Packages
Lemmatizes and inflects English words using dictionary lookup and neural network rules, with support for Universal Dependencies and Penn Treebank tags, and optional integration with spaCy.
However, the dormant maintenance status (last update 2022-10-02) means no active development or bug fixes; install only if the current feature set meets your needs…
Normality removes diacritics, punctuation, and other character classes from Unicode text to prepare it for downstream analysis, offering functions like normalize, slugify, and collapse_spaces.
Install it if you need to normalize Unicode text; avoid it only if pyicu is unavailable in your environment and you cannot use an older version.
Normalizes and denormalizes text in Chinese, English, and Japanese using finite state transducers, converting between written and spoken forms with support for character conversions and linguistic preprocessing.
torchtext provides text datasets, preprocessing transforms, and pre-trained models for natural language processing tasks in PyTorch, including tokenizers, vocabulary management, and example workflows.
However, the abandoned maintenance status (paused since September 2023, archived repository) means no new features or dataset support will be added.
Provides a curated dataset of English given names and their associated nicknames, accessible via a Python API with methods to look up nicknames for a name or canonical names for a nickname.
Edlib calculates edit distance (Levenshtein distance) between two sequences and optionally finds the optimal alignment path, supporting global, prefix, and infix alignment modes.
Implements the Metaphone and Double Metaphone phonetic encoding algorithms to generate approximate phonetic codes for words and names, useful for fuzzy matching and handling misspellings.
However, verify compatibility with your Python version first—requires_python is unspecified, and the last release was 2016-08-24.
Extracts emojis and emoticons from text, returning their positions, Unicode names, and meanings in a dictionary format.
However, exercise caution: the project is dormant (last release 2021-08-02), the GPL license terms are unclear, and Python version support is unspecified.
English is a utility library providing English language processing functions for Python, with a single runtime dependency on six.
Validates CoNLL-U format files against Universal Dependencies specifications and scores dependency parsing results from shared tasks.
Efficiently parse and stream-process MediaWiki XML database dumps with memory-conscious iteration and optional distributed processing across multiple files.
Install it if you need to process wiki database exports; skip it if you're not working with MediaWiki XML data.
Udapi is a Python framework for reading, processing, and manipulating Universal Dependencies treebank data in CoNLL-U format.
Detects sentence boundaries in text across many languages using lightweight 8-bit quantized ONNX models, splitting raw text into individual sentences.
Converts text between Simplified and Traditional Chinese using MediaWiki vocabulary tables, supporting regional variants including Mainland, Taiwan, Hong Kong, and Singapore Chinese.
Not recommended for new projects requiring active maintenance or support; consider it for stable, self-contained use cases where regional Chinese text conversion is a…
Converts written-out number words in text to their digit equivalents, handling both formal and informal phrasing across a range of scales and styles.
Install it if you need this conversion; skip it if your input is already numeric.
Vale is a command-line tool for enforcing editorial style guides on text, packaged for Python environments so it can be installed as a dependency without manual setup.
Pynini compiles grammar rules into weighted finite-state transducers and related automata structures, enabling programmatic construction and application of complex linguistic transformations.
Extracts quantities, measurements, and their units from unstructured text, disambiguating between similar units using vector similarity and Wikipedia context.
Simplemma converts inflected word forms to their dictionary base forms (lemmas) across 54 languages using pure Python with no external dependencies or model downloads.
Install it for baseline NLP work, teaching, or low-resource settings; do not install it if you need the highest accuracy and can afford the overhead of neural pipelines.
Reads DAWG (Directed Acyclic Word Graph) files created by the dawgdic C++ library or DAWG Python package, providing pure-Python access without compiled extensions.
Converts numbers to spelled-out text in multiple languages and formats using Unicode CLDR rule-based number formatting (RBNF).
Morphological analyzer and inflection engine for Russian and Ukrainian text, performing part-of-speech tagging and word form generation.
However, be aware that maintenance is dormant—no updates since 2020—so you should verify compatibility with your Python version and consider whether you need active…
Provides the IPAdic Japanese morphological dictionary for use with mecab-python3 or fugashi, enabling Japanese text tokenization and part-of-speech tagging.
Install only if you have a documented reason to use the original IPAdic.
Provides pre-trained morphological analysis models for Korean text processing, enabling tokenization and part-of-speech tagging when installed as a dependency.
Provides Russian morphological dictionaries for the pymorphy2 library, enabling Russian language text analysis and morphological parsing.
However, verify that its dictionary data meets your orthography and morphology standards—no updates have been released since 2020, so it may not reflect recent…
Identifies the language of UTF-8 text using Facebook's pretrained fastText lid.176 model, supporting 176 languages with optional memory-efficient compressed mode.
Install it if you need fast, accurate language identification across 176 languages without external service calls.
Provides intent recognition data and utilities for Home Assistant voice automation, enabling natural language understanding for smart home commands.
Parses natural language sentences into structured intents using YAML-defined templates, slot lists, and expansion rules for Home Assistant voice command recognition.
Extends Python's set class to perform fuzzy string matching using N-gram similarity, allowing efficient searches for similar items in a collection.
However, do not adopt it for security-sensitive applications or if you require ongoing maintenance and updates.
Sumy extracts summaries from HTML pages or plain text using multiple automatic summarization algorithms (LSA, LexRank, Luhn, Edmundson) and provides evaluation tools for summary quality.
Provides Vietnamese language processing tools including tokenization, part-of-speech tagging, and accent manipulation using conditional random fields.
However, verify that scikit-learn and sklearn-crfsuite versions remain compatible with your Python environment, and be aware that no updates have been released since…
PanPhon maps International Phonetic Alphabet (IPA) segments to articulatory phonological feature vectors, enabling programmatic analysis of phonetic and phonological properties of speech sounds.
Wn is a Python library for querying and exploring wordnet data—semantic networks of word meanings, definitions, and relationships—with support for multiple languages and interlingual lookups.
Konoha provides a unified Python interface to multiple Japanese tokenizers (MeCab, Janome, Sentencepiece, and others), plus rule-based tokenizers and sentence splitters, letting you switch between them without rewriting your code.
A Python SDK for the Gladia speech-to-text API, supporting both pre-recorded audio transcription and live streaming transcription with features like diarization, translation, and PII redaction.
Computes Damerau-Levenshtein edit distance between sequences using Cython for high performance, supporting strings, lists, tuples, and other sequence types with optional distance thresholds.
PyArabic provides functions to manipulate Arabic text and letters—detecting character types, removing diacritics, tokenizing into words or sentences, and normalizing Arabic script variants.
However, the abandoned maintenance status means no bug fixes or updates will be forthcoming—do not install if you expect ongoing support or compatibility with future…
Translators provides a unified Python interface to multiple free online translation services, allowing you to translate text across many language pairs without building individual integrations.
Converts Korean Hangul text to romanized (Latin character) representations using configurable linguistic rules.
Parses natural language time expressions (like "May 5th 2:30 in the afternoon") into structured datetime objects, supporting English and German text relative to a reference time.