A deep learning library containing thousands of pre-trained models on different tasks. The goto place for anything related to Large Language Models.
PythonApache License 2.0active
MachineLearning Natural Language Processing
Search all MachineLearning projects →40 projectsPython › Natural Language Processing
- 28%active
- 10%steady
- 20%slowing
- 42%dormant
Natural Language Processing
Chinese Words Segmentation Utilities.
PythonMIT Licenseslowing
Industrial strength NLP with Python and Cython.
PythonMIT Licenseactive
A framework for building industrial-strength applications with Transformer models and LLMs.
PythonApache License 2.0active
A "machine learning framework to automate text-and voice-based conversations."
PythonApache License 2.0active
Fuzzy String Matching in Python.
PythonGNU General Public License v2.0dormantarchived
A web mining module for the Python programming language. It has tools for natural language processing, machine learning, among others.
PythonBSD 3-Clause "New" or "Revised" Licenseactive
A better version of Jieba, developed by Peking University.
PythonMIT Licensedormant
A library for processing Chinese text.
PythonMIT Licensedormant
A python library for accurate and scalable fuzzy matching, record deduplication and entity-resolution.
PythonMIT Licenseslowing
Reading Wikipedia to answer open-domain questions.
PythonOtherslowingarchived
Natural Language Understanding library for intent classification and entity extraction
PythonApache License 2.0dormant
Multilingual text (NLP) processing toolkit.
PythonOtherslowing
higher-level NLP built on Spacy.
PythonOtherslowing
a python library for doing approximate and phonetic matching of strings.
Jupyter NotebookMIT Licenseactive
Named-entity recognition using neural networks providing state-of-the-art-results
PythonMIT Licensedormant
A python framework to transform natural language questions to queries in a database query language.
PythonOtherdormant
The simplest way to run an LLM locally. Supports tool calling and grammar constrained sampling.
RustEuropean Union Public License 1.2active
The Classical Language Toolkit.
PythonMIT Licenseactive
topic modelling platform.
C++Othersteady
Python wrapper for Stanford CoreNLP [Deprecated]
PythonGNU General Public License v2.0dormant
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.
PythonGNU General Public License v3.0slowing
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).
PythonMIT Licensesteady
Enterprise-Grade Graph RAG for Secure, On-Premise AI with Verifiable Attribution.
Pythonactive
A Chinese segment based on Conditional Random Field.
PythonOtherdormant
Text processing tools and wrappers (e.g. Vowpal Wabbit)
Jupyter NotebookOtherdormant
A library for email Spam filtering built on top of NLTK
PythonGNU General Public License v3.0dormant
Python binding to C++ library for extracting and working with basic linguistic constructions such as n-grams and skipgrams in a quick and memory-efficient way.
C++GNU General Public License v3.0steady
A sentence aligner, a friendly tool for extracting parallel sentences from comparable corpora. [Deprecated]
PythonOtherdormant
Natural language Understanding Toolkit. [Deprecated]
Cdormant
Levenshtein and Hamming distance computation. [Deprecated]
COtherdormant
Another Chinese segmentation library. [Deprecated]
PythonBSD 3-Clause "New" or "Revised" Licensedormant
Python interface for converting Penn Treebank trees to Stanford Dependencies.
Pythondormant
Blazing fast, lightweight and customizable fuzzy and semantic text search in Python with fuzzywuzzy/thefuzz compatible API.
PythonMIT Licenseslowing
Python binding to Frog, an NLP suite for Dutch. (pos tagging, lemmatisation, dependency parsing, NER)
CythonGNU General Public License v3.0active
Python bindings for ZPar, a statistical part-of-speech-tagger, constituency parser, and dependency parser for English.
PythonMIT Licensedormantarchived
Python binding to ucto (a unicode-aware rule-based tokenizer for various languages).
Cythonactive
A Natural Adversarial Language Processing framework built over Tensorflow.
PythonApache License 2.0steady
Transcode sentence (or other sequence) to list of word vector.
PythonMIT Licensedormantarchived
Text preprocessing package for use in NLP tasks.
PythonMIT Licenseslowing
Back to Awesome MachineLearningSearch Awesome MachineLearning →