Skip to main content

probabilistic spell checker

Project description

Probabilistic Spell Checker in Python

Spell checker based on edit distance (Levenshtein-ish) and word frequency in a training corpus.

For theoretical background, see Peter Norvig's article,

Comes with a dictionary trained from German Wikipedia articles.


import json
import re
import probspellchecker

spellchecker = probspellchecker.ProbabilisticSpellChecker(
    word_whitelist=["my", "custom", "wordlist"],

text = "lorem ipsum whatever"
for word in re.findall(r"\w+", text):
    correction = spellchecker.correction(word.lower())
    if correction:

Word counts is just that, a dict with word to count mapping. To build your own dictionaries, see and You may also specify a whitelist of words that should just be accepted by the spell checker, which is useful if your name is not in the dictionary.

If your language sports special characters like the German umlauts, you might need to pass an additional charset parameter which is a string with all allowed characters of your language, to the ProbabilisticSpellChecker. This is then used to generate candidate words.


If the logging annoys you, just shut it up:

spell_log = logging.getLogger("probspellchecker")
spell_log.setLevel(logging.ERROR)  # log only errors

Project details

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

probspellchecker-0.1.3.tar.gz (4.2 kB view hashes)

Uploaded source

Built Distribution

probspellchecker-0.1.3-py3-none-any.whl (5.4 kB view hashes)

Uploaded py3

Supported by

AWS AWS Cloud computing Datadog Datadog Monitoring Facebook / Instagram Facebook / Instagram PSF Sponsor Fastly Fastly CDN Google Google Object Storage and Download Analytics Huawei Huawei PSF Sponsor Microsoft Microsoft PSF Sponsor NVIDIA NVIDIA PSF Sponsor Pingdom Pingdom Monitoring Salesforce Salesforce PSF Sponsor Sentry Sentry Error logging StatusPage StatusPage Status page