{"id":13862234,"url":"https://github.com/jagilley/autodrummer","last_synced_at":"2025-07-14T11:33:02.532Z","repository":{"id":85659914,"uuid":"561947410","full_name":"jagilley/autodrummer","owner":"jagilley","description":"A text-to-audio model for generating text-conditioned drum beats","archived":false,"fork":false,"pushed_at":"2023-04-25T14:11:16.000Z","size":70450,"stargazers_count":18,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2024-08-05T06:05:28.265Z","etag":null,"topics":["drum-machine","gpt-3","llm","music"],"latest_commit_sha":null,"homepage":"https://huggingface.co/spaces/jspr/autodrummer","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/jagilley.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":"2022-11-04T21:38:42.000Z","updated_at":"2024-05-23T09:09:36.000Z","dependencies_parsed_at":"2024-08-05T06:14:43.251Z","dependency_job_id":null,"html_url":"https://github.com/jagilley/autodrummer","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/jagilley%2Fautodrummer","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jagilley%2Fautodrummer/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jagilley%2Fautodrummer/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jagilley%2Fautodrummer/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/jagilley","download_url":"https://codeload.github.com/jagilley/autodrummer/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":225974360,"owners_count":17553940,"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":["drum-machine","gpt-3","llm","music"],"created_at":"2024-08-05T06:01:40.092Z","updated_at":"2024-11-22T22:30:47.750Z","avatar_url":"https://github.com/jagilley.png","language":"Python","funding_links":[],"categories":["Python"],"sub_categories":[],"readme":"# autodrummer\n**_A text-to-audio model for generating text-conditioned drum beats._**\n\n## how it works\nautodrummer is a transformer model created by converting the MIDI data from Google Magenta's [E-GMD dataset](https://magenta.tensorflow.org/datasets/e-gmd) to a specialized variant of plaintext upon which to train a transformer. This repo covers everything necessary to convert the raw MIDI data from E-GMD into tokens for the transformer.\n\n## installation\n1. Download the [E-GMD dataset](https://magenta.tensorflow.org/datasets/e-gmd) and place it in this repo in a folder named `e-gmd`\n2. `git clone https://github.com/angelfaraldo/pymidifile` _within this repo_ and replace its `quantize.py` with this repo's version of `quantize.py`. _you have to run quantize.py from the autodrummer repo directory, not the pymidifile repo directory, or else you'll get import errors._\n3. run `pip install -r requirements.txt`\n\n## current workflow (to prepare data for your own finetune)\n1. `pymidifile/quantize.py`: quantize the MIDI data in the e-gmd dataset and convert it to matrices representing `(drum_code, hit_time)` pairs\n2. `matrix2text.py`: convert said matrices into plaintext\n3. `df2jsonl.py`: convert dataframe of plaintext to `jsonl` file\n4. *train model here*\n5. `txt2audio.py` **or** `evaluator.py`: convert back from plaintext to audio\n\n## contact\n[Jasper on Twitter](https://twitter.com/0xjasper)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjagilley%2Fautodrummer","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjagilley%2Fautodrummer","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjagilley%2Fautodrummer/lists"}