{"id":16392195,"url":"https://github.com/justinsalamon/scaper","last_synced_at":"2025-04-04T07:05:47.206Z","repository":{"id":7836042,"uuid":"56619706","full_name":"justinsalamon/scaper","owner":"justinsalamon","description":"A library for soundscape synthesis and augmentation","archived":false,"fork":false,"pushed_at":"2022-05-04T10:23:27.000Z","size":68764,"stargazers_count":377,"open_issues_count":60,"forks_count":55,"subscribers_count":8,"default_branch":"master","last_synced_at":"2024-10-12T04:48:48.419Z","etag":null,"topics":["audio","audio-processing","data-augmentation","machine-learning","machine-listening","soundscape","soundscape-synthesis","sox","synthesis"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"bsd-3-clause","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/justinsalamon.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}},"created_at":"2016-04-19T18:03:35.000Z","updated_at":"2024-09-25T14:53:51.000Z","dependencies_parsed_at":"2022-08-08T09:30:14.708Z","dependency_job_id":null,"html_url":"https://github.com/justinsalamon/scaper","commit_stats":null,"previous_names":[],"tags_count":39,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/justinsalamon%2Fscaper","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/justinsalamon%2Fscaper/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/justinsalamon%2Fscaper/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/justinsalamon%2Fscaper/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/justinsalamon","download_url":"https://codeload.github.com/justinsalamon/scaper/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247135142,"owners_count":20889420,"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","audio-processing","data-augmentation","machine-learning","machine-listening","soundscape","soundscape-synthesis","sox","synthesis"],"created_at":"2024-10-11T04:48:54.802Z","updated_at":"2025-04-04T07:05:47.186Z","avatar_url":"https://github.com/justinsalamon.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# scaper\n\n\u003cimg src=\"http://www.justinsalamon.com/uploads/4/3/9/4/4394963/scaper-logo_orig.png\" width=\"400\" height=\"108\"\u003e\n\nA library for soundscape synthesis and augmentation\n\n[![PyPI](https://img.shields.io/pypi/v/scaper.svg)](https://pypi.python.org/pypi/scaper)\n[![License](https://img.shields.io/badge/License-BSD%203--Clause-blue.svg)](https://opensource.org/licenses/BSD-3-Clause)\n[![Build Status](https://travis-ci.org/justinsalamon/scaper.svg?branch=master)](https://travis-ci.org/justinsalamon/scaper)\n[![Coverage Status](https://coveralls.io/repos/github/justinsalamon/scaper/badge.svg?branch=master)](https://coveralls.io/github/justinsalamon/scaper?branch=master)\n[![Documentation Status](https://readthedocs.org/projects/scaper/badge/?version=latest)](http://scaper.readthedocs.io/en/latest/?badge=latest)\n[![Downloads](https://pepy.tech/badge/scaper)](https://pepy.tech/project/scaper)\n[![PyPI](https://img.shields.io/badge/python-2.7%2C%203.4%2C%203.5%2C%203.6-blue.svg)]()\n\nPlease refer to the [documentation](http://scaper.readthedocs.io/) for details.\n\nFor the motivation behind scaper and its applications check out the scaper-paper:\n\n[Scaper: A library for soundscape synthesis and augmentation](http://www.justinsalamon.com/uploads/4/3/9/4/4394963/salamon_scaper_waspaa_2017.pdf)\u003cbr /\u003e\nJ. Salamon, D. MacConnell, M. Cartwright, P. Li, and J. P. Bello\u003cbr /\u003e\nIn IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), New Paltz, NY, USA, Oct. 2017.\n\n## Installation\n\n### Non-python dependencies\nScaper has one non-python dependency:\n- FFmpeg: https://ffmpeg.org/\n\nIf you are installing Scaper on Windows, you will also need:\n- SoX: http://sox.sourceforge.net/\n\nOn Linux/macOS SoX is replaced by [SoxBindings](https://github.com/pseeth/soxbindings) which is significantly faster, giving better runtime performance in Scaper. On these platforms SoxBindings is installed automatically when calling `pip install scaper` (see below).\n\n#### Linux/macOS\nIf you're using [Anaconda](https://www.anaconda.com/distribution/) (or [miniconda](https://docs.conda.io/en/latest/miniconda.html)) to manage your python environment (recommended), you can install FFmpeg using `conda` on macOS/Linux:\n\n```\nconda install -c conda-forge ffmpeg\n```\n\n#### macOS\nOn macOS FFmpeg can be installed using [homebrew](https://brew.sh/):\n\n```\nbrew install ffmpeg\n```\n\n#### Linux\nOn linux you can use your distribution's package manager, e.g. on Ubuntu (15.04 \"Vivid Vervet\" or newer):\n\n```\nsudo apt-get install ffmpeg\n```\nNOTE: on earlier versions of Ubuntu [ffmpeg may point to a Libav binary](http://stackoverflow.com/a/9477756/2007700) which is not the correct binary. If you are using Anaconda, you can install the correct version as described earlier by calling `conda install -c conda-forge ffmpeg`. Otherwise, you can [obtain a static binary from the ffmpeg website](https://ffmpeg.org/download.html).