{"id":19428886,"url":"https://github.com/eleutherai/aria","last_synced_at":"2025-04-24T18:31:35.181Z","repository":{"id":169009069,"uuid":"642937730","full_name":"EleutherAI/aria","owner":"EleutherAI","description":null,"archived":false,"fork":false,"pushed_at":"2024-07-18T13:22:20.000Z","size":427,"stargazers_count":38,"open_issues_count":0,"forks_count":8,"subscribers_count":3,"default_branch":"main","last_synced_at":"2024-08-05T06:05:18.218Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/EleutherAI.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":"2023-05-19T17:34:59.000Z","updated_at":"2024-07-18T13:22:23.000Z","dependencies_parsed_at":"2024-01-24T18:49:05.084Z","dependency_job_id":"1176a3d7-e865-4b51-834b-1873866f321c","html_url":"https://github.com/EleutherAI/aria","commit_stats":null,"previous_names":["eleutherai/music-transformer","eleutherai/aria"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/EleutherAI%2Faria","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/EleutherAI%2Faria/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/EleutherAI%2Faria/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/EleutherAI%2Faria/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/EleutherAI","download_url":"https://codeload.github.com/EleutherAI/aria/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":223961111,"owners_count":17232251,"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":[],"created_at":"2024-11-10T14:17:04.827Z","updated_at":"2024-11-10T14:17:05.473Z","avatar_url":"https://github.com/EleutherAI.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# gpt-aria\n\n[Discord](https://discord.com/invite/zBGx3azzUn)\n\nA repository containing resources for pre-training, fine-tuning, and evaluating musical (MIDI) transformer models.\n\n***Note that this project is under active development***\n\n## Description\n\nThe main goal of the gpt-aria project is to create a suite of powerful pre-trained generative (symbolic) music models. We want to investigate how modern training (pre-training \u0026 fine-tuning) techniques can be used to improve the quality/usefulness of such models. Alongside this we are building various data (MIDI) preprocessing tools, allowing **you** to easily fine-tune our models on your own data.\n\nIf you are new to symbolic music models, a good place to start are the following projects/blogposts by Google Magenta and OpenAI:\n\n- [Music Transformer](https://magenta.tensorflow.org/music-transformer)\n- [MuseNet](https://openai.com/research/musenet)\n\n Long story short: Transformer + MIDI + GPUs = 🎵 x ∞\n\n## Installation\n\nMake sure you are using Python 3.10+. Note that I haven't explicitly developed this project for anything other than Linux. If you are using Windows, things might not work properly. In this case I suggest installing using WSL.\n\n```\ngit clone https://github.com/eleutherai/aria\ncd aria\npip install -e .\n```\n\n## Inference\n\nYou can find preliminary checkpoints at the following locations \n\nFinetuned piano-only checkpoints (improved robustness):\n\n```\nlarge - https://storage.googleapis.com/aria-checkpoints/large-abs-inst.safetensors\n```\n\nPretrained checkpoints:\n\n```\nlarge - https://storage.googleapis.com/aria-checkpoints/large-abs-pt.bin\nmedium - https://storage.googleapis.com/aria-checkpoints/medium-abs-pt.bin\nsmall - https://storage.googleapis.com/aria-checkpoints/small-abs-pt.bin\n```\n\nYou can then sample using the cli:\n\n```\naria sample \\\n    -m large \\\n    -c \u003cpath-to-checkpoint\u003e \\\n    -p \u003cpath-to-midifile\u003e \\\n    -var \u003cnum-variations-to-generate\u003e \\\n    -trunc \u003cseconds-in-to-truncate-prompt\u003e \\\n    -l \u003cnumber-of-tokens-to-generate\u003e \\\n    -temp 0.95 \\\n    -e\n```\n\nYou can use `aria sample -h` to see a full list of options. If you wish to sample from a pretrained checkpoint, please use the `-pt` flag.\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Feleutherai%2Faria","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Feleutherai%2Faria","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Feleutherai%2Faria/lists"}