{"id":28529503,"url":"https://github.com/mlcommons/peoples-speech","last_synced_at":"2025-08-01T19:08:20.803Z","repository":{"id":38296607,"uuid":"338177905","full_name":"mlcommons/peoples-speech","owner":"mlcommons","description":"The People’s Speech Dataset","archived":false,"fork":false,"pushed_at":"2024-01-11T19:14:32.000Z","size":147829,"stargazers_count":104,"open_issues_count":37,"forks_count":12,"subscribers_count":15,"default_branch":"main","last_synced_at":"2025-06-09T14:12:56.820Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"https://mlcommons.org/en/peoples-speech/","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/mlcommons.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE.md","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":".github/CODEOWNERS","security":null,"support":null,"governance":null,"roadmap":null,"authors":null}},"created_at":"2021-02-11T23:16:38.000Z","updated_at":"2025-05-28T10:54:35.000Z","dependencies_parsed_at":"2024-01-11T23:38:45.333Z","dependency_job_id":"ab9d13cd-77c6-4e13-86e2-9041389d493c","html_url":"https://github.com/mlcommons/peoples-speech","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/mlcommons/peoples-speech","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mlcommons%2Fpeoples-speech","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mlcommons%2Fpeoples-speech/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mlcommons%2Fpeoples-speech/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mlcommons%2Fpeoples-speech/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/mlcommons","download_url":"https://codeload.github.com/mlcommons/peoples-speech/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mlcommons%2Fpeoples-speech/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":268281834,"owners_count":24225159,"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":"2025-08-01T02:00:08.611Z","response_time":67,"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":[],"created_at":"2025-06-09T14:11:11.688Z","updated_at":"2025-08-01T19:08:20.765Z","avatar_url":"https://github.com/mlcommons.png","language":"Jupyter Notebook","funding_links":[],"categories":["Popular Training Datasets"],"sub_categories":["Mixed Tokenizers"],"readme":"# People's Speech Data Pipelines\n\nInstallation\n\n\n```\n# libprotobuf-dev is an onnx dependency, transitively brought in by nemo.\nsudo apt-get install git-lfs sox ffmpeg\n# Set up a virtual environment of some sort\npip install numpy Cython\npython setup.py develop\ncp galvasr2/*.jar $(python -c \"import pyspark; print(pyspark.__path__[0])\")/jars\n```\n\nRun forced alignment pipeline.\n\n```\npython galvasr2/align/spark/align_cuda_decoder.py --stage=0\n```\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmlcommons%2Fpeoples-speech","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmlcommons%2Fpeoples-speech","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmlcommons%2Fpeoples-speech/lists"}