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.

This package enables you to deserialize Lua torch-serialized objects from Python.

This package provides Autograd-compatible approximations to the gamma family of functions.

This package provides fast machine learning algorithms including matrix factorization and divisive clustering for large sparse and dense matrices.

Scikit-rebate is a scikit-learn-compatible Python implementation of ReBATE, a suite of Relief-based feature selection algorithms for Machine Learning. These algorithms excel at identifying features that are predictive of the outcome in supervised learning problems, and are especially good at identifying feature interactions that are normally overlooked by standard feature selection algorithms.

This package provides easy download of thousands of pretrained models to perform tasks on different modalities such as text, vision, and audio.

These models can be applied on:

• Text, for tasks like text classification, information extraction, question answering, summarization, translation, and text generation, in over 100 languages.

• Images, for tasks like image classification, object detection, and segmentation.

• Audio, for tasks like speech recognition and audio classification.

Transformer models can also perform tasks on several modalities combined, such as table question answering, optical character recognition, information extraction from scanned documents, video classification, and visual question answering.

This package provides APIs to quickly download and use those pretrained models on a given text, fine-tune them on your own datasets and then share them with the community. At the same time, each Python module defining an architecture is fully standalone and can be modified to enable quick research experiments.

Transformers is backed by the three most popular deep learning libraries — Jax, PyTorch and TensorFlow — with a seamless integration between them.

Kaldi is an extensible toolkit for speech recognition written in C++.

This package provides a Python library for probabilistic modeling and inference.

A Python library for reading and writing GGUF & GGML format ML models.

ggml is a ML library written in C and C++ with a focus on transformer inference, similar to ML libraries such as PyTorch and TensorFlow.

Lap is a linear assignment problem solver using Jonker-Volgenant algorithm for dense (LAPJV) or sparse (LAPMOD) matrices.

XGBoost is an optimized distributed gradient boosting library designed to be highly efficient, flexible and portable. It implements machine learning algorithms under the Gradient Boosting framework. XGBoost provides a parallel tree boosting (also known as GBDT, GBM) that solve many data science problems in a fast and accurate way.

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).

SentencePiece is an unsupervised text tokenizer and detokenizer mainly for Neural Network-based text generation systems where the vocabulary size is predetermined prior to the neural model training. SentencePiece implements subword units---e.g., byte-pair-encoding (BPE) and unigram language model---with the extension of direct training from raw sentences. SentencePiece allows us to make a purely end-to-end system that does not depend on language-specific pre- or post-processing.

paramz is a lightweight parameterization framework for parameterized model creation and handling. Its features include:

• Easy model creation with parameters.

• Fast optimized access of parameters for optimization routines.

• Memory efficient storage of parameters (only one copy in memory).

• Renaming of parameters.

• Intuitive printing of models and parameters.

• Gradient saving directly inside parameters.

• Gradient checking of parameters.

• Optimization of parameters.

• Jupyter notebook integration.

• Efficient storage of models, for reloading.

• Efficient caching.

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.

MNN is a deep learning framework. It supports inference and training of deep learning models for inference and training on-device.

frugally-deep is a header-only C++ library for inference of Keras machine learning models on a single CPU core.

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.

This package provides a machine learning library of popular datasets, model architectures, and common transformations to apply python-pytorch in the audio domain.

Visualization and NeuroML import/export tools for the Brian 2 simulator.

QNNPACK is a library for low-precision neural network inference. It contains the implementation of common neural network operators on quantized 8-bit tensors.

This package provides the main server that Magic-Wormhole clients connect to. The server performs store-and-forward delivery for small key-exchange and control messages. Bulk data is sent over a direct TCP connection, or through a transit-relay.

Magic-Wormhole is a library and a command-line tool named wormhole, which makes it possible to securely transfer arbitrary-sized files and directories (or short pieces of text) from one computer to another. The two endpoints are identified by using identical "wormhole codes": in general, the sending machine generates and displays the code, which must then be typed into the receiving machine.

The codes are short and human-pronounceable, using a phonetically-distinct wordlist. The receiving side offers tab-completion on the codewords, so usually only a few characters must be typed. Wormhole codes are single-use and do not need to be memorized.