{"id":13510693,"url":"https://github.com/hayabhay/frogbase","last_synced_at":"2025-09-30T10:30:55.378Z","repository":{"id":61666909,"uuid":"552888127","full_name":"hayabhay/frogbase","owner":"hayabhay","description":"Transform audio-visual content into navigable knowledge.","archived":true,"fork":false,"pushed_at":"2023-10-25T01:41:48.000Z","size":1277,"stargazers_count":784,"open_issues_count":18,"forks_count":95,"subscribers_count":19,"default_branch":"main","last_synced_at":"2025-01-16T01:37:37.450Z","etag":null,"topics":["embeddings","package","python","search","semantic-search","speech-to-text","streamlit","ui"],"latest_commit_sha":null,"homepage":"https://frogbase.dev","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/hayabhay.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"docs/contributing.md","funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":"docs/roadmap.md","authors":null}},"created_at":"2022-10-17T11:39:25.000Z","updated_at":"2025-01-10T01:57:48.000Z","dependencies_parsed_at":"2024-01-13T19:35:34.986Z","dependency_job_id":"513daed6-8661-4572-a734-e4732f2eddd1","html_url":"https://github.com/hayabhay/frogbase","commit_stats":null,"previous_names":["hayabhay/whisper-ui"],"tags_count":8,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hayabhay%2Ffrogbase","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hayabhay%2Ffrogbase/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hayabhay%2Ffrogbase/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hayabhay%2Ffrogbase/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/hayabhay","download_url":"https://codeload.github.com/hayabhay/frogbase/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":234724895,"owners_count":18877279,"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":["embeddings","package","python","search","semantic-search","speech-to-text","streamlit","ui"],"created_at":"2024-08-01T02:01:50.318Z","updated_at":"2025-09-30T10:30:50.028Z","avatar_url":"https://github.com/hayabhay.png","language":"Python","readme":"# 🐸 FrogBase\n\n\u003e _**Create navigable knowledge from multi-media content**_\n\n**FrogBase** (previously whisper-ui) simplifies the `download-transcribe-embed-index` workflow for multi-media content.\nIt does so by linking content from various platforms\n([yt_dlp](https://github.com/yt-dlp/yt-dlp))\nwith speech-to-text models ([OpenAI's Whisper](https://github.com/openai/whisper)),\nimage \u0026 text encoders ([SentenceTransformers](https://github.com/UKPLab/sentence-transformers)),\nand embedding stores ([hnswlib](https://github.com/nmslib/hnswlib)).\n\n\u003e ⚠️ Warning: This is currently a pre-release version and is known to be very unstable. For stable releases, please use any 1.x versions.\n\n```python\nfrom frogbase import FrogBase\nfb = FrogBase()\nfb.demo()\nfb.search(\"What is the name of the squeaky frog?\")\n```\n\n\u003e [Full Documentation](https://hayabhay.github.io/frogbase/) (WIP).\n\n_FrogBase also comes with a **ready-to-use UI for non-technical users!**_\n\nhttps://user-images.githubusercontent.com/6735526/216852681-53b6c3db-3e74-4c86-806f-6f6774a9003a.mp4\n\n[![PyPI](https://img.shields.io/pypi/v/frogbase.svg)][pypi_]\n[![Status](https://img.shields.io/pypi/status/frogbase.svg)][status]\n[![Python Version](https://img.shields.io/pypi/pyversions/frogbase)][python version]\n[![License](https://img.shields.io/pypi/l/frogbase)][license]\n\n[pypi_]: https://pypi.org/project/frogbase/\n[status]: https://pypi.org/project/frogbase/\n[python version]: https://pypi.org/project/frogbase\n[license]: https://github.com/hayabhay/frogbase/blob/main/LICENSE\n\n## Features\n\nFrogBase currently provides functionality to:\n\n- Download media files from a wide range of platforms (YouTube, TikTok, Vimeo, etc.) using [yt_dlp](https://github.com/yt-dlp/yt-dlp)\n- Transcribe audio streams for downloaded \u0026 local files using [OpenAI's Whisper](https://openai.com/blog/whisper/)\n- Embed transcribed text from corresponding video segments using [Sentence Transformers](https://www.sbert.net/)\n- Index \u0026 search the embedded content using [hnswlib](https://github.com/nmslib/hnswlib)\n\nFrogBase also includes a [Streamlit](https://streamlit.io/) UI to provide a simple GUI for the above functionality enabling a locally hosted, interactive experience.\n\n## Quickstart\n\n- [Software Developers](###Developers)\n- [Non-technical Users](###Non-technical-Users)\n\n### Software Developers\n\nThis section is for software developers who want to use FrogBase as a python package.\n\n1. Install `ffmpeg` and FrogBase\n\n   ```console\n   sudo apt install ffmpeg\n   pip install frogbase\n   ```\n\n2. Import FrogBase and use it as follows -\n\n   ```python\n   from frogbase import FrogBase\n\n   fb = FrogBase()\n\n   sources = [\n      \"https://www.youtube.com/watch?v=HBxn56l9WcU\",\n      \"https://www.youtube.com/@hayabhay\"\n   ]\n\n   fb.add(sources)\n\n   fb.search(\"What is the name of the squeaky frog?\")\n   ```\n\n### Non-technical Users\n\nThis section is for non-technical users who want to use FrogBase primarily through the accompanying Streamlit UI.\n\n1. Download the latest release of FrogBase from [here](https://github.com/hayabhay/frogbase/archive/refs/heads/main.zip) and unzip it.\n   Or, you can also clone the repository\n   `console\ngit clone https://github.com/hayabhay/frogbase.git\n`\n\n2. Install FrogBase dependencies manually and run the UI.\n\n   \u003e Note: This also requires `ffmpeg` to be installed on your system. You can install it using `sudo apt install ffmpeg` on Ubuntu.\n\n   1. Using pip\n\n      ```console\n      pip install frogbase streamlit\n      streamlit run ui/01_🏠_Home.py\n      ```\n\n\u003e [Coming soon] Instructions, environment for installation using Docker \u0026 Anaconda\n\n## Links\n\n- [Documentation](https://hayabhay.github.io/frogbase/)\n- [Issues](https://github.com/hayabhay/frogbase/issues) \u0026 [Discussions](https://github.com/hayabhay/frogbase/discussions)\n- [Discord](https://discord.gg/HKkpnx8pU)\n- [History](docs/history.md)\n- [Roadmap](docs/roadmap.md)\n- [Contributing Guide](docs/contributing.md)\n- [License](LICENSE) (MIT)\n","funding_links":[],"categories":["Python","ui"],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhayabhay%2Ffrogbase","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fhayabhay%2Ffrogbase","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhayabhay%2Ffrogbase/lists"}