{"id":21702393,"url":"https://github.com/basharovv/whatsound","last_synced_at":"2025-07-22T04:31:47.619Z","repository":{"id":92684349,"uuid":"43493440","full_name":"basharovV/whatsound","owner":"basharovV","description":"Neural network for classifying audio samples into categories. This was my BSc final year project.","archived":false,"fork":false,"pushed_at":"2018-12-02T23:13:26.000Z","size":31011,"stargazers_count":3,"open_issues_count":0,"forks_count":0,"subscribers_count":3,"default_branch":"master","last_synced_at":"2025-07-13T07:37:11.574Z","etag":null,"topics":["audio-processing","classification","essentia","extraction","music","neural-network","pybrain"],"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/basharovV.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":"2015-10-01T11:47:07.000Z","updated_at":"2025-04-02T00:55:50.000Z","dependencies_parsed_at":null,"dependency_job_id":"ef3b173d-96c4-4acf-a111-21e790cc4604","html_url":"https://github.com/basharovV/whatsound","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/basharovV/whatsound","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/basharovV%2Fwhatsound","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/basharovV%2Fwhatsound/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/basharovV%2Fwhatsound/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/basharovV%2Fwhatsound/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/basharovV","download_url":"https://codeload.github.com/basharovV/whatsound/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/basharovV%2Fwhatsound/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":266427789,"owners_count":23926873,"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":"2025-07-22T02:00:09.085Z","response_time":66,"last_error":null,"robots_txt_status":null,"robots_txt_updated_at":null,"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":["audio-processing","classification","essentia","extraction","music","neural-network","pybrain"],"created_at":"2024-11-25T21:15:11.931Z","updated_at":"2025-07-22T04:31:47.279Z","avatar_url":"https://github.com/basharovV.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# whatsound - a Python ML toolkit for audio classification\n\n*whatsound* is a toolkit for training, and testing audio classification using a neural network.\n- Music\n- Speech\n- Ambient/Noise\n- Silence\n\nThis toolkit uses [Essentia](http://essentia.upf.edu/documentation/) for audio feature extraction, and [PyBrain](http://pybrain.org/) for the use of a backpropagation neural network for the training and testing of classification.\n\n## How it works\n\n### WS_classify.py\n\nThis is the toolkit for classification, which exposes the main classification functionality.\n\n\n## Source modules\n\nThe project is split into modules fit for different purposes. \n\n### /core\n\nThese modules are needed for audio training and classification.\n\n#### WS_extractor.py\n\nExtracts audio features from a stream. The [Essentia](http://essentia.upf.edu/documentation/) library is used for audio analysis.\nThe features which are used for extraction are:\n- MFCC\n- Zero crossing rate\n- Key strength\n- Spectral Flux\n- Pitch strength\n- LPC\n\n#### WS_utils.py\n\nUtility functions\n\n#### WS_global_data.py\n\nThese are global parameters - settings for the neural net, training parameters, audio settings and classifier types.\n\n#### WS_network.py\n\nThis module allows training and testing of a data set, with optional the following parameters:\n- `weights` : the path to a PyBrain weights XML file\n- `dataset`: the path to a directory containing audio samples split by class\n- `split`: the ratio with which to split the data set between training/testing\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbasharovv%2Fwhatsound","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fbasharovv%2Fwhatsound","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbasharovv%2Fwhatsound/lists"}