21 Lessons, Get Started Building with Generative AI

Data and code behind the articles and graphics at FiveThirtyEight

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

🪼 a python library for doing approximate and phonetic matching of strings.

Developer APIs to Accelerate LLM Projects

Official Implementation of "KBLaM: Knowledge Base augmented Language Model"

Croissant is a high-level format for machine learning datasets that brings together four rich layers.

Analyze documents with Amazon Textract and generate output in multiple formats.

🎲 Notes explaining Dirichlet Processes, HDPs, and Latent Dirichlet Allocation

How to use OpenAIs Whisper to transcribe and diarize audio files

potato: portable text annotation tool

Python for Data Science (Seminar Course at UC Berkeley; AY 250)

Predict Race and Ethnicity Based on the Sequence of Characters in a Name

Scripts and data for various Vox Media stories and news projects

Code for the paper: "Large Language Models as Corporate Lobbyists" (2023).

A pytest plugin for running and analyzing LLM evaluation tests.

This is an introduction to tensorflow

Notebooks covering introductory material to ML, ML with sklearn and tips.

Python 3.x notebooks about real-world data cleaning and visualization

A tutorial on optical character recognition using tesseract, ImageMagick and other open source tools

Course materials for a data visualization course taught at the University of Nebraska-Lincoln's College of Journalism and Mass Communications

A Los Angeles Times analysis of Every shot in Kobe Bryant's NBA career

A Los Angeles Times analysis of serious assaults misclassified by LAPD

A collection of Jupyter notebooks demonstrating ways to analyze Census data

Data and materials to reproduce Bloomberg's investigation into racial and gender bias in OpenAI's GPT

Inspect a URL and estimate if it contains a news story

Data and analysis supporting several passages in the BuzzFeed News article, "The New American Slavery: Invited To The U.S., Foreign Workers Find A Nightmare," published July 24, 2015.

Suggestions, schedules, and other information about the Engineering Chapter's Tech Talk meetings.

Whisper Audio Transcriber: Streamlined tool for converting audio to text using the powerful Whisper ASR model. User-friendly and efficient.