{"id":37163292,"url":"https://github.com/xserrat/docker-facebook-demucs","last_synced_at":"2026-01-14T19:25:13.213Z","repository":{"id":45414323,"uuid":"332541430","full_name":"xserrat/docker-facebook-demucs","owner":"xserrat","description":"Dockerized Facebook Demucs library to make it easy its execution","archived":false,"fork":false,"pushed_at":"2024-11-24T18:41:07.000Z","size":34,"stargazers_count":141,"open_issues_count":7,"forks_count":41,"subscribers_count":9,"default_branch":"main","last_synced_at":"2024-11-24T19:34:02.824Z","etag":null,"topics":["demucs","docker","facebook","facebook-demucs","machine-learning","music"],"latest_commit_sha":null,"homepage":"","language":"Makefile","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/xserrat.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":"2021-01-24T19:51:18.000Z","updated_at":"2024-11-24T18:33:28.000Z","dependencies_parsed_at":"2024-11-24T23:48:59.914Z","dependency_job_id":null,"html_url":"https://github.com/xserrat/docker-facebook-demucs","commit_stats":null,"previous_names":[],"tags_count":3,"template":false,"template_full_name":null,"purl":"pkg:github/xserrat/docker-facebook-demucs","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/xserrat%2Fdocker-facebook-demucs","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/xserrat%2Fdocker-facebook-demucs/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/xserrat%2Fdocker-facebook-demucs/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/xserrat%2Fdocker-facebook-demucs/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/xserrat","download_url":"https://codeload.github.com/xserrat/docker-facebook-demucs/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/xserrat%2Fdocker-facebook-demucs/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":28432592,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-01-14T18:57:19.464Z","status":"ssl_error","status_checked_at":"2026-01-14T18:52:48.501Z","response_time":107,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.6:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"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":["demucs","docker","facebook","facebook-demucs","machine-learning","music"],"created_at":"2026-01-14T19:25:12.539Z","updated_at":"2026-01-14T19:25:13.198Z","avatar_url":"https://github.com/xserrat.png","language":"Makefile","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Docker Facebook Demucs\nThis repository dockerizes [Demucs](https://github.com/adefossez/demucs)\nto split music tracks into different tracks (bass, drums, voice, others).\n\n## Usage\n### Clone this repository\n```bash\ngit clone https://github.com/xserrat/docker-facebook-demucs.git demucs\n```\n### Split a music track\n1. Copy the track you want to split into the `input` folder (e.g., `input/mysong.mp3`).\n2. Execute `demucs` via the `run` job in the `Makefile`, specifying the `track` argument with only the name of the file:\n```bash\nmake run track=mysong.mp3\n```\n\nThis process will take some time the first time it is run, as the execution will:\n* Download the Docker image that is setup to run the `facebook demucs` script.\n* Download the pretrained models.\n* Execute `demucs` to split the track.\n\nSubsequent runs will not need to download the Docker image or download the models, unless the model specified has not yet been used.\n\n#### Options\nThe following options are available when splitting music tracks with the `run` job:\n\nOption | Default Value | Description\n--- | --- | ---\n`gpu`           | `false` | Enable Nvidia CUDA support (requires an Nvidia GPU).\n`model`         | `demucs`| The model used for audio separation. See https://github.com/facebookresearch/demucs#separating-tracks for a list of available models to use.\n`mp3output`     | `false` | Output separated audio in `mp3` format instead of the default `wav` format.\n`shifts`        | `1`     | Perform multiple predictions with random shifts (a.k.a the shift trick) of the input and average them. This makes prediction `SHIFTS` times slower. Don't use it unless you have a GPU.\n`overlap`       | `0.25`  | Control the amount of overlap between prediction windows. Default is 0.25 (i.e. 25%) which is probably fine. It can probably be reduced to 0.1 to improve separation speed.\n`jobs`          | `1`     | Specify the number of parallel jobs to run during separation. This will multiply the amount of RAM used by the same number, so be careful!\n`splittrack`    |         | Individual track to split/separate from the others (e.g., you only want to separate drums). Valid options are `bass`, `drums`, `vocals` and `other`. Other values may be allowed if the model can separate additional track types.\n\nExample commands:\n```bash\n# Use the \"fine tuned\" demucs model\nmake run track=mysong.mp3 model=htdemucs_ft\n\n# Enable Nvidia CUDA support and output separated audio in mp3 format\nmake run track=mysong.mp3 gpu=true mp3output=true\n```\n\n### Run Interactively\n\nTo experiment with other `demucs` options on the command line, you can also run the Docker image interactively via the `run-interactive` job. Note that only the `gpu` option is applicable for this job.\n\nExample:\n```bash\nmake run-interactive gpu=true\n```\n\n## Building the Image\n\nThe Docker image can be built locally via the `build` job:\n```bash\nmake build\n```\n\n## License\nThis repository is released under the MIT license as found in the [LICENSE](LICENSE) file.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fxserrat%2Fdocker-facebook-demucs","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fxserrat%2Fdocker-facebook-demucs","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fxserrat%2Fdocker-facebook-demucs/lists"}