{"id":15980747,"url":"https://github.com/ccoreilly/datapipe","last_synced_at":"2025-07-15T06:42:45.627Z","repository":{"id":107871468,"uuid":"447691627","full_name":"ccoreilly/datapipe","owner":"ccoreilly","description":"An audio ETL pipeline for generating datasets from youtube sources","archived":false,"fork":false,"pushed_at":"2022-05-05T13:20:13.000Z","size":17019,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-06-26T12:02:40.767Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":false,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"agpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/ccoreilly.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":"CITATION.cff","codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2022-01-13T17:31:17.000Z","updated_at":"2022-05-05T13:22:06.000Z","dependencies_parsed_at":null,"dependency_job_id":"98d95bb7-b311-4272-9bae-1d9ff624c7d3","html_url":"https://github.com/ccoreilly/datapipe","commit_stats":{"total_commits":25,"total_committers":1,"mean_commits":25.0,"dds":0.0,"last_synced_commit":"024cae35cda82abf0bc1326827246d44cb677913"},"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/ccoreilly/datapipe","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ccoreilly%2Fdatapipe","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ccoreilly%2Fdatapipe/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ccoreilly%2Fdatapipe/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ccoreilly%2Fdatapipe/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ccoreilly","download_url":"https://codeload.github.com/ccoreilly/datapipe/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ccoreilly%2Fdatapipe/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":262063448,"owners_count":23252761,"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":"2024-10-08T00:22:17.085Z","updated_at":"2025-06-26T12:04:05.310Z","avatar_url":"https://github.com/ccoreilly.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Audio datapipe\n\nA data processing pipeline that (currently) extracts audio clips from youtube videos and generates two transcription candidates with a Vosk (Kaldi) and a Wav2Vec2 model. The goal of the software is to ease the generation of datasets for ASR by automatically extracting and processing large audio sources.\n\nThis software has been written for internal use and made public as it might be useful for someone. However, no support and no warranty will be provided.\n\nCopyright © 2021 Ciaran O'Reilly\n\nLicensed under the GNU AFFERO GENERAL PUBLIC LICENSE (AGPLv3)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fccoreilly%2Fdatapipe","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fccoreilly%2Fdatapipe","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fccoreilly%2Fdatapipe/lists"}