{"id":15159938,"url":"https://github.com/fabiogra/moseca","last_synced_at":"2025-04-06T02:09:33.990Z","repository":{"id":165252403,"uuid":"607384714","full_name":"fabiogra/moseca","owner":"fabiogra","description":"A Streamilt web app for music source separation \u0026 karaoke","archived":false,"fork":false,"pushed_at":"2024-07-01T15:13:51.000Z","size":12034,"stargazers_count":312,"open_issues_count":8,"forks_count":39,"subscribers_count":6,"default_branch":"main","last_synced_at":"2025-03-30T01:06:09.046Z","etag":null,"topics":["audio-processing","demucs","huggingface","music-separation","streamlit","vocal-remover"],"latest_commit_sha":null,"homepage":"https://fabiogra.com/moseca","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/fabiogra.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":"2023-02-27T21:47:25.000Z","updated_at":"2025-03-24T13:32:13.000Z","dependencies_parsed_at":"2023-11-11T13:42:04.834Z","dependency_job_id":"fd166a50-5b4b-41c3-b399-dd80566d0a9e","html_url":"https://github.com/fabiogra/moseca","commit_stats":{"total_commits":91,"total_committers":5,"mean_commits":18.2,"dds":"0.43956043956043955","last_synced_commit":"2379df2dd27171cc3376868b97eb015bc99454fd"},"previous_names":["fabiogra/moseca","fabiogra/st-music-splitter"],"tags_count":1,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/fabiogra%2Fmoseca","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/fabiogra%2Fmoseca/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/fabiogra%2Fmoseca/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/fabiogra%2Fmoseca/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/fabiogra","download_url":"https://codeload.github.com/fabiogra/moseca/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247423515,"owners_count":20936626,"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":["audio-processing","demucs","huggingface","music-separation","streamlit","vocal-remover"],"created_at":"2024-09-26T22:02:30.822Z","updated_at":"2025-04-06T02:09:33.965Z","avatar_url":"https://github.com/fabiogra.png","language":"Python","funding_links":["https://www.buymeacoffee.com/fabiogra"],"categories":["others"],"sub_categories":[],"readme":"---\ntitle: Moseca\nemoji: 🎤🎸🥁🎹\ncolorFrom: yellow\ncolorTo: purple\nsdk: docker\napp_port: 7860\nmodels: [\"https://huggingface.co/fabiogra/baseline_vocal_remover\"]\ntags: [\"audio\", \"music\", \"vocal-removal\", \"karaoke\", \"music-separation\", \"music-source-separation\"]\npinned: true\n---\n\n\u003ch2 align=\"center\"\u003eMoseca - Music Source Separation \u0026 Karaoke\u003c/h1\u003e\n\u003cp align=\"center\"\u003e\n    \u003ca href=\"https://colab.research.google.com/drive/1ODoK3VXajprNbskqy7G8P1h-Zom92TMA?usp=sharing\"\u003e\n        \u003cimg src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"\u003e\n    \u003c/a\u003e\n    \u003ca href=\"https://huggingface.co/spaces/fabiogra/moseca\"\u003e\n        \u003cimg src=\"https://img.shields.io/badge/🤗%20Hugging%20Face-Spaces-blue\" alt=\"Hugging Face Spaces\"\u003e\n    \u003c/a\u003e\n    \u003ca href=\"https://huggingface.co/spaces/fabiogra/moseca/discussions?docker=true\"\u003e\n        \u003cimg src=\"https://img.shields.io/badge/-Docker%20Image-blue?logo=docker\u0026labelColor=white\" alt=\"Docker\"\u003e\n    \u003c/a\u003e\n    \u003ca href=\"https://www.buymeacoffee.com/fabiogra\"\u003e\n        \u003cimg src=\"https://img.shields.io/badge/Buy%20me%20a%20coffee--yellow.svg?logo=buy-me-a-coffee\u0026logoColor=orange\u0026style=social\" alt=\"Buy me a coffee\"\u003e\n    \u003c/a\u003e\n\u003c/p\u003e\n\n---\n\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"https://i.imgur.com/QoSd3Fg.gif\" alt=\"Demo Moseca\"/\u003e\n\u003c/p\u003e\n\u003cp align=\"center\"\u003e\n    \u003ca href=\"https://www.producthunt.com/posts/moseca?utm_source=badge-featured\u0026utm_medium=badge\u0026utm_souce=badge-moseca\" target=\"_blank\"\u003e\n        \u003cimg src=\"https://api.producthunt.com/widgets/embed-image/v1/featured.svg?post_id=415833\u0026theme=light\" alt=\"Moseca - Extract vocals and instrument from any song | Product Hunt\" width=\"250\" height=\"54\" /\u003e\n    \u003c/a\u003e\n\u003c/p\u003e\n\n\n- [Setup](#setup)\n  - [Local environment](#local-environment)\n  - [Docker](#docker)\n  - [(Optional) Preprocess samples](#optional-preprocess-samples)\n- [About](#about)\n  - [High-Quality Stem Separation](#high-quality-stem-separation)\n  - [Advanced AI Algorithms](#advanced-ai-algorithms)\n  - [Karaoke Fun](#karaoke-fun)\n  - [Easy Deployment](#easy-deployment)\n  - [Open-Source and Free](#open-source-and-free)\n  - [Support](#support)\n- [FAQs](#faqs)\n  - [What is Moseca?](#what-is-moseca)\n  - [Are there any limitations?](#are-there-any-limitations)\n  - [How does Moseca work?](#how-does-moseca-work)\n  - [How do I use Moseca?](#how-do-i-use-moseca)\n  - [Where can I find the code for Moseca?](#where-can-i-find-the-code-for-moseca)\n  - [How can I get in touch with you?](#how-can-i-get-in-touch-with-you)\n- [Disclaimer](#disclaimer)\n\n---\n\n\n## Setup\n### Local environment\nCreate a new environment with Python 3.10 and install the requirements:\n```bash\npip install -r requirements.txt\n```\nset the `PYTHONPATH` to the root folder:\n```bash\nexport PYTHONPATH=path/to/moseca\n```\ndownload the vocal remover model:\n```bash\nwget --progress=bar:force:noscroll https://huggingface.co/fabiogra/baseline_vocal_remover/resolve/main/baseline.pth\n```\nthen run the app with:\n```bash\nstreamlit run app/header.py\n```\n### Docker\nYou can also run the app with Docker:\n```bash\ndocker build -t moseca .\ndocker run -it --rm -p 7860:7860 $(DOCKER_IMAGE_NAME)\n```\nor pull the image from Hugging Face Spaces:\n```bash\ndocker run -it -p 7860:7860 --platform=linux/amd64 \\\n\tregistry.hf.space/fabiogra-moseca:latest\n```\n\nYou can set the following environment variables to limit the resources used by the app:\n- ENV_LIMITATION=true\n- LIMIT_CPU=true\n\n### (Optional) Preprocess samples\nIf you want to preprocess the samples used in the demo, you need to set the env variable `PREPARE_SAMPLES=true` as a secret (create the file `run/secrets/PREPARE_SAMPLES` with `true` value inside).\n\nIf you run locally you also need to move the files inside `scripts` to the root folder and run `prepare_samples.sh`.\n```\ncp scripts/ .\nchmod +x prepare_samples.sh\npython prepare_samples.sh\n```\n\n---\n## About\n\nWelcome to Moseca, your personal web application designed to redefine your music experience.\nWhether you're a musician looking to remix your favorite songs, a karaoke\nenthusiast, or a music lover wanting to dive deeper into your favorite tracks,\nMoseca is for you.\n\n\u003cbr\u003e\n\n### High-Quality Stem Separation\n\n\u003cimg title=\"High-Quality Stem Separation\" src=\"https://i.imgur.com/l7H8YWL.png\" width=\"250\" \u003e\u003c/img\u003e\n\n\n\u003cbr\u003e\n\nSeparate up to 6 stems including 🗣voice, 🥁drums, 🔉bass, 🎸guitar,\n🎹piano (beta), and 🎶 others.\n\n\u003cbr\u003e\n\n### Advanced AI Algorithms\n\n\u003cimg title=\"Advanced AI Algorithms\" src=\"https://i.imgur.com/I8Pvdav.png\" width=\"250\" \u003e\u003c/img\u003e\n\n\u003cbr\u003e\n\nMoseca utilizes state-of-the-art AI technology to extract voice or music from\nyour original songs accurately.\n\n\u003cbr\u003e\n\n### Karaoke Fun\n\n\u003cimg title=\"Karaoke Fun\" src=\"https://i.imgur.com/nsn3JGV.png\" width=\"250\" \u003e\u003c/img\u003e\n\n\u003cbr\u003e\n\nEngage with your favorite tunes in a whole new way!\n\nMoseca offers an immersive online karaoke experience, allowing you to search\nfor any song on YouTube and remove the vocals online.\n\nEnjoy singing along with high-quality instrumentals at the comfort of your home.\n\n\n\u003cbr\u003e\n\n### Easy Deployment\n\n\nWith Moseca, you can deploy your personal Moseca app in the\n\u003ca href=\"https://huggingface.co/spaces/fabiogra/moseca?duplicate=true\"\u003e\n\u003cimg src=\"https://img.shields.io/badge/🤗%20Hugging%20Face-Spaces-blue\"\nalt=\"Hugging Face Spaces\"\u003e\u003c/a\u003e or locally with\n[![Docker Call](https://img.shields.io/badge/-Docker%20Image-blue?logo=docker\u0026labelColor=white)](https://huggingface.co/spaces/fabiogra/moseca/discussions?docker=true)\nin just one click.