#
Lists (4)
Starred repositories
A curated list of awesome Speaker Diarization papers, libraries, datasets, and other resources.
experimental web browser optimized for rabbit-holing
DuckDB wrapper for FAISS - Experimental
A fast and simple image viewer / editor for many operating systems
Model2Vec: Distill a Small Fast Model from any Sentence Transformer
Things you can do with the token embeddings of an LLM
Javascript port of the S2 Geometry library for {browser, node}
A list of selected resources, methods, and tools dedicated to Legal Text Analytics.
PostgreSQL Languages AST and statements prettifier: master branch covers PG10, v2 branch covers PG12, v3 covers PG13, v4 covers PG14, v5 covers PG15, v6 covers PG16
TorchGeo: datasets, samplers, transforms, and pre-trained models for geospatial data
Plumb a PDF for detailed information about each char, rectangle, line, et cetera — and easily extract text and tables.
Fast, accurate, open-source geocoding in Python
Swiss-army tool for scraping and extracting data from online assets, made for hackers
Easily copy all relevant source files in a repository to clipboard. For use in LLM code understanding and generation workflows
PostgreSQL extension adding HyperLogLog data structures as a native data type
Fast, lightweight access to Apache Arrow data.
Speech Note Linux app. Note taking, reading and translating with offline Speech to Text, Text to Speech and Machine translation.
Official code implementation of General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model
Query Snowflake tables locally with DuckDB, without any need for a running warehouse
A Jupyter widget to visualize tensor data in notebooks.