{"id":23725988,"url":"https://github.com/voidful/soundon","last_synced_at":"2026-02-13T13:05:42.754Z","repository":{"id":251357577,"uuid":"833158881","full_name":"voidful/SoundON","owner":"voidful","description":null,"archived":false,"fork":false,"pushed_at":"2024-09-08T06:20:22.000Z","size":133,"stargazers_count":1,"open_issues_count":0,"forks_count":1,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-19T06:04:36.784Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/voidful.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"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":"2024-07-24T13:19:31.000Z","updated_at":"2024-09-08T06:20:25.000Z","dependencies_parsed_at":"2024-09-08T07:40:30.892Z","dependency_job_id":null,"html_url":"https://github.com/voidful/SoundON","commit_stats":null,"previous_names":["voidful/soundon"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/voidful/SoundON","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/voidful%2FSoundON","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/voidful%2FSoundON/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/voidful%2FSoundON/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/voidful%2FSoundON/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/voidful","download_url":"https://codeload.github.com/voidful/SoundON/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/voidful%2FSoundON/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":273541900,"owners_count":25124056,"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":"2025-09-04T02:00:08.968Z","response_time":61,"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":"2024-12-31T00:18:06.807Z","updated_at":"2026-02-13T13:05:37.730Z","avatar_url":"https://github.com/voidful.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"\n# SoundOn: Any Codec to Mel Spectrogram\n\nSoundOn is a project that converts audio files to mel spectrograms, a format suitable for training sound generation models. This repository contains scripts to prepare the dataset and convert audio files to mel spectrograms.\n\n## Getting Started\n\n### Dependencies\n\n- Python 3.8 or later\n- PyTorch\n- torchaudio\n- librosa (optional, for additional audio processing)\n\nEnsure you have Python installed on your system. This project is developed and tested on macOS, but it should be compatible with Linux and Windows, provided all dependencies are met.\n\n### Installing\n\nClone the repository to your local machine:\n\n```bash\ngit clone https://github.com/yourusername/soundon.git\ncd soundon\n```\n\n### Preparing the Dataset\n\nPlace your `.wav` audio files in a directory. Update the `directory` parameter in the `MelDataset` instantiation in `dataset_prepare.py` to point to this directory.\n\n### Running the Dataset Preparation\n\nExecute `dataset_prepare.py` to start the dataset preparation process:\n\n```bash\npython dataset_prepare.py\n```\n\nThis script will process all `.wav` files in the specified directory, converting them into mel spectrograms and printing their shapes.\n\n## Usage\n\nThe `MelDataset` class can be used as follows:\n\n```python\nfrom dataset_prepare import MelDataset\nfrom torch.utils.data import DataLoader\n\nparams = {\n    'sampling_rate': 24000,\n    'n_fft': 1024,\n    'win_size': 1024,\n    'hop_size': 256,\n    'num_mels': 100,\n    'fmin': 0,\n    'fmax': None,\n}\n\ndataset = MelDataset(directory='/path/to/audio/files', params=params)\ndataloader = DataLoader(dataset, batch_size=32, shuffle=True, num_workers=4)\n\nfor mel_spec in dataloader:\n    print(mel_spec.shape)\n```\n\n## Contributing\n\nContributions to the project are welcome! Please fork the repository, create a feature branch, and submit a pull request.\n\n## License\n\nThis project is licensed under the MIT License - see the `LICENSE` file for details.\n\n## Acknowledgments\n\n- The `code2mel.py` and `dataset_prepare.py` scripts are foundational to this project, enabling the conversion of audio files to a format suitable for sound generation models.\n```\n\nThis `README.md` template provides a comprehensive overview of your project, including how to get started, use the project, and contribute. Adjust the repository URL and any specific details as necessary.","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fvoidful%2Fsoundon","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fvoidful%2Fsoundon","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fvoidful%2Fsoundon/lists"}