybe useful for some tests.\n   \n## Standalone Faster-Whisper info:\n\nSome defaults are tweaked for movies transcriptions and to make it portable.    \nFeatures various new experimental settings and tweaks.   \nShows the progress bar in the title bar of command-line interface. [or it can be printed with `-pp`]   \nBy default it looks for models in the same folder, in path like this -> `_models\\faster-whisper-medium`.   \nModels are downloaded automatically or can be downloaded manually from: [Systran](https://huggingface.co/Systran) & [Purfview](https://huggingface.co/Purfview)        \nDeprecated. Use Faster-Whisper-XXL\n\n## Standalone Faster-Whisper-XXL info:\n\nIncludes all Standalone Faster-Whisper features + the additional ones, for example:   \nPreprocess audio with MDX23 Kim_vocal_v2 vocal extraction model.   \nAlternative VAD methods: 'silero_v3', 'silero_v4', 'silero_v5', 'pyannote_v3', 'pyannote_onnx_v3', 'auditok', 'webrtc'.   \n[Speaker Diarization](https://github.com/Purfview/whisper-standalone-win/discussions/322).    \nRead more about new features in [the Discussions' thread](https://github.com/Purfview/whisper-standalone-win/discussions/231).\n\n## Standalone Faster-Whisper-XXL Pro info:    \n    \nSpecial non-public version for the donators.     \nIncludes some new advanced features, there is the log: [the Discussions' thread](https://github.com/Purfview/whisper-standalone-win/discussions/456).","github_created_at":"2023-02-25T18:32:55+00:00","created_at":"2026-07-11T12:16:21.922094+00:00","updated_at":"2026-07-30T12:00:33.18872+00:00","categories":[{"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":"asr","name":"asr"},{"slug":"faster-whisper","name":"faster-whisper"},{"slug":"speech-recognition","name":"speech-recognition"},{"slug":"speech-to-text","name":"speech-to-text"},{"slug":"transcriber","name":"transcriber"},{"slug":"whisper","name":"whisper"}],"trust":{"provenance":{"is_fork":false,"github_id":606520610,"owner_type":"User","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-07-30T12:00:32.402Z","maintenance":{"label":"Slowing","score":36,"methodology":"github_public_v1","releases_90d":0,"days_since_push":264,"last_release_at":"2025-11-07T19:21:55Z"},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T12:16:23.523Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-07-30T12:00:32.911Z"}},"decision_facts":{"hosting":null,"pricing":{"model":"freemium","summary":"The basic versions are free to use. The 'Standalone Faster-Whisper-XXL Pro' offers advanced features exclusively to donators."},"requirements":{"notes":["Minimum RAM recommended based on the usage of not smaller than medium model for decent transcription."],"min_ram_gb":8},"constraints":{"min_ram_gb":8,"pricing_model":"freemium"},"when_to_use":["When you need a no-code solution for speech-to-text transcription on Windows, Linux, or macOS.","If you prefer command-line interfaces or integrating into programs like Subtitle Edit or Tero Subtitler.","For users who wish to use Whisper models without the complexity of setting up Python environments."],"when_not_to_use":["When your project requires real-time speech recognition capabilities, as this tool may have latency issues due to its standalone nature.","If you require extensive customization or integration with other languages and tools that use Python APIs directly.","In environments where GPU acceleration is critical and the overhead of automatic detection for CUDA could affect performance."],"source":"enrich:decision_facts","observed_at":"2026-07-17T01:23:24.412Z"},"constraint_facets":{"min_ram_gb":8,"pricing_model":"freemium"},"decision_summary":[{"label":"Pricing","value":"freemium - The basic versions are free to use. The 'Standalone Faster-Whisper-XXL Pro' offers advanced features exclusively to donators."},{"label":"Requirements","value":"Min 8 GB RAM; Minimum RAM recommended based on the usage of not smaller than medium model for decent transcription."},{"label":"Adopt for","value":"whisper-standalone-win is a collection of executable files for Whisper and Faster-Whisper models designed to simplify speech recognition tasks without requiring Python."}]}}