{"id":15687124,"url":"https://github.com/robsdedude/melody-composer","last_synced_at":"2025-06-25T20:06:01.429Z","repository":{"id":113257883,"uuid":"71576426","full_name":"robsdedude/melody-composer","owner":"robsdedude","description":"Using higher Order Markov Modells and Clustering to compose melodies similar to a training data set","archived":false,"fork":false,"pushed_at":"2017-05-17T16:26:36.000Z","size":37,"stargazers_count":10,"open_issues_count":0,"forks_count":1,"subscribers_count":3,"default_branch":"public","last_synced_at":"2025-06-21T02:58:40.164Z","etag":null,"topics":["ai","artificial-intelligence","clustering","compose-melodies","computational-creativity","content-generation"],"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/robsdedude.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE.md","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":"2016-10-21T15:13:04.000Z","updated_at":"2025-01-27T15:29:43.000Z","dependencies_parsed_at":"2023-03-29T19:47:35.330Z","dependency_job_id":null,"html_url":"https://github.com/robsdedude/melody-composer","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/robsdedude/melody-composer","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/robsdedude%2Fmelody-composer","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/robsdedude%2Fmelody-composer/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/robsdedude%2Fmelody-composer/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/robsdedude%2Fmelody-composer/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/robsdedude","download_url":"https://codeload.github.com/robsdedude/melody-composer/tar.gz/refs/heads/public","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/robsdedude%2Fmelody-composer/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":261945365,"owners_count":23234236,"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":["ai","artificial-intelligence","clustering","compose-melodies","computational-creativity","content-generation"],"created_at":"2024-10-03T17:43:51.451Z","updated_at":"2025-06-25T20:06:00.977Z","avatar_url":"https://github.com/robsdedude.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"This program is part of my bachelor thesis which can be found on\n[arXiv](https://arxiv.org/pdf/1612.09212.pdf). It's a machine learning algorithm\nthat generates monophonic melodies similar to those of a phrase annotated\ndata-set. In- and output are midi files (i.e. machine readable music).\n\nSetup\n=====\nUse virtualenv\n--------------\n\n    virtualenv venv\n    source venv/bin/activate\n    export LC_ALL=C\n    pip install -r requirements.txt\n\nTroubleshooting\n---------------\nOn Ubuntu based systems it can happen, that there are header files missing. Do:\n`sudo apt-get install liblapack-dev libblas-dev`\nIt can also happen, that you need to install a fortran compiler. Do:\n`sudo install gfortran`\nAfter fixing these things re-run `pip install -r requirements.txt` each time.\n\nTrainings Data\n-------------\nDownload the [MTC-FS data set](http://www.liederenbank.nl/mtc/collections.php)\nand unzip it into the folder `MTC-FS-1.0`\n\nThen run the preporcessing\n\n    mkdir -p MTC-FS-1.0/good_midi  # create folder to put pre-processed midi files in\n    source venv/bin/activate       # activate virtualenv\n    python preprocess.py           # run preprocessing\n    deactivate                     # deactivate virtualenv\n\n\nRun the program\n===============\nStart the virtual environment with\n`source venv/bin/activate`\nTo general start the program go to this directory and run\n`python main.py`\nMore information: `python2 main.py --help`\n\n\nOther things\n============\nTo see how the clustering is working have a look at main() in contour.py\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Frobsdedude%2Fmelody-composer","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Frobsdedude%2Fmelody-composer","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Frobsdedude%2Fmelody-composer/lists"}