apricot implements submodular optimization for the purpose of summarizing massive data sets into minimally redundant subsets that are still representative of the original data. These subsets are useful for both visualizing the modalities in the data and for training accurate machine learning models with just a fraction of the examples and compute.

Gloo is a collective communications library. It comes with a number of collective algorithms useful for machine learning applications. These include a barrier, broadcast, and allreduce.

HDBSCAN - Hierarchical Density-Based Spatial Clustering of Applications with Noise. Performs DBSCAN over varying epsilon values and integrates the result to find a clustering that gives the best stability over epsilon. This allows HDBSCAN to find clusters of varying densities (unlike DBSCAN), and be more robust to parameter selection. HDBSCAN is ideal for exploratory data analysis; it's a fast and robust algorithm that you can trust to return meaningful clusters (if there are any).

Inquirer should ease the process of asking end user questions, parsing, validating answers, managing hierarchical prompts and providing error feedback.

TensorPipe provides a tensor-aware channel to transfer rich objects from one process to another while using the fastest transport for the tensors contained therein.

PyTorch is a Python package that provides two high-level features:

• tensor computation (like NumPy) with strong GPU acceleration;

• deep neural networks (DNNs) built on a tape-based autograd system.

You can reuse Python packages such as NumPy, SciPy, and Cython to extend PyTorch when needed.

Note: currently this package does not provide GPU support.

This package provides a Python implementation of the CMA-ES algorithm and a few related numerical optimization tools.

TensorFlow Lite for Microcontrollers is a port of TensorFlow Lite designed to run machine learning models on DSPs, microcontrollers and other devices with limited memory.

Hmmlearn is a set of algorithms for unsupervised learning and inference of Hidden Markov Models.

This package provides simple access speech to text for using in Linux without being tied to a desktop environment, using the vosk-api. The user configuration lets you manipulate text using Python string operations. It has zero overhead, as this relies on manual activation and there are no background processes. Dictation is accessed manually with nerd-dictation begin and nerd-dictation end commands.

This is a modular Python implementation of t-Distributed Stochastic Neighbor Embedding (t-SNE), a popular dimensionality-reduction algorithm for visualizing high-dimensional data sets.

SpaCy is a library for advanced Natural Language Processing in Python and Cython. It comes with pretrained pipelines and currently supports tokenization and training for 70+ languages. It features state-of-the-art speed and neural network models for tagging, parsing, named entity recognition, text classification and more, multi-task learning with pretrained transformers like BERT, as well as a production-ready training system and easy model packaging, deployment and workflow management.

TorchMetrics is a collection of 100+ PyTorch metrics implementations and an easy-to-use API to create custom metrics. It offers:

• A standardized interface to increase reproducibility

• Reduces boilerplate

• Automatic accumulation over batches

• Metrics optimized for distributed-training

• Automatic synchronization between multiple devices

FANN is a neural network library, which implements multilayer artificial neural networks in C with support for both fully connected and sparsely connected networks.

Gloo is a collective communications library. It comes with a number of collective algorithms useful for machine learning applications. These include a barrier, broadcast, and allreduce.

LinearOperator is a PyTorch package for abstracting away the linear algebra routines needed for structured matrices (or operators).

jaxtyping provides type annotations and runtime checking for shape and dtype of JAX arrays, PyTorch, NumPy, TensorFlow, and PyTrees.

Stanza is a collection of accurate and efficient tools for the linguistic analysis of many human languages. Starting from raw text, Stanza divides it into sentences and words, and then can recognize parts of speech and entities, do syntactic analysis, and more.

This package provides a reimplementation of OpenAI's Whisper model using CTranslate2, which is a inference engine for transformer models.

CTranslate2 is a C++ and Python library for efficient inference with Transformer models.

The project implements a custom runtime that applies many performance optimization techniques such as weights quantization, layers fusion, batch reordering, etc., to accelerate and reduce the memory usage of Transformer models on CPU and GPU.

This package provides a command line interface for Lightning AI services.

This package provides a tool for visualizing live, rich data for Torch and Numpy.

This package provides a speech recognition toolkit based on kaldi. It supports more than 20 languages and dialects - English, Indian English, German, French, Spanish, Portuguese, Chinese, Russian, Turkish, Vietnamese, Italian, Dutch, Catalan, Arabic, Greek, Farsi, Filipino, Ukrainian, Kazakh, Swedish, Japanese, Esperanto, Hindi, Czech, Polish. The program works offline, even on lightweight devices. Portable per-language models are about 50Mb each, and there are much bigger and precise models available.

Vosk API provides a streaming API allowing to use it on-the-fly and bindings for different programming languages. It allows quick reconfiguration of vocabulary for better accuracy, and supports speaker identification beside simple speech recognition.

Uniform Manifold Approximation and Projection is a dimension reduction technique that can be used for visualization similarly to t-SNE, but also for general non-linear dimension reduction.