{"id":18349037,"url":"https://github.com/icoxfog417/magenta_session","last_synced_at":"2025-04-06T09:31:58.501Z","repository":{"id":145819284,"uuid":"84801148","full_name":"icoxfog417/magenta_session","owner":"icoxfog417","description":":musical_keyboard: Music Session with Google Magenta","archived":false,"fork":false,"pushed_at":"2019-10-27T12:50:41.000Z","size":20434,"stargazers_count":81,"open_issues_count":1,"forks_count":134,"subscribers_count":6,"default_branch":"master","last_synced_at":"2025-03-21T21:22:01.324Z","etag":null,"topics":["machine-learning","music","webaudio-api"],"latest_commit_sha":null,"homepage":"http://magenta-session.herokuapp.com/","language":"JavaScript","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/icoxfog417.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}},"created_at":"2017-03-13T08:21:44.000Z","updated_at":"2024-01-04T16:12:16.000Z","dependencies_parsed_at":null,"dependency_job_id":"1024cc79-6b86-4960-b643-5c463b92c110","html_url":"https://github.com/icoxfog417/magenta_session","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/icoxfog417%2Fmagenta_session","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/icoxfog417%2Fmagenta_session/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/icoxfog417%2Fmagenta_session/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/icoxfog417%2Fmagenta_session/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/icoxfog417","download_url":"https://codeload.github.com/icoxfog417/magenta_session/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247463745,"owners_count":20942935,"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":["machine-learning","music","webaudio-api"],"created_at":"2024-11-05T21:20:12.080Z","updated_at":"2025-04-06T09:31:55.989Z","avatar_url":"https://github.com/icoxfog417.png","language":"JavaScript","readme":"# magenta session\r\n\r\nThe code to session with [magenta](https://github.com/tensorflow/magenta).  \r\nDo you have any MIDI instrument? If then, you can do call \u0026 response with magenta!  \r\n(You don't have such instruments? Of course, you can play this without it!)\r\n\r\n**You can see the sample play from here**\r\n\r\n* [Playing Video](https://youtu.be/owOI2CMavoE)\r\n* [Recorded Session](https://soundcloud.com/icoxfog417/magenta-sessioned-track)\r\n\r\n(Sorry about my poor keyboard play!)\r\n\r\nYou can deploy your own Magenta Session to Heroku by following button.\r\n\r\n[![Deploy](https://www.herokucdn.com/deploy/button.svg)](https://heroku.com/deploy)\r\n\r\n## Architecture\r\n\r\n![architecture.PNG](./docs/architecture.PNG)\r\n\r\nThe model is ported from [ai-duet](https://github.com/googlecreativelab/aiexperiments-ai-duet).\r\n\r\n## How to use\r\n\r\n1. Install `magenta_session`\r\n2. Run `python server/server.py`\r\n3. Access the [Server(localhost:8080)](http://localhost:8080)\r\n4. Session Now! (please refer following image).\r\n\r\n![gui.PNG](./docs/gui.PNG)\r\n\r\n### Additional Usage\r\n\r\n* [Train your own model](https://github.com/icoxfog417/magenta_session/tree/master/scripts)\r\n* [Session with your own model](https://github.com/icoxfog417/magenta_session/tree/master/server)\r\n\r\n## Install \r\n\r\n`magenta_session` depends on TensorFlow and magenta.  \r\nPlease refer [magenta installation guide](https://github.com/tensorflow/magenta#installation).\r\n\r\n### Miniconda\r\n\r\nInstall the [Miniconda](https://conda.io/miniconda.html) (Miniconda3 is also ok), and create the Magenta environment.\r\n\r\n```\r\nconda create -n magenta numpy scipy scikit-learn matplotlib jupyter pyyaml\r\n```\r\n\r\n(If you use Miniconda3, please set `python=2.7` additionaly when create magenta environment. Because Magenta only works on Python2!)\r\n\r\nThen activate the `magenta` environment, and install the dependencies.\r\n\r\n```\r\nsource activate magenta\r\npip install -r requirements.txt\r\n```\r\n\r\n**CAUTION**\r\n\r\n* `pyenv` user will have the trouble with `source activate magenta`. To avoid this, configure your environment by `pyenv versions`, and use `pyenv local` to set the magenta environment that you created.\r\n* `TensorFlow` does not support Windows except the Python3.5 version (and Magenta does not work on Python3.5!). So If you want to run it on Windows, you have to use [bash on Windows](https://msdn.microsoft.com/en-us/commandline/wsl/install_guide).\r\n\r\n\r\n### Docker\r\n\r\nDocker is an open-source containerization software which simplifies installation across various OSes.Once you have Docker installed, you can just run:\r\n\r\n```bash\r\n$ docker run -it --rm -p 80:8080 asashiho/magenta_session\r\n```\r\n\r\nIf you want to build DockerImage yourself, you can just run:\r\n\r\n```bash\r\n$ docker build -t magenta_session .\r\n$ docker run -it --rm -p 80:8080 magenta_session\r\n```\r\n**Tips!** Docker to automatically clean up the container and remove the file system when the container exits, you can add the `--rm`\r\n\r\nYou can now play with `magenta_session` at `http://\u003cdocker-server-ipaddress\u003e/`.\r\n\r\nSession Now and Enjoy Music!\r\n\r\n## Dependencies\r\n\r\nPython\r\n\r\n* [magenta](https://github.com/tensorflow/magenta)\r\n* [TensorFlow](https://github.com/tensorflow/tensorflow)\r\n* [Flask](https://github.com/pallets/flask)\r\n\r\nJavaScript\r\n\r\n* [Tone.js](https://github.com/Tonejs/Tone.js)\r\n* [MidiConvert](https://github.com/Tonejs/MidiConvert)\r\n* [jQuery](https://github.com/jquery/jquery) (It's enough to such a simple application)\r\n\r\nCSS\r\n\r\n* [Bulma](http://bulma.io/)\r\n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ficoxfog417%2Fmagenta_session","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ficoxfog417%2Fmagenta_session","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ficoxfog417%2Fmagenta_session/lists"}