\n\n#### Windows\nOn windows you can use the provided installation binaries:\n- SoX: https://sourceforge.net/projects/sox/files/sox/\n- FFmpeg: https://ffmpeg.org/download.html#build-windows\n\n### Installing Scaper\n\nThe simplest way to install scaper is by using `pip`, which will also install the required python dependencies if needed. To install scaper using pip, simply run:\n\n```\npip install scaper\n```\n\nTo install the latest version of scaper from source, clone or pull the lastest version:\n\n```\ngit clone git@github.com:justinsalamon/scaper.git\n```\n\nThen enter the source folder and install using pip to handle python dependencies:\n\n```\ncd scaper\npip install -e .\n```\n## Tutorial\n\nTo help you get started with scaper, please see this [step-by-step tutorial](http://scaper.readthedocs.io/en/latest/tutorial.html).\n\n## Example\n\n```python\nimport scaper\nimport numpy as np\n\n# OUTPUT FOLDER\noutfolder = 'audio/soundscapes/'\n\n# SCAPER SETTINGS\nfg_folder = 'audio/soundbank/foreground/'\nbg_folder = 'audio/soundbank/background/'\n\nn_soundscapes = 1000\nref_db = -50\nduration = 10.0 \n\nmin_events = 1\nmax_events = 9\n\nevent_time_dist = 'truncnorm'\nevent_time_mean = 5.0\nevent_time_std = 2.0\nevent_time_min = 0.0\nevent_time_max = 10.0\n\nsource_time_dist = 'const'\nsource_time = 0.0\n\nevent_duration_dist = 'uniform'\nevent_duration_min = 0.5\nevent_duration_max = 4.0\n\nsnr_dist = 'uniform'\nsnr_min = 6\nsnr_max = 30\n\npitch_dist = 'uniform'\npitch_min = -3.0\npitch_max = 3.0\n\ntime_stretch_dist = 'uniform'\ntime_stretch_min = 0.8\ntime_stretch_max = 1.2\n    \n# Generate 1000 soundscapes using a truncated normal distribution of start times\n\nfor n in range(n_soundscapes):\n    \n    print('Generating soundscape: {:d}/{:d}'.format(n+1, n_soundscapes))\n    \n    # create a scaper\n    sc = scaper.Scaper(duration, fg_folder, bg_folder)\n    sc.protected_labels = []\n    sc.ref_db = ref_db\n    \n    # add background\n    sc.add_background(label=('const', 'noise'), \n                      source_file=('choose', []), \n                      source_time=('const', 0))\n\n    # add random number of foreground events\n    n_events = np.random.randint(min_events, max_events+1)\n    for _ in range(n_events):\n        sc.add_event(label=('choose', []), \n                     source_file=('choose', []), \n                     source_time=(source_time_dist, source_time), \n                     event_time=(event_time_dist, event_time_mean, event_time_std, event_time_min, event_time_max), \n                     event_duration=(event_duration_dist, event_duration_min, event_duration_max), \n                     snr=(snr_dist, snr_min, snr_max),\n                     pitch_shift=(pitch_dist, pitch_min, pitch_max),\n                     time_stretch=(time_stretch_dist, time_stretch_min, time_stretch_max))\n    \n    # generate\n    audiofile = os.path.join(outfolder, \"soundscape_unimodal{:d}.wav\".format(n))\n    jamsfile = os.path.join(outfolder, \"soundscape_unimodal{:d}.jams\".format(n))\n    txtfile = os.path.join(outfolder, \"soundscape_unimodal{:d}.txt\".format(n))\n    \n    sc.generate(audiofile, jamsfile,\n                allow_repeated_label=True,\n                allow_repeated_source=False,\n                reverb=0.1,\n                disable_sox_warnings=True,\n                no_audio=False,\n                txt_path=txtfile)\n```\n\n## How to contribute\n\nIf you would like to contribute a feature and/or bugfix to this repository, please follow the following steps:\n\n1. Create an issue describing the feature/fix.\n2. I will reply on the issue thread to determine whether the feature/fix can/should be added.\n3. Discuss design/implementation details in the issue thread and reach consensus.\n4. Once consensus is reached (and only then), start a pull request (PR). Further discsussion can continue in the PR thread.\n5. Implement feature/fix, ensuring all current unit tests pass and new tests are added to maintain 100% test coverage. Inline docstrings as well as the main docs files should also be updated accordingly.\n6. Request code review once the pull request is ready for review.\n7. Fix requested changes to the pull request if any. Repeat steps 5-7 until the PR is approved.\n8. once the PR is approved I will merge it into master (and most likely create a new release).\n\nIMPORTANT: please be sure to always discuss a proposed feature/fix in an issue before creating a pull request.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjustinsalamon%2Fscaper","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjustinsalamon%2Fscaper","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjustinsalamon%2Fscaper/lists"}