{"id":19428900,"url":"https://github.com/eleutherai/aria-amt","last_synced_at":"2025-10-04T15:44:18.409Z","repository":{"id":222518272,"uuid":"756364809","full_name":"EleutherAI/aria-amt","owner":"EleutherAI","description":"Efficient and robust implementation of seq-to-seq automatic piano transcription.","archived":false,"fork":false,"pushed_at":"2025-07-09T13:07:00.000Z","size":96237,"stargazers_count":50,"open_issues_count":0,"forks_count":9,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-07-09T14:24:23.636Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","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,"zenodo":null}},"created_at":"2024-02-12T14:24:01.000Z","updated_at":"2025-07-09T13:07:05.000Z","dependencies_parsed_at":"2025-07-09T14:34:34.937Z","dependency_job_id":null,"html_url":"https://github.com/EleutherAI/aria-amt","commit_stats":null,"previous_names":["eleutherai/aria-amt"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/EleutherAI/aria-amt","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/EleutherAI%2Faria-amt","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/EleutherAI%2Faria-amt/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/EleutherAI%2Faria-amt/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/EleutherAI%2Faria-amt/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/EleutherAI","download_url":"https://codeload.github.com/EleutherAI/aria-amt/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/EleutherAI%2Faria-amt/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":278335448,"owners_count":25970086,"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","status":"online","status_checked_at":"2025-10-04T02:00:05.491Z","response_time":63,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"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":"2024-11-10T14:17:06.395Z","updated_at":"2025-10-04T15:44:18.376Z","avatar_url":"https://github.com/EleutherAI.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# aria-amt\n\nEfficient and robust implementation of seq-to-seq automatic piano transcription.\n\n## Install \n\nRequires Python 3.11\n\n```\ngit clone https://github.com/EleutherAI/aria-amt.git\ncd aria-amt\npip install -e .\n```\n\nDownload the preliminary model weights:\n\nPiano (v1)\n\n```\nwget https://storage.googleapis.com/aria-checkpoints/amt/piano-medium-double-1.0.safetensors\n```\n\n## Usage\n\nYou can download mp3s from youtube using [yt-dlp](https://github.com/yt-dlp/yt-dlp):\n\n```\nyt-dlp --audio-format mp3 --extract-audio --no-playlist --audio-quality 0 \u003cyoutube-link\u003e -o \u003csave-path\u003e\n```\n\nYou can then transcribe using the cli: \n\n```\naria-amt transcribe \\\n    medium-double \\\n    \u003cpath-to-checkpoint\u003e \\\n    -load_path \u003cpath-to-audio\u003e \\\n    -save_dir \u003cpath-to-save-dir\u003e \\\n    -bs 1 \\\n    -compile\n```\n\nIf you want to do batch transcription, use the `-load_dir` flag and adjust `-bs` accordingly. Compiling and may take some time, but provides a significant speedup. Quantizing (`-q8` flag) further speeds up inference when the `-compile` flag is also used.\n\nNOTE: Int8 quantization is only supported on GPUs that support BF16.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Feleutherai%2Faria-amt","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Feleutherai%2Faria-amt","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Feleutherai%2Faria-amt/lists"}