hayabhay/frogbase

Transform audio-visual content into navigable knowledge.

Archived
46
/ 100
Emerging

Orchestrates a complete pipeline linking media sources (yt_dlp, local files) through OpenAI Whisper transcription, SentenceTransformers embeddings, and hnswlib vector search—enabling semantic queries across multi-modal content. Includes both a Python API and Streamlit UI, allowing developers to build search applications or non-technical users to run locally without coding.

778 stars. No commits in the last 6 months.

Archived Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

778

Forks

92

Language

Python

License

MIT

Category

video-semantic-search

Last pushed

Oct 25, 2023

Commits (30d)

0

GitHub
Video Semantic Search · 27 tools

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/hayabhay/frogbase"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.

Higher-rated alternatives

ssrajadh/sentrysearch

Semantic search over videos using Gemini Embedding 2.

58

zilliz-bootcamp/audio_search

This project use PANNs for audio tagging and sound event detection, and finally get audio...

32

kyegomez/Pegasus

PegasusX: The Future of Multimodal Embeddings đŸ¦„ đŸ¦„

29

ashvardanian/SwiftSemanticSearch

Real-time on-device text-to-image and image-to-image Semantic Search with video stream camera...

29

tomfalainen/word_spotting

Semantic and Verbatim Word Spotting in Torch

27

Explore Embedding Tools

All categories Trending Embeddings directory Insights