# PyThaiNLP/pythainlp

Thai natural language processing in Python

Repository: https://github.com/PyThaiNLP/pythainlp
Canonical: https://ross.abutalabs.com/products/pythainlp
Homepage: https://pythainlp.org/
Language: Python
License: Apache-2.0
License Family: permissive
Topics: python, thai-nlp, nlp-library, thai-language, natural-language-processing, thai-nlp-library, thai-soundex, soundex, word-segmentation, thai, hacktoberfest, computational-linguistics, text-processing, hacktoberfest-accepted
Last push: 2026-08-20T19:05:13+00:00

## Health v2 (maintenance only)
Score: 98/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 98, release rhythm 98, longevity 100
- inputs: {"age_days": 3723, "days_push": 13, "days_rel": 19, "gap_med": 24.0, "n_releases_24m": 13}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1149, forks 300 (observed 2026-08-28T04:03:46.273066+00:00)

## What it is
PyThaiNLP is a Python library for Thai natural language processing, offering tokenization, POS tagging, transliteration, soundex, spell correction, and related linguistic utilities, comparable to NLTK but focused on Thai. It also ships a small command-line interface (thainlp) and bundled corpora and models under open licenses.

## Use cases
- segment Thai text into words, sentences, and subwords
- part-of-speech tagging for Thai sentences
- romanize or transliterate Thai text to IPA or Latin script
- spell-check and correct Thai words
- generate Thai soundex codes for name matching
- convert numbers to Thai words and format Thai dates
- fix Thai-English keyboard mistyping
- preprocess Thai text for machine learning pipelines

## When to choose
- you need Thai-specific NLP in Python with a mature, well-maintained toolkit
- you want multiple tokenization engines and bundled corpora under permissive licenses
- you need utilities like Thai soundex, collation, or bahttext that general NLP libraries lack

## When to avoid
- your project processes only English or other non-Thai languages
- you need a general-purpose NLP framework with broad multilingual model support
- you require deep-learning model training rather than text processing utilities

## Facets
- artifact type: library
- maturity: active
- function: nlp, parser, sdk
- domain: text-editors
- platform: python, cli, cross-platform
- tags: thai-language, tokenization, word-segmentation, pos-tagging, transliteration, soundex, spell-correction, computational-linguistics, natural-language-processing, localization

## Member repositories
- PyThaiNLP/pythainlp (main) score 98

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:46.273066+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:33:43.361653+00:00, confidence not recorded.
  - readme: https://github.com/PyThaiNLP/pythainlp (fetched 2026-08-28T04:03:46.273066+00:00, sha 261af69074eb)
  - homepage: https://pythainlp.org/ (fetched 2026-08-29T12:38:41.131159+00:00, sha 6819e579a0de)
  - site_page: https://pythainlp.org/about (fetched 2026-08-29T12:38:41.143498+00:00, sha 9c88a8ea94c3)
  - registry_pypi: https://pypi.org/pypi/pythainlp/json (fetched 2026-08-29T12:38:41.144996+00:00, sha 2025ae7cd254)
  - site_page: https://pythainlp.org/resource (fetched 2026-08-29T12:38:41.140139+00:00, sha 5d568c31a6aa)
  - site_page: https://pythainlp.org/FAQ (fetched 2026-08-29T12:38:41.141878+00:00, sha efdea0677c9b)
- Data as of 2026-08-30T08:39:29.467469+00:00.