GV

GeezerVison

The World Wide Web, restored to 800 pixels of glory.

Home|About|Gaming cabinet|Archives|How it works|Starter sites

On this site

  • Sign in
  • ActionsCI/CD and automation
  • CodespacesCloud development environments
  • All Features
  • Documentation
  • Training
  • Certifications
  • Build with Copilot
  • Customize Copilot
  • Integrations
  • Trending repos
  • GitHub Sponsors
  • Developer articles
  • Enterprises

This view

  • Original page
  • New address

GeezerVison is showing github.com — Build software better, together

#

unigram

Star

Here are 68 public repositories matching this topic...

Language: All
Filter by language
All 68 Python 28 Jupyter Notebook 12 C# 5 Rust 5 HTML 3 Java 3 JavaScript 2 TypeScript 2 C++ 1 Dart 1
Sort: Most stars
Sort options
Most stars Fewest stars Most forks Fewest forks Recently updated Least recently updated

UnigramDev / Unigram

Star 5.5k

Telegram for Windows

windows xaml telegram universal uwp mtproto unigram fluent-design secret-chats winui tgcalls
  • Updated Nov 11, 2026
  • C#

ollie283 / language-models

Star 85

Build unigram and bigram language models, implement Laplace smoothing and use the models to compute the perplexity of test corpora.

python natural-language-processing smoothing bigrams unigram
  • Updated Jun 24, 2017
  • Python

words / n-gram

Star 83

Get n-grams from text

ngram unigram n-gram pentagram trigram hexagram bigram dugram tetragram heptagram octogram enneagram
  • Updated Nov 1, 2022
  • JavaScript
kitoken

Systemcluster / kitoken

Sponsor
Star 62

Fast tokenizer for language models, compatible with SentencePiece, Tokenizers, Tiktoken and more. Supports BPE, Unigram and WordPiece tokenization in JavaScript, Python and Rust.

nodejs python nlp rust web tokenizer word-segmentation unigram bpe sentencepiece
  • Updated Oct 26, 2026
  • Rust

susantabiswas / Word-Prediction-Ngram

Star 36

Next Word Prediction using n-gram Probabilistic Model with various Smoothing Techniques

nlp prediction trigrams backoff ngrams bigrams language-model unigram good-turing quadgrams knesser-ney-smoothing prediction-ngram ngram-probabilistic-model interpolated-knesser-ney
  • Updated Jul 23, 2018
  • Jupyter Notebook

umran666 / UniqToken

Star 18

High-precision, Byte-Fallback Unigram tokenizer with dual-offset tracking, arithmetic isolation, and multilingual Unicode protection.

nlp rust deep-learning tokenizer help-wanted up-for-grabs hacktoberfest unigram good-first-issue pyo3 subwords byte-fallback
  • Updated Oct 25, 2026
  • Python

sudhanshusks / twitter_bot

Star 14
entropy text-generator unigram bigram-model trigram-model perplexity twitter-chatbot
  • Updated Mar 10, 2018
  • HTML

UnigramDev / unigram.me

Star 9

The Unigram website build with React and Bootstrap.

website pwa landing-page react-router service-worker reactjs bootstrap-4 responsive-design unigram
  • Updated Aug 3, 2017
  • HTML

iAmKankan / Natural-Language-Processing-NLP-Tutorial

Star 9

NLP tutorials and guidelines to learn efficiently

word2vec word-embeddings bow glove stopwords bigrams cbow tokenization stemming lemmatization unigram tf-idf-vectorizer one-hot-encoding
  • Updated Jan 17, 2023

francofrizzo / marcos-bot-js

Star 8

Telegram bot that generates random messages using a Markov chain, now for Node.js

bot telegram telegram-bot markov-chain language-model unigram
  • Updated Jul 19, 2025
  • TypeScript

DmitryAsdre / UnigramTokenization

Star 7

Unigram Tokenization realization from scratch

python from-scratch unigram unigramtokenization
  • Updated Apr 11, 2024
  • Jupyter Notebook

hikmatazimzade / azerbaijani-tokenizer

Star 5

High-Performance Azerbaijani Tokenizers (30% fewer tokens, 40% faster than multilingual alternatives)

nlp ai tokenizer transformers tokenization unigram bpe huggingface azerbaijani text-tokenization azerbaijani-language azerbaijani-nlp
  • Updated Aug 19, 2025
  • Jupyter Notebook

2arian3 / Artificial-Intelligence

Star 5

All AUT's principles and applications of artificial intelligence course projects.

python nlp csp astar pygame backtracking backoff ids sudoku bfs heuristics dls forward-checking unigram degree bigram mrv
  • Updated Feb 11, 2021
  • Python

aliazizii / Who-wrote-this-poem

Star 5

NLP extra project at AUT Artificial Intelligence course (Fall 2020)

nlp unigram bigram backoff-model
  • Updated Feb 15, 2021
  • Python

JunhoKim94 / Word2Vec_Study

Star 4

Word2Vec using Hierarchy Softmax and Negative Sampling with Unigram & Subsampling

word2vec unigram word2vec-study hierarchy-softmax
  • Updated Feb 7, 2020
  • Python

clj0020 / python-web-crawler

Star 3