{"id":23104807,"url":"https://github.com/mayniklas/whisper_bench","last_synced_at":"2025-04-03T22:13:05.585Z","repository":{"id":109061427,"uuid":"597551867","full_name":"MayNiklas/whisper_bench","owner":"MayNiklas","description":"A benchmark script to evaluate the performance of Whisper on different hardware.","archived":false,"fork":false,"pushed_at":"2023-11-04T12:20:36.000Z","size":16097,"stargazers_count":0,"open_issues_count":0,"forks_count":2,"subscribers_count":3,"default_branch":"main","last_synced_at":"2025-02-09T10:09:42.375Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/MayNiklas.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"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}},"created_at":"2023-02-04T22:08:43.000Z","updated_at":"2023-02-05T10:29:45.000Z","dependencies_parsed_at":"2023-08-27T03:20:16.471Z","dependency_job_id":null,"html_url":"https://github.com/MayNiklas/whisper_bench","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MayNiklas%2Fwhisper_bench","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MayNiklas%2Fwhisper_bench/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MayNiklas%2Fwhisper_bench/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MayNiklas%2Fwhisper_bench/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/MayNiklas","download_url":"https://codeload.github.com/MayNiklas/whisper_bench/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247086027,"owners_count":20881160,"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","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":[],"created_at":"2024-12-17T00:36:26.368Z","updated_at":"2025-04-03T22:13:05.569Z","avatar_url":"https://github.com/MayNiklas.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# whisper Benchmark\n\nThank you for helping us to evaluate the performance of Whisper on different hardware platforms!\n\n## How to run the benchmark\n\n### NixOS\n\n```bash\n# nix run the benchmark\nnix run 'github:mayniklas/whisper_bench'#whisper_bench_withCUDA\n```\n\n### Linux\n\nPre-requisites:\n\n1. install [NVIDIA CUDA](https://developer.nvidia.com/cuda-downloads?target_os=Linux)\n2. install ffmpeg (e.g. `sudo apt install ffmpeg`)\n\n```bash\n# clone the repository\ngit clone https://github.com/MayNiklas/whisper_bench.git\n\n# change into the directory\ncd whisper_bench\n\n# create a virtual environment\npython3 -m venv .venv\nsource .venv/bin/activate\n\n# install dependencies into the virtual environment\n.venv/bin/pip3 install -r requirements.txt\n\n# run the benchmark from within the virtual environment\n.venv/bin/python3 bench/bench.py\n```\n\n### Windows\n\nPre-requisites:\n\n1. install [NVIDIA CUDA](https://developer.nvidia.com/cuda-downloads?target_os=Windows\u0026target_arch=x86_64)\n2. install the command-line tool ffmpeg (e.g. `choco install ffmpeg`)\n\n```powershell\n# clone the repository\ngit clone 'https://github.com/MayNiklas/whisper_bench.git'\n\n# create a virtual environment\npython3 -m venv .venv\n.venv\\Scripts\\activate\n\n# change into the directory\ncd whisper_bench\n\n# install PyTorch - see https://pytorch.org/get-started/locally/\n# to get the correct command for your system\n# e.g.\npip3 install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cu117\n\n# install dependencies into the virtual environment\n.venv\\Scripts\\pip3 install -r requirements.txt\n\n# run the benchmark from within the virtual environment\n.venv\\Scripts\\python3 bench\\bench.py\n```\n\n## Projects being used\n\n* [OpenAI Whisper](https://github.com/openai/whisper)\n* [PyTorch](https://pytorch.org/)\n\n## Audio files being used\n\nTo compare the performance for different lengths of audio files, we run the benchmark with one short and one long audio file.\nIn theory, the setup time should stay arround the same for both files, while the processing time should linearly increase with the length of the audio file.\n\n* \u003chttps://en.wikipedia.org/wiki/File:En-Open_Source_Software_CD-article.ogg\u003e (public domain license)\n* \u003chttps://commons.wikimedia.org/wiki/File:A_Time_for_Choosing.ogg\u003e (public domain license)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmayniklas%2Fwhisper_bench","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmayniklas%2Fwhisper_bench","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmayniklas%2Fwhisper_bench/lists"}