FrogBase: Audiovisual Knowledge Search

FrogBase is an open-source package that simplifies the download-transcribe-embed-index workflow for audiovisual content.
It does so by linking content from various platforms (yt_dlp) with speech-to-text models (OpenAI’s Whisper), image & text encoders (SentenceTransformers), and embedding stores (hnswlib).
FrogBase also comes with a ready-to-use Streamlit UI for non-technical users.

Note: FrogBase supports and prioritizes self-hosted use-cases like audio-journaling, semantic search for personal video catalog etc.