fbunau

ogrodje-events

Ogrodje Events Aggregator

ml-engineering

Machine Learning Engineering Open Book

instance_matcher_using_embeddings

The project uses three types of embeddings (DOC2Vec, Word2Vec, RDF2Vec) to perform instance matching on Knowledge Graphs

datatrove

Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.

insanely-fast-whisper

prompts-for-edu

WebGPT

Run GPT model on the browser with WebGPU. An implementation of GPT inference in less than ~1500 lines of vanilla Javascript.

consistency_models

Official repo for consistency models.

whisper_streaming

Whisper realtime streaming for long speech-to-text transcription and translation

Prompt-Engineering-Guide

🐙 Guides, papers, lecture, notebooks and resources for prompt engineering

gpt4-spanish

A GPT-4 prompt that helps you learn Spanish.

paper-qa

LLM Chain for answering questions from documents with citations

indigo-examples

Examples of how to build things in Indigo, running the latest release.

indigo

An FP game engine for Scala.

tyrian

Elm-inspired Scala UI library.

libgdx-graalvm-example

Advanced LibGDX demo with GraalVM native-image configuration

delverengine

Delver game engine and editor

unilm

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

textual

The lean application framework for Python. Build sophisticated user interfaces with a simple Python API. Run your apps in the terminal and a web browser.

whisperX

WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)

bertviz

BertViz: Visualize Attention in NLP Models (BERT, GPT2, BART, etc.)

whisper.cpp

Port of OpenAI's Whisper model in C/C++

pyannote-audio

Neural building blocks for speaker diarization: speech activity detection, speaker change detection, overlapped speech detection, speaker embedding

slist

A spruced up version of the built-in python list. More post fixed methods for lovely typesafe chaining!

streamlit-autorefresh

An autorefresh component for Streamlit apps

EasyOCR

Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.

frogbase

Transform audio-visual content into navigable knowledge.

steamdeck-emulation

🎮 Guide to play emulated games on Steam Deck

delta-oms

DeltaOMS is a solution that help build a centralized repository of Delta Transaction logs and associated operational metrics/statistics for your Delta Lakehouse. Unity Catalog supported in the v0.7.0-rc1 release.Documentation here - https://databrickslabs.github.io/delta-oms/v0.7.0-rc1/

Data-Science-Extensions