{"id":16114872,"url":"https://github.com/solarliner/latentwt","last_synced_at":"2026-03-06T02:06:06.266Z","repository":{"id":80989181,"uuid":"537626848","full_name":"SolarLiner/latentwt","owner":"SolarLiner","description":"Generate wavetables, with AI.","archived":false,"fork":false,"pushed_at":"2022-09-20T15:50:58.000Z","size":6717,"stargazers_count":8,"open_issues_count":0,"forks_count":0,"subscribers_count":4,"default_branch":"main","last_synced_at":"2025-02-12T13:55:23.950Z","etag":null,"topics":["autoencoder","deep-learning","wavetables"],"latest_commit_sha":null,"homepage":"https://latentwt.netlify.app","language":"Vue","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/SolarLiner.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":"2022-09-16T21:38:18.000Z","updated_at":"2024-10-06T10:24:04.000Z","dependencies_parsed_at":null,"dependency_job_id":"34b78df1-e77b-4ba9-848e-14d1dfdd9f64","html_url":"https://github.com/SolarLiner/latentwt","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/SolarLiner%2Flatentwt","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SolarLiner%2Flatentwt/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SolarLiner%2Flatentwt/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SolarLiner%2Flatentwt/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/SolarLiner","download_url":"https://codeload.github.com/SolarLiner/latentwt/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247451776,"owners_count":20940967,"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":["autoencoder","deep-learning","wavetables"],"created_at":"2024-10-09T20:16:15.239Z","updated_at":"2026-03-06T02:06:01.198Z","avatar_url":"https://github.com/SolarLiner.png","language":"Vue","funding_links":[],"categories":[],"sub_categories":[],"readme":"# [Latent Wavetables](https://latentwt.netlify.app)\n\nAn autoencoder for wavetables\n\nThis project aims to create a latent space of wavetables, such that exploring them is as easy as hovering over a 2D graph. You can generate wavetable sequences from dragging around the graph.\n\nThe model is provided at `public/latentwt.onnx` in ONNX format, and runs in the browser.\n\n## Wavetable licences\n\nThe wavetables from the web frontend are from [WaveEdit Online](https://waveeditonline.com/), which are CC0 - any wavetable generated from this tool is also CC0.\n\n## Training\n\nTo train the model, you'll need a corpus of wavetable sequences to feed to the model. This project feeds from the [WaveEdit Online](https://waveeditonline.com/), but should be flexible enough to be trained on any other wavetable sequences that you may have.\n\nThe `model.py` is a runnable script with a CLI interface that allows you to train and save the model with your own wavetables.\n\n```\nusage: model.py [-h] -w WAVETABLES [-W WIDTH] [-d {cuda,cpu}] [-e EPOCHS] output\n\npositional arguments:\n  output                Output ONNX model\n\noptions:\n  -h, --help            show this help message and exit\n  -w WAVETABLES, --wavetables WAVETABLES\n                        Path to the folder containing wavetable sequence wav files \n  -W WIDTH, --width WIDTH\n                        Wavetable width (default: 256)\n  -d {cuda,cpu}, --device {cuda,cpu}\n                        Use CPU/GPU to compute the model (default is detected) \n  -e EPOCHS, --epochs EPOCHS\n                        Number of training epochs (default: 50)\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsolarliner%2Flatentwt","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsolarliner%2Flatentwt","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsolarliner%2Flatentwt/lists"}