GitHub projects

> An easy-to-use & supercharged open-source AI metadata tracker.

Enterprise-Grade Graph RAG for Secure, On-Premise AI with Verifiable Attribution.

Text preprocessing package for use in NLP tasks.

Track, log, visualize and evaluate your LLM prompts and prompt chains.

A deep learning-based translation library between 50 languages, built with transformers.

A Natural Adversarial Language Processing framework built over Tensorflow.

topic modelling platform.

conversational AI library with many pre-trained Russian NLP models.

Named-entity recognition using neural networks providing state-of-the-art-results

Natural Language Understanding library for intent classification and entity extraction

A python library for accurate and scalable fuzzy matching, record deduplication and entity-resolution.

Reading Wikipedia to answer open-domain questions.

Multilingual text (NLP) processing toolkit.

Transcode sentence (or other sequence) to list of word vector.

A "machine learning framework to automate text-and voice-based conversations."

The Classical Language Toolkit.

Python wrapper for Stanford CoreNLP [Deprecated]

higher-level NLP built on Spacy.

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

Blazing fast, lightweight and customizable fuzzy and semantic text search in Python with fuzzywuzzy/thefuzz compatible API.

Fuzzy String Matching in Python.

Levenshtein and Hamming distance computation. [Deprecated]

Python interface for converting Penn Treebank trees to Stanford Dependencies.

Python bindings for ZPar, a statistical part-of-speech-tagger, constituency parser, and dependency parser for English.

Python binding to Frog, an NLP suite for Dutch. (pos tagging, lemmatisation, dependency parsing, NER)

Python binding to ucto (a unicode-aware rule-based tokenizer for various languages).

Python package that implements a novel white-box machine learning model for text classification, called SS3. Since SS3 has the ability to visually explain its rationale, this package also comes with easy-to-use interactive visualizations tools (online demos).

Python Natural Language Processing Library. General purpose NLP library for Python. Also contains some specific modules for parsing common NLP formats, most notably for FoLiA, but also ARPA language models, Moses phrasetables, GIZA++ alignments.

Text processing tools and wrappers (e.g. Vowpal Wabbit)

Natural language Understanding Toolkit. [Deprecated]

A Chinese segment based on Conditional Random Field.

Another Chinese segmentation library. [Deprecated]

A library for email Spam filtering built on top of NLTK

A library for processing Chinese text.

A sentence aligner, a friendly tool for extracting parallel sentences from comparable corpora. [Deprecated]

A python framework to transform natural language questions to queries in a database query language.

A web mining module for the Python programming language. It has tools for natural language processing, machine learning, among others.

A better version of Jieba, developed by Peking University.

MLX is an array framework for machine learning on Apple silicon, developed by Apple machine learning research.

PyTorch image models, scripts, pretrained weights -- ResNet, ResNeXT, EfficientNet, EfficientNetV2, NFNet, Vision Transformer, MixNet, MobileNet-V3/V2, RegNet, DPN, CSPNet, and more.

as known as L0CV, is a new generation of computer vision open source online learning media, a cross-platform interactive learning framework integrating graphics, source code and HTML. the L0CV ecosystem — Notebook, Datasets, Source Code, and from Diving-in to Advanced — as well as the L0CV Hub.

face recognition system that can be easily integrated into any system without prior machine learning skills. CompreFace provides REST API for face recognition, face verification, face detection, face mask detection, landmark detection, age, and gender recognition and is easily deployed with docker.

Light face detection and recognition system with huge possibilities, based on Microsoft Face API and TensorFlow made for small IoT devices like raspberry pi.

Energy-based machine learning models built upon PyTorch.

Lightly is a computer vision framework for self-supervised learning.

Tensorflow and OpenAI Clarity's Lucid adapted for PyTorch.

A PyTorch implementation of DeepDream. Allows individuals to quickly and easily train their own custom GoogleNet models with custom datasets for DeepDream.

TF-GAN is a lightweight library for training and evaluating Generative Adversarial Networks (GANs).