{"id":23147597,"url":"https://github.com/harrytwigg/feeg3003","last_synced_at":"2026-04-19T01:02:06.912Z","repository":{"id":162176659,"uuid":"479444158","full_name":"harrytwigg/FEEG3003","owner":"harrytwigg","description":"Using DDSP to learn and synthesize singing with modifiable latent space parameters","archived":false,"fork":false,"pushed_at":"2022-06-09T10:26:00.000Z","size":68967,"stargazers_count":2,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-02-09T23:26:58.732Z","etag":null,"topics":["ddsp","machine-learning","ml"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","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/harrytwigg.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":"2022-04-08T15:28:54.000Z","updated_at":"2024-11-14T09:53:39.000Z","dependencies_parsed_at":null,"dependency_job_id":"4b2342aa-869d-4bc6-b267-0fa1a1b3a6bf","html_url":"https://github.com/harrytwigg/FEEG3003","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/harrytwigg%2FFEEG3003","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/harrytwigg%2FFEEG3003/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/harrytwigg%2FFEEG3003/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/harrytwigg%2FFEEG3003/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/harrytwigg","download_url":"https://codeload.github.com/harrytwigg/FEEG3003/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247188504,"owners_count":20898529,"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":["ddsp","machine-learning","ml"],"created_at":"2024-12-17T16:52:51.369Z","updated_at":"2026-04-19T01:02:06.874Z","avatar_url":"https://github.com/harrytwigg.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Using DDSP to learn and synthesize singing with adjustable latent space parameters\n\nThesis project by Harry Twigg at the Univeristy of Southampton.\n\n## Getting Started\n\nOther reports or can be seen in their respective folders.\n\nResults can be found in the folder `results`.\n\n## Project Code\n\nAll experimental research can be seen in the folder `vocal_ddsp`. This contains pre-processing, training and evaluation scripts.\n\nDataset preparation, training and inferencing was done in Google Colab, the notebooks of which are available in the `vocal_ddsp/notebooks` folder.\n\nRequired gin configs are available in the `vocal_ddsp/gin` folder.\n\nTraining models and datasets:\n\nhttps://drive.google.com/drive/folders/1CWdEco9tJ5fNBZfvLGqbSrfdYQ6pLZsz?usp=sharing\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fharrytwigg%2Ffeeg3003","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fharrytwigg%2Ffeeg3003","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fharrytwigg%2Ffeeg3003/lists"}