{"id":13415250,"url":"https://github.com/CoffeeVampir3/audiocraft-webui","last_synced_at":"2025-03-14T22:33:07.909Z","repository":{"id":174283239,"uuid":"652017961","full_name":"CoffeeVampir3/audiocraft-webui","owner":"CoffeeVampir3","description":"Quick webui for audiocraft","archived":false,"fork":false,"pushed_at":"2024-03-06T12:14:09.000Z","size":1089,"stargazers_count":137,"open_issues_count":2,"forks_count":13,"subscribers_count":6,"default_branch":"main","last_synced_at":"2024-07-31T21:53:34.860Z","etag":null,"topics":["audiocraft","free","machine-learning","musicgen","opensource","unlicense","webui"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"unlicense","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/CoffeeVampir3.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":"2023-06-10T20:24:20.000Z","updated_at":"2024-07-29T13:09:51.000Z","dependencies_parsed_at":null,"dependency_job_id":"aa0fa6e3-d368-4a74-9fc0-d825021f1ef4","html_url":"https://github.com/CoffeeVampir3/audiocraft-webui","commit_stats":null,"previous_names":["coffeevampir3/audiocraft-webui"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CoffeeVampir3%2Faudiocraft-webui","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CoffeeVampir3%2Faudiocraft-webui/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CoffeeVampir3%2Faudiocraft-webui/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CoffeeVampir3%2Faudiocraft-webui/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/CoffeeVampir3","download_url":"https://codeload.github.com/CoffeeVampir3/audiocraft-webui/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":243658057,"owners_count":20326459,"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":["audiocraft","free","machine-learning","musicgen","opensource","unlicense","webui"],"created_at":"2024-07-30T21:00:45.922Z","updated_at":"2025-03-14T22:33:07.903Z","avatar_url":"https://github.com/CoffeeVampir3.png","language":"Python","funding_links":[],"categories":["Python","🌟 Featured Community Projects"],"sub_categories":[],"readme":"[![Discord](https://img.shields.io/discord/232596713892872193?logo=discord)](https://discord.gg/2JhHVh7CGu)\n\n# audiocraft-webui v2.0!\nLocal web UI for Facebook's Audiocraft model: \u003chttps://github.com/facebookresearch/audiocraft\u003e\n\n![](https://github.com/CoffeeVampir3/audiocraft-webui/blob/1a1390e2842a7eaa8de376503abb51fbfad233ca/preview.png)\n\n## Features:\n\n- **Long Audio**: Generate audio as long as you like.\n- **Processing Queue**: Add multiple prompts to the queue and process them automatically.\n- **Generation History**: Replay generated audio and view the settings used for each.\n\n## Install:\n\nIf you'd like GPU acceleration and do not have torch installed, visit [PyTorch Installation Guide](https://pytorch.org/get-started/locally/) for instructions on installing GPU-enabled torch correctly.\n\n### **Option 1: Manual Installation (Classic Method)**\nIf you prefer manual installation, install dependencies using:\n```bash\npip install -r requirements.txt\n```\n(If you encounter errors with **audiocraft**, please refer to their [official documentation](https://github.com/facebookresearch/audiocraft)).\n\n### **Option 2: Using the Install Script (Automated Setup)**\nTo automate installation and environment setup, use the provided script:\n- **Linux/macOS:**\n  ```bash\n  ./install.sh\n  ```\n- **Windows:**\n  ```cmd\n  install.bat\n  ```\nThis will check for **Python 3.10**, create a virtual environment (`venv`), and install all required dependencies automatically. If Conda is available, it can be used instead of venv.\n\n---\n\n## Run:\n\n### **Option 1: Manual Run (Classic Method)**\nStart the web UI manually using:\n```bash\npython webui.py\n```\n\n### **Option 2: Using the Run Script (Automated Execution)**\nAlternatively, use the run script for easier execution:\n- **Linux/macOS:**\n  ```bash\n  ./run.sh\n  ```\n- **Windows:**\n  ```cmd\n  run.bat\n  ```\nThis will automatically activate the appropriate environment (virtualenv or Conda) and start `webui.py`. Once the script is stopped, it ensures the environment is properly deactivated.\n\n---\n\nThere's no need to download any external models. Simply pick a model from the dropdown menu, and when you run it for the first time, it will be automatically downloaded via **Audiocraft**.\n\nIf you want to use **Melody Mode**, select the **Melody model**, and an option to upload your melody audio file will appear.\n\n---\n\n## Notes:\n- Generated files are saved in the `static/audio/` directory.\n- The currently active model remains loaded in memory by default. To unload it after each generation, launch with:\n  ```bash\n  python webui.py --unload-after-gen\n  ```\n- The UI could use an improved design—contributors are welcome!\n\n---\n\n## Parameters:\n\n- **Top-K**: Affects the variety of generated audio. Higher values lead to more diverse results but may increase randomness.\n- **Top-P**: Recommended around 0.7. Controls sampling diversity, with lower values producing more stable results.\n- **Duration**: Length of generated audio.\n- **CFG (Classifier Free Guidance)**: Determines how strictly the output follows the prompt (recommended 3-5).\n- **Temperature**: Controls randomness. Higher values (1.05-1.5) create more chaotic results, while lower values yield structured outputs.\n\n---\n\n## Troubleshooting:\n- **Torch Installation Issues:**\n  Ensure you have the correct **CPU/GPU version** installed ([PyTorch Guide](https://pytorch.org/get-started/locally/)).\n- **Virtual Environment Issues:**\n  If activation fails, try:\n  ```bash\n  source venv/bin/activate  # Linux/macOS\n  venv\\Scripts\\activate    # Windows\n  ```\n- **Conda Not Found?**\n  Ensure Conda is installed and added to `PATH`. Verify by running:\n  ```bash\n  conda --version\n  ```\n- **Installation Script Issues?**\n  Ensure scripts have execution permissions:\n  ```bash\n  chmod +x install.sh run.sh\n  ```\n\n---\n\n## Changelog:\n\n### Feb-25-2024:\n- Rewrote everything.\n- Added generation history for audio outputs.\n- Removed outdated dependencies.\n- Removed deprecated parameters (`overlap` and `segments`).\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FCoffeeVampir3%2Faudiocraft-webui","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FCoffeeVampir3%2Faudiocraft-webui","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FCoffeeVampir3%2Faudiocraft-webui/lists"}