Reverse Dependencies of spacy

The following projects have a declared dependency on spacy:

• llmetrics — A metrics and evaluation library for LLMs
• llmproxy — no summary
• lm-polygraph — Uncertainty Estimation Toolkit for Transformer Language Models
• lmms-eval — A framework for evaluating large multi-modality language models
• lmproof — Language model powered proof reader for correcting contextual errors in natural language.
• locationtagger — Detect & Extract locations from text or URL and find relationships among locations
• LODlit — Retrieving literal values from LOD
• logai — LogAI is unified framework for AI-based log analytics
• longeval — Prepare your summarization data in a format compatible with the longeval guidelines for human evaluation.
• lora-textnormalization — A text normalization package for general English NLP tasks.
• ludwig-myelin — A deep learning experimentation toolbox
• luna-nlg — Source code for the LUNA project
• lyrics-transcriber — Automatically create synchronised lyrics files in ASS and MidiCo LRC formats with word-level timestamps, using Whisper and lyrics from Genius and Spotify
• lytspel — A Simple Phonetic Respelling for the English Language
• madai — no summary
• magi-dataset — Convenient access to massive corpus of GitHub repositories
• MailClassification — Classify Mail to Cargo or Tonnage
• mailcom — Pseudonymize email content in Romance languages
• maitag — MAIT - Machine-Assisted Intent Tagging
• mapling — no summary
• marian-library — Python wrapper for Marian NMT for Neural Grammar Correction with Error Types
• mask-predictor — A wrapper of BERT to predict the covered word in a sentence
• mathspell — A library for converting numbers to words contextually.
• MatNexus — Library for natural language processing for scientific papers
• maverick-coref-de — co-reference resolution for German using the Maverick system
• maxbot — Maxbot is an open source library and framework for creating conversational apps.
• mc-providers — Search Providers package for Mediacloud
• mdparse — Parsing markdown files for deep learning.
• medcat — Concept annotation tool for Electronic Health Records
• medico — Extract vital medical information from text.
• medkit-lib — A Python library for a learning health system
• MedLytics — A text analysis package for medical text analytics using NLP libraries.
• MedRoom.AI.DataEngineer — A Natural Language Processing Data Engineer
• medspacy-io — A collection of modules to facilitate reading text from various sources and writing to various sources.
• medspacy-quickumls — QuickUMLS is a tool for fast, unsupervised biomedical concept extraction from medical text
• meerkat-ml — Meerkat is building new data abstractions to make machine learning easier.
• meguru-tokenizer — simple tokenizer for tensorflow 2.x and PyTorch
• memory-journal-mcp-server — MCP server for memory journal from local photos (iCloud Photos)
• meno — Topic modeling toolkit for messy text data
• mental-models — Extracts human mental models from text and facilitates mental model comparison and contrasting. (See J Diesner 2003)
• metamart-ingestion — Ingestion Framework for MetaMart
• miade — A set of tools for extracting formattable data from clinical notes stored in electronic health record systems.
• microservice-story-manager — Microservice Story Manager is a Python library for optimizing user story assignments in microservice architectures. It features story and microservice management, genetic algorithm optimization, and visualization tools. The library calculates metrics like coupling and cohesion, allows comparison of optimization strategies, and supports CSV data loading. It aids in microservice design decisions, helping maximize cohesion and minimize coupling in software architectures.
• milanlp — MilaNLP Library
• minapip1 — kjdfdlsjlkdfl
• minapipe — this first test pipe
• minapipe1 — this first test pipe
• mindmeld — A Conversational AI platform.
• misaki — G2P engine for TTS
• ml-swissknife — Reusable ML research primitives for fast prototyping.
• MLEssentials — A comprehensive toolkit that streamlines machine learning development by installing all essential libraries in a single command.
• mllibs — Simplifying Machine Learning
• mlx-audio — MLX-Audio is a package for inference of text-to-speech (TTS) and speech-to-speech (STS) models locally on your Mac using MLX
• mmda — MMDA - multimodal document analysis
• mmkit-features — A multimodal architecture to build multimodal knowledge graphs with flexible multimodal feature extraction and dynamic multimodal concept generation.
• mngdataclean — Text preprocessing package
• model-fkeywords — A Natural Language Processing Library
• modelscope — ModelScope: bring the notion of Model-as-a-Service to life.
• modified-repository-miner — A tool to mine software repositories for defect prediction.
• modlee — modlee package
• mofid-normalizer — first version of Mofid Normalizer
• monapipe — MONAPipe provides natural-language-processing tools for German, implemented in Python/spaCy.
• monarch-py — Python package for interacting with Monarch Initiative knowledge graph
• monito — Tool to monitor and filter news websites and alike.
• monito-tools — Tools for Monito
• moralizer — > Simple tool to get the Moral Foundations counts of a given text.
• moralstrength — A package to predict the Moral Foundations for a tweet or text
• mordecai3 — no summary
• MordinezNLP — Powerfull python tool for modern NLP processing
• MoreThanSentiments — An NLP python package for computing Boilerplate score and many other text features.
• MorphoPreText — A bilingual text preprocessing toolkit for English and Persian.
• mosaic-common-utils — Utils library for Mosaic
• mosaic-utils — Utils library for Mosaic
• motliere — A morphological and linguistically motivated segmentation tool for French !
• MovieChat — Long video understanding
• mozi-ai — 墨子AI:军事人工智能领航者, developed by HSFW
• MrSnippets — A complete collection of commonly used code Snippets in Python
• mudes — Toxic Spans Prediction
• musaddiquehussainlabs — MusaddiqueHussainLabs: Empowering text analytics with advanced tools for comprehensive Natural Language Processing (NLP) and Language Models (LLMs).
• my-torch — A transparent boilerplate + bag of tricks to ease my (yours?) (our?) PyTorch dev time.
• mypackage0917 — A simple example Python package
• MySQL-NLP-CLI — A Python package that allows to use the CLI and Natural Language processing to write MySQL queries.
• naimai — Python library to help with scientific literature research
• nalaf — Natural Language Framework, for NER and RE
• namas — no summary
• namebuster — A tool for generating common username permutations from a list of names, a file, or url, to aid with username enumeration
• NameExtractor — Name Extractor is a small AI program to extract name and gender from characters in text.
• nanga — NLP tasks
• natas — Python library for processing historical English
• nb-phone-extractor — This is a program that takes in Phone Data in a semi-structured format in excel, and returns another excel sheet that shows select details about it
• nb-quality-profile — Tools for profiling Jupyter notebook quality and visualing notebook structure.
• negate — A Python module that negates sentences.
• nemo-curator — Scalable Data Preprocessing Tool for Training Large Language Models
• nemoguardrails — NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.
• NeoMind — Create your own custom AI chatbot package using Groq and Neo4j for knowledge-based responses.
• neon-chatbot-core — Core utilities for Klat chatbots
• ner-annotator — GUI useful to manually annotate text for Named Entity Recognition purposes
• ner-d — Python module for Named Entity Recognition (NER).
• nerpii — A python library to perform NER on structured data and generate PII with Faker
• nerwhal — Find personally identifiable information in German texts using NER and rule based matching.