{"data":{"slug":"softcatala-whisper-ctranslate2","name":"whisper-ctranslate2","tagline":"Whisper command line client compatible with original OpenAI client based on CTranslate2","github_url":"https://github.com/Softcatala/whisper-ctranslate2","owner":"Softcatala","repo":"whisper-ctranslate2","owner_avatar_url":"https://avatars.githubusercontent.com/u/978352?v=4","primary_language":"Python","stars":1350,"forks":126,"topics":["openai-","openai-whisper","speech-recognition","speech-to-text","whisper"],"archived":false,"github_pushed_at":"2026-02-14T19:16:02+00:00","maintenance_label":"Slowing","stars_delta_30d":17,"url":"https://www.graphcanon.com/tools/softcatala-whisper-ctranslate2","markdown_url":"https://www.graphcanon.com/tools/softcatala-whisper-ctranslate2.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/softcatala-whisper-ctranslate2","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=softcatala-whisper-ctranslate2","description":"Whisper command line client compatible with original OpenAI client based on CTranslate2.","homepage_url":null,"license":"MIT","open_issues":13,"watchers":19,"ai_summary":"A speech-to-text tool that provides a command-line interface for Whisper models using CTranslate2, compatible with the original OpenAI client.","readme_excerpt":"## Using prebuild Docker image\n\nYou can use build docker image. First pull the image:\n\n    docker pull ghcr.io/softcatala/whisper-ctranslate2:latest\n\nThe Docker image includes the small, medium and large-v2 models.\n\nTo run it:\n\n    docker run --gpus \"device=0\" \\\n        -v \"$(pwd)\":/srv/files/ \\\n        -it ghcr.io/softcatala/whisper-ctranslate2:latest \\\n        /srv/files/e2e-tests/gossos.mp3 \\\n        --output_dir /srv/files/\n    \nNotes:\n* _--gpus \"device=0\"_ gives access to the GPU. If you do not have a GPU, remove this.\n* _\"$(pwd)\":/srv/files/_ maps your current directory to /srv/files/ inside the container\n\nIf you always need to use a model that is not in the image, you can create a derived Docker image with the model preloaded or use Docker volumes to persist and share the model files.","github_created_at":"2023-03-17T10:19:45+00:00","created_at":"2026-07-11T12:19:32.121879+00:00","updated_at":"2026-09-20T04:29:51.343081+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":"ctranslate2","name":"ctranslate2"},{"slug":"docker","name":"docker"},{"slug":"gpu-support","name":"gpu-support"},{"slug":"openai","name":"openai"},{"slug":"openai-whisper","name":"openai-whisper"},{"slug":"speech-recognition","name":"speech recognition"},{"slug":"speech-to-text","name":"speech-to-text"},{"slug":"whisper","name":"whisper"}],"trust":{"provenance":{"is_fork":false,"github_id":615270502,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-09-18T08:19:06.742Z","maintenance":{"label":"Slowing","score":36,"methodology":"github_public_v1","releases_90d":0,"days_since_push":215,"last_release_at":null,"stars_delta_30d":17,"open_issues_delta_30d":0},"security_summary":{"status":"ok","scanner":"osv@v1","low_count":0,"high_count":0,"last_scan_at":"2026-09-18T08:19:08.374Z","medium_count":0,"scan_profile":"deps","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-09-18T08:19:05.685Z"},"deploy":{"source":"dockerfile:Dockerfile","self_host":true,"observed_at":"2026-09-18T08:19:05.685Z","managed_saas":false},"languages":{"value":["python"],"source":"github.language","observed_at":"2026-09-18T08:19:05.685Z"},"has_docker":{"value":true,"source":"dockerfile:Dockerfile","observed_at":"2026-09-18T08:19:05.685Z"},"license_spdx":{"value":"MIT","source":"github.license","observed_at":"2026-09-18T08:19:05.685Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["Use whisper-ctranslate2 when you need a command-line interface for Whisper models that is compatible with the original OpenAI client and leverages CTranslate2 for performance.","Opt for whisper-ctranslate2 if you are working in an environment where Docker is preferred for deployment, as it provides a prebuilt Docker image that includes the small, medium, and large-v2 models.","Choose this tool if you require GPU acceleration for faster processing, as it supports GPU usage through Docker configuration."],"when_not_to_use":["Avoid whisper-ctranslate2 if you do not have access to a GPU and require a tool that performs well without GPU acceleration.","Do not use whisper-ctranslate2 if you need a tool that supports models not included in the prebuilt Docker image and you cannot or do not want to create a derived Docker image or use Docker volumes.","If your workflow does not align with Docker-based deployment, consider alternatives that do not require Docker for operation."],"source":"enrich:decision_facts","observed_at":"2026-09-18T10:14:59.633Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"whisper-ctranslate2 is a speech-to-text tool that offers a command-line interface for Whisper models using CTranslate2, ensuring compatibility with the original OpenAI client."}]}}