{"id":27067055,"url":"https://github.com/mimisukemaster/faster-whisper-test","last_synced_at":"2025-08-31T20:11:22.741Z","repository":{"id":283941706,"uuid":"953357255","full_name":"mimisukeMaster/faster-whisper-test","owner":"mimisukeMaster","description":"A sample project to test and demonstrate faster-whisper","archived":false,"fork":false,"pushed_at":"2025-03-27T10:25:20.000Z","size":31560,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-06-12T12:08:28.823Z","etag":null,"topics":["faster-whisper","speech-recognition","speech-to-text","stt","voice-recognition"],"latest_commit_sha":null,"homepage":"https://github.com/SYSTRAN/faster-whisper","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/mimisukeMaster.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2025-03-23T06:58:11.000Z","updated_at":"2025-03-27T10:25:23.000Z","dependencies_parsed_at":null,"dependency_job_id":"45b332e2-2d14-48c6-967f-e280982bcce6","html_url":"https://github.com/mimisukeMaster/faster-whisper-test","commit_stats":null,"previous_names":["mimisukemaster/faster-whisper-test"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/mimisukeMaster/faster-whisper-test","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mimisukeMaster%2Ffaster-whisper-test","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mimisukeMaster%2Ffaster-whisper-test/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mimisukeMaster%2Ffaster-whisper-test/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mimisukeMaster%2Ffaster-whisper-test/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/mimisukeMaster","download_url":"https://codeload.github.com/mimisukeMaster/faster-whisper-test/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mimisukeMaster%2Ffaster-whisper-test/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":273032934,"owners_count":25034067,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-08-31T02:00:09.071Z","response_time":79,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["faster-whisper","speech-recognition","speech-to-text","stt","voice-recognition"],"created_at":"2025-04-05T19:39:48.553Z","updated_at":"2025-08-31T20:11:22.733Z","avatar_url":"https://github.com/mimisukeMaster.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# faster-whisper-test\n[\u003cimg src=\"https://img.shields.io/github/stars/mimisukeMaster/faster-whisper-test\"\u003e](https://github.com/mimisukeMaster/faster-whisper-test/stargazers)\n[\u003cimg  src=\"https://img.shields.io/github/license/mimisukeMaster/faster-whisper-test\"\u003e](/LICENSE)\n[\u003cimg src=\"https://img.shields.io/badge/issues-welcome-orange\"\u003e](https://github.com/mimisukeMaster/faster-whisper-test/issues)\u003cbr\u003e\n\u003cimg src=\"https://img.shields.io/github/repo-size/mimisukeMaster/faster-whisper-test?color=ff69b4\u0026logo=gitlfs\"\u003e\n[\u003cimg src=\"https://img.shields.io/static/v1?label=\u0026message=Open%20in%20Visual%20Studio%20Code\u0026color=007acc\u0026style=flat\"\u003e](https://github.dev/mimisukeMaster/faster-whisper-test)\n\nA sample project to test and demonstrate [faster-whisper](https://github.com/guillaumekln/faster-whisper).\n\n\n## About\n\n[faster-whisper](https://github.com/guillaumekln/faster-whisper) のテストと動作確認を目的としたサンプルプロジェクトです。\n\nfaster-whisperは、高速な音声認識推論を実現するライブラリです。このプロジェクトでは、実際にYoutubeのリンクからその動画の文字起こし(STT処理)を行います。\n\n## Requirements and Models\n- 必要なパッケージは以下の通りです。（実行するタイミングは下方参照）\u003cbr\u003e\nバージョンはあくまで自機で動作確認済みのものです。\n    ```cmd\n    yt-dlp==2025.3.21 \n    faster_whisper==1.1.1\n    ffmpeg==4.3.1\n    cudnn==9.1.1.17\n    ```\n\n- GPUでの推論の場合、動かすモデルに対応するスペック以上のGPUが必要です。\u003cbr\u003e\n実行時間は5~6倍かかりますが、CPUで動かすことも可能です。\n\n    |モデル|パラメータ数|推奨VRAM|\n    |:----:|:----:|:----:|\n    |tiny|32M|1GB以上|\n    |base|74M|2GB以上|\n    |small|244M|4GB以上|\n    |medium|769M|6GB以上|\n    |large, large-v3|1550M|10GB以上|\n\n    また、GPUはFP16（半精度浮動小数点）計算に対応しており、CUDA Compute Capability 6.0以上（Pascal世代以降）が推奨です。\n    ※GPUの性能が対象のモデルに見合わない場合、推論が正常に行われず、音声の一部が変換されなかったり`out-of-memory`エラーにより処理が中断される可能性があります。\n\n  - 2025/3現在、公式のHugging Faceでは`large`モデル以外を使う場合、より軽量・高速化した蒸留モデル`distil-large-v3`の使用が推奨されています([参照](https://huggingface.co/distil-whisper))が、日本語の推論はサポートされていないことをご注意ください。\n\n\n## Get Started\n\n### 1. conda環境の作成\n\n[Anaconda](https://www.anaconda.com/)を使用してPythonの実行環境を用意します。\u003cbr\u003e**環境作成にvenvを用いると、ffmpeg, cudnnを手動で入れる手間が生じるので、condaの使用を推奨します。**\n\nAnaconda Prompt から、新しいconda環境を作成します。\n```cmd\nconda create -n [環境名] python==3.11\n```\nその環境内で、以下のコマンドを実行して必要なパッケージをインストールしてください。\n\n```cmd\npip install yt-dlp\npip install faster_whisper\nconda install -c conda-forge ffmpeg\nconda install -c conda-forge cudnn\n```\n\n### 2. 実行方法\n実行方法は2通りあります:\n\n1. **VSCode から実行する場合:**\n   - VSCode でこのプロジェクトを開きます。\n   - 右下の `インタプリタの選択` から先ほど作成したconda環境を選択します。\n   - `main.py` を実行してください。\n\n2. **Anaconda Prompt から実行する場合:**\n   - 作成した環境をactivateさせたAnaconda Prompt から、`main.py` が存在するディレクトリに移動します。\n   - 以下のコマンドを実行してください:\n     ```bash\n     python main.py\n     ```\n\n## References\n\n- このプロジェクトはこちらの記事をもとに作成しました:\u003cbr\u003e\n    https://zenn.dev/tsuzukia/articles/1381e6c9a88577\n- faster-whisper Hugging Face:\u003cbr\u003e\n    https://huggingface.co/models?search=openai/whisper\n- 推論時の量子化処理の程度と必要なスペック:\u003cbr\u003e\n    https://opennmt.net/CTranslate2/quantization.html\n\n\n## License\nfaster-whisper-test is under the [MIT](/LICENSE) license.","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmimisukemaster%2Ffaster-whisper-test","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmimisukemaster%2Ffaster-whisper-test","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmimisukemaster%2Ffaster-whisper-test/lists"}