Replace the vendor app for your Pocket AI voice recorder. Pull recordings over BLE, transcribe locally with Whisper, diarize speakers, and summarize with your own API keys — no vendor cloud, ~$2/year.

Building a 'clean room' open-source implementation of Pocket

Flower: A Friendly Federated AI Framework

Supercharge Your LLM Application Evaluations 🚀

Train transformer language models with reinforcement learning.

Class notes for the course "Long Term Memory in AI - Vector Search and Databases" COS 597A @ Princeton Fall 2023

Code for reco-gym: A Reinforcement Learning Environment for the problem of Product Recommendation in Online Advertising

A modular RL library to fine-tune language models to human preferences

A command line tool to easily add an ethics checklist to your data science projects.

DoWhy is a Python library for causal inference that supports explicit modeling and testing of causal assumptions. DoWhy is based on a unified language for causal inference, combining causal graphic…

Cleanlab's open-source library is the standard data-centric AI package for data quality and machine learning with messy, real-world data and labels.

Minimal keyword extraction with BERT

Visual, Interactive Articles About Machine Learning: https://mlu-explain.github.io/

📚 Papers & tech blogs by companies sharing their work on data science & machine learning in production.

A community-maintained Python framework for creating mathematical animations.

A Python package to assess and improve fairness of machine learning models.

A library for efficient similarity search and clustering of dense vectors.

NLP, before and after spaCy

A low code Machine Learning personalized ranking service for articles, listings, search results, recommendations that boosts user engagement. A friendly Learn-to-Rank engine

A game theoretic approach to explain the output of any machine learning model.

SpikeX - SpaCy Pipes for Knowledge Extraction

ConvoKit is a toolkit for extracting conversational features and analyzing social phenomena in conversations. It includes several large conversational datasets along with scripts exemplifying the u…

Stanford NLP Python library for tokenization, sentence segmentation, NER, and parsing of many human languages

Package for causal inference in graphs and in the pairwise settings. Tools for graph structure recovery and dependencies are included.

Open source annotation tool for machine learning practitioners.

Deepparse is a state-of-the-art library for parsing multinational street addresses using deep learning

A comprehensive reference for all topics related to Natural Language Processing

Augmenty is an augmentation library based on spaCy for augmenting texts.

A python package to run contextualized topic modeling. CTMs combine contextualized embeddings (e.g., BERT) with topic models to get coherent topics. Published at EACL and ACL 2021 (Bianchi et al.).