{"id":49493429,"url":"https://github.com/tsukamotoshio/sumisoraomr","last_synced_at":"2026-05-01T08:01:51.379Z","repository":{"id":348735906,"uuid":"1199408318","full_name":"Tsukamotoshio/SumisoraOMR","owner":"Tsukamotoshio","description":"An OMR to Jianpu (numbered musical notation) converter/一个五线谱转简谱工具","archived":false,"fork":false,"pushed_at":"2026-04-28T10:05:42.000Z","size":2496,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-04-28T10:34:36.603Z","etag":null,"topics":["jianpu","midi","music-notation","musicxml","omr","python"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"agpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Tsukamotoshio.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,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2026-04-02T10:17:09.000Z","updated_at":"2026-04-28T10:05:46.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/Tsukamotoshio/SumisoraOMR","commit_stats":null,"previous_names":["tsukamotoshio/omr-to-jianpu-conversion-tool","tsukamotoshio/sumisoraomr"],"tags_count":11,"template":false,"template_full_name":null,"purl":"pkg:github/Tsukamotoshio/SumisoraOMR","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Tsukamotoshio%2FSumisoraOMR","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Tsukamotoshio%2FSumisoraOMR/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Tsukamotoshio%2FSumisoraOMR/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Tsukamotoshio%2FSumisoraOMR/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Tsukamotoshio","download_url":"https://codeload.github.com/Tsukamotoshio/SumisoraOMR/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Tsukamotoshio%2FSumisoraOMR/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32489164,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-30T13:12:12.517Z","status":"online","status_checked_at":"2026-05-01T02:00:05.856Z","response_time":64,"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":["jianpu","midi","music-notation","musicxml","omr","python"],"created_at":"2026-05-01T08:01:46.383Z","updated_at":"2026-05-01T08:01:51.363Z","avatar_url":"https://github.com/Tsukamotoshio.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# SumisoraOMR\n\n\u003e Batch-convert Western staff notation (PDF / PNG / JPG) to Jianpu (numbered musical notation) PDFs, with optional MIDI output.\n\n[![License: AGPL-3.0](https://img.shields.io/badge/License-AGPL%20v3-blue.svg)](LICENSE)\n[![Platform: Windows](https://img.shields.io/badge/Platform-Windows-lightgrey.svg)]()\n[![Python 3.10+](https://img.shields.io/badge/Python-3.10%2B-blue.svg)]()\n\n**[中文说明 →](README.zh.md)**\n\n---\n\n## Features\n\n- Batch-processes files from the `Input` folder; results land in `Output`\n- Skips already-converted files automatically (hash-based deduplication)\n- Optional MIDI generation alongside each Jianpu PDF\n- Handles Chinese, Japanese, and other non-ASCII filenames\n- Optional super-resolution upscaling to improve recognition on low-quality scans\n\n---\n\n## Engines\n\n### OMR (Optical Music Recognition)\n\n| Engine | Best for | Notes |\n|--------|----------|-------|\n| **Audiveris** | Digital PDFs | Reads PDFs exported from notation software (MuseScore, Sibelius, Finale, etc.). Fast and accurate on clean vector files — no GPU needed. |\n| **Homr** | Scans \u0026 photos | AI-powered engine for PNG/JPG images of printed or photographed sheet music. Handles noise and real-world imperfections; GPU-accelerated (CUDA / DirectML). |\n\n\u003e Auto mode picks **Audiveris** for PDF files and **Homr** for images (PNG/JPG) automatically.\n\n### Super-Resolution (optional pre-processing)\n\n| Engine | Notes |\n|--------|-------|\n| **Real-ESRGAN** | Default SR engine; higher-fidelity upscaling; anime-optimized models; Vulkan GPU-accelerated |\n| **waifu2x-ncnn-vulkan** | Alternative SR engine; Vulkan GPU-accelerated |\n\n---\n\n## Usage\n\n### Conversion\n\n1. Drop your staff notation files (`.pdf`, `.png`, `.jpg`) into the `Input`\n   folder, or drag them directly into the file sidebar.\n2. Launch the app — double-click the **SumisoraOMR** shortcut or run\n   `SumisoraOMR.exe`.\n3. In the file sidebar, check the files you want to convert.\n4. Choose an OMR engine (or leave it on **Auto**), then click **Start Conversion**.\n5. Confirm options in the dialog (MIDI generation, skip duplicates) and\n   click **Start Conversion**.\n6. Converted Jianpu PDFs appear in the `Output` folder.\n\n### Jianpu Preview\n\nAfter conversion, switch to the **Jianpu Preview** tab to browse all\ngenerated PDFs. Check files using the checkboxes, then click the export\nbutton in the sidebar header to copy them to a folder of your choice.\nClick **Edit Jianpu** in the top bar to open the currently previewed file\nin the editor.\n\n### Jianpu Editor\n\nThe editor lets you inspect and manually correct `.jianpu.txt` source files.\nThe left pane shows the original score image for reference; the right pane\ncontains editable Jianpu text. After editing, click **Regenerate PDF** to\nrebuild the output.\n\n### Transposer\n\nThe transposer reads a MusicXML score from `xml-scores/` and renders it in\na different key. Three modes are available:\n\n- **By semitone** — enter an exact semitone offset.\n- **By interval** — choose a named interval (perfect 4th, major 3rd, etc.)\n  and direction.\n- **Diatonic** — shift notes by scale degree within the current key.\n\nSettings auto-preview on any change. The result can be exported as a Jianpu\nPDF or a staff-notation PDF.\n\n---\n\n## Running from Source\n\n**Prerequisites**\n\n- Python 3.10+\n- JDK 17+ on `PATH` (required only for PDF recognition via Audiveris)\n- The following runtime directories alongside the repo root:\n\n  | Directory | Purpose |\n  |-----------|---------|\n  | `omr_engine/audiveris/` | Audiveris OMR engine — used for PDF inputs |\n  | `lilypond-2.24.4/` | LilyPond engraving engine |\n  | `jdk/` | Java runtime for Audiveris |\n  | `omr_engine/homr/` | Homr deep-learning OMR engine — used for PNG/JPG inputs |\n  | `waifu2x-ncnn-vulkan/` *(optional)* | waifu2x SR binary |\n  | `realesrgan-runtime/` *(optional)* | Real-ESRGAN binary and models |\n\n**Install dependencies**\n\n```bash\npip install -r requirements.txt\n```\n\n**Run**\n\n```bash\npython app.py\n```\n\nFor hot-reload during development:\n\n```bash\nflet run app.py\n```\n\n---\n\n## Directory Layout\n\n```\nInput/                   # Drop source files here\nOutput/                  # Converted Jianpu PDFs and MIDIs\neditor-workspace/        # Intermediate .jianpu.txt files for manual editing\nxml-scores/              # MusicXML archives (used by the transposer)\nlogs/                    # Runtime logs\nTHIRD_PARTY_NOTICES.md   # Third-party component licenses\n```\n\n---\n\n## Known Limitations\n\n- **Recognition accuracy** depends heavily on scan quality. Blurry or complex scores may produce wrong or missing notes.\n- **Polyphony** — scores with many voices or dense chords may retain only the main melody.\n- **No lyrics** — only note data is exported.\n- **Processing speed** — Homr processes images in seconds; Audiveris startup is slow and multi-page PDFs can take several minutes.\n- **Edge cases** — uncommon time signatures or mid-piece key changes may yield inaccurate results.\n\n---\n\n## Attribution\n\nIntegration, scripting, feature development, and packaging by **Tsukamotoshio**.\n\nWhen redistributing, please retain this notice and `THIRD_PARTY_NOTICES.md` to distinguish:\n\n- **Integration \u0026 packaging**: Tsukamotoshio\n- **Third-party component copyrights \u0026 licenses**: remain with their respective authors (see `THIRD_PARTY_NOTICES.md`)\n\n---\n\n## License\n\nThis project is licensed under the **GNU Affero General Public License v3.0 (AGPL-3.0)** — see the [`LICENSE`](LICENSE) file for details.\n\nThis tool bundles third-party components (Audiveris, LilyPond, music21, waifu2x-ncnn-vulkan, Real-ESRGAN, and others). Their respective licenses are listed in [`THIRD_PARTY_NOTICES.md`](THIRD_PARTY_NOTICES.md).\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftsukamotoshio%2Fsumisoraomr","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ftsukamotoshio%2Fsumisoraomr","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftsukamotoshio%2Fsumisoraomr/lists"}