\n\nYou can also speed up the music separation process by [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1ODoK3VXajprNbskqy7G8P1h-Zom92TMA?usp=sharing) with GPU support.\n\n\u003cbr\u003e\n\n### Open-Source and Free\n\nMoseca is the free and open-source alternative to lalal.ai, splitter.ai or media.io vocal remover.\n\nYou can modify, distribute, and use it free of charge. I believe in the power of community\ncollaboration and encourage users to contribute to our source code, making Moseca better with\neach update.\n\n\n\u003cbr\u003e\n\n### Support\n\n- Show your support by giving a star to the GitHub repository [![GitHub stars](https://img.shields.io/github/stars/fabiogra/moseca.svg?style=social\u0026label=Star)](https://github.com/fabiogra/moseca).\n- If you have found an issue or have a suggestion to improve Moseca, you can open an [![GitHub issues](https://img.shields.io/github/issues/fabiogra/moseca.svg)](https://github.com/fabiogra/moseca/issues/new)\n- Enjoy Moseca? [![Buymeacoffee](https://img.shields.io/badge/Buy%20me%20a%20coffee--yellow.svg?logo=buy-me-a-coffee\u0026logoColor=orange\u0026style=social)](https://www.buymeacoffee.com/fabiogra)\n\n------\n\n## FAQs\n\n### What is Moseca?\n\nMoseca is an open-source web app that utilizes advanced AI technology to separate vocals and\ninstrumentals from music tracks. It also provides an online karaoke experience by allowing you\nto search for any song on YouTube and remove the vocals.\n\n### Are there any limitations?\nYes, in this environment there are some limitations regarding lenght processing\nand CPU usage to allow a smooth experience for all users.\n\n\u003cb\u003eIf you want to \u003cu\u003eremove these limitations\u003c/u\u003e you can deploy a Moseca app in your personal\nenvironment like in the \u003ca href=\"https://huggingface.co/spaces/fabiogra/moseca?duplicate=true\"\u003e\u003cimg src=\"https://img.shields.io/badge/🤗%20Hugging%20Face-Spaces-blue\" alt=\"Hugging Face Spaces\"\u003e\u003c/a\u003e or locally with [![Docker Call](https://img.shields.io/badge/-Docker%20Image-blue?logo=docker\u0026labelColor=white)](https://huggingface.co/spaces/fabiogra/moseca/discussions?docker=true)\u003c/b\u003e\n\n### How does Moseca work?\nMoseca utilizes the Hybrid Spectrogram and Waveform Source Separation ([DEMUCS](https://github.com/facebookresearch/demucs)) model from Facebook. For fast karaoke vocal removal, Moseca uses the AI vocal remover developed by [tsurumeso](https://github.com/tsurumeso/vocal-remover).\n\n### How do I use Moseca?\n1. Upload your file: choose your song and upload it to Moseca. It supports\na wide range of music formats for your convenience.\n\n2. Choose separation mode: opt for voice only, 4-stem or 6-stem separation\ndepending on your requirement.\n\n3. Let AI do its magic: Moseca’s advanced AI will work to separate vocals\nfrom music in a matter of minutes, giving you high-quality, separated audio tracks.\n\n4. Download and enjoy: preview and download your separated audio tracks.\nNow you can enjoy them anytime, anywhere!\n\n\n### Where can I find the code for Moseca?\n\nThe code for Moseca is readily available on\n[GitHub](https://github.com/fabiogra/moseca) and\n[Hugging Face](https://huggingface.co/spaces/fabiogra/moseca).\n\n\n### How can I get in touch with you?\n\nFor any questions or feedback, feel free to contact me on\n[![Twitter](https://badgen.net/badge/icon/twitter?icon=twitter\u0026label)](https://twitter.com/grsFabio)\nor [LinkedIn](https://www.linkedin.com/in/fabio-grasso/en).\n\n------\n## Disclaimer\n\nMoseca is designed to separate vocals and instruments from copyrighted music for\nlegally permissible purposes, such as learning, practicing, research, or other non-commercial\nactivities that fall within the scope of fair use or exceptions to copyright. As a user, you are\nresponsible for ensuring that your use of separated audio tracks complies with the legal\nrequirements in your jurisdiction.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ffabiogra%2Fmoseca","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ffabiogra%2Fmoseca","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ffabiogra%2Fmoseca/lists"}