{"id":29099925,"url":"https://github.com/bcc-code/bccmedia-song-or-not","last_synced_at":"2025-06-28T17:38:01.008Z","repository":{"id":176660006,"uuid":"648211916","full_name":"bcc-code/bccmedia-song-or-not","owner":"bcc-code","description":"[BCC Media] NN to determine what parts of an audio file are songs and which are speech","archived":false,"fork":false,"pushed_at":"2024-08-27T13:45:47.000Z","size":1136,"stargazers_count":1,"open_issues_count":0,"forks_count":1,"subscribers_count":3,"default_branch":"master","last_synced_at":"2024-08-28T12:57:33.056Z","etag":null,"topics":["bcc-media"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/bcc-code.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}},"created_at":"2023-06-01T13:02:44.000Z","updated_at":"2024-08-27T13:45:50.000Z","dependencies_parsed_at":"2024-08-27T12:49:06.050Z","dependency_job_id":"247a2733-9102-409f-b726-9b07d5f65671","html_url":"https://github.com/bcc-code/bccmedia-song-or-not","commit_stats":null,"previous_names":["bcc-code/bccmedia-song-or-not"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/bcc-code/bccmedia-song-or-not","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bcc-code%2Fbccmedia-song-or-not","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bcc-code%2Fbccmedia-song-or-not/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bcc-code%2Fbccmedia-song-or-not/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bcc-code%2Fbccmedia-song-or-not/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/bcc-code","download_url":"https://codeload.github.com/bcc-code/bccmedia-song-or-not/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bcc-code%2Fbccmedia-song-or-not/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":262471043,"owners_count":23316603,"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":["bcc-media"],"created_at":"2025-06-28T17:37:49.664Z","updated_at":"2025-06-28T17:38:01.001Z","avatar_url":"https://github.com/bcc-code.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Song-Or-Not\n## Summary\n\nThis is the code used to train a neural network with the goal of detecting of parts of a recording\nare speech or song.\n\n## Training data\n\nThe training data used is in forms of MP3 files (not included) and can be placed into the `songs`\nor `speech` folders. Then you can run the `./split.sh` scripts which splits the file into chunks\nwith the specified length. Currently only files with 44100 Hz sample rate are supported\n\n## Dependencies\n\nIncomplete and untested list:\n\n```\nconda install -c apple tensorflow-deps \nconda install tensorflow_io\nconda install torchaudio\n```\n\n## Training\n\nRun `python3 train.py`\n\nThis will produce a `./songornot_trained.pt` file. If you run the script again the file will be replaced\n\n## Inference\n\nAs a sample you can run `./tests/inference_test.py \u003cmodel\u003e \u003caudio file\u003e`.\n\nResults will be similar to this:\n\n```\n/Users/matjaz/meeting.wav\nChunks: 1317\nTotal items: 1317\nsong (15:10): 00:00 - 15:10\nspeech (04:00): 15:10 - 19:10\nsong (03:05): 19:10 - 22:15\nspeech (18:30): 22:15 - 40:45\nsong (04:00): 40:45 - 44:45\nspeech (00:20): 44:45 - 45:05\nsong (00:15): 45:05 - 45:20\nspeech (08:05): 45:20 - 53:25\nsong (03:30): 53:25 - 56:55\nspeech (25:05): 56:55 - 82:00\nsong (01:55): 82:00 - 83:55\nspeech (20:40): 83:55 - 104:35\nsong (03:30): 104:35 - 108:05\n\n```\n\n### Models\n\nThe provided models are provided for demonstration purposes and are (C) 2023 BCC Media STI.\n\n## License \n\nModel files listed here are licensed under [CC BY-NC-ND 4.0](https://creativecommons.org/licenses/by-nc-nd/4.0/) license:\n\n* songornot_2s.pt\n* songornot_5s.pt\n\n\nEverything with the exception of the above list of files is released under the MIT License.\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbcc-code%2Fbccmedia-song-or-not","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fbcc-code%2Fbccmedia-song-or-not","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbcc-code%2Fbccmedia-song-or-not/lists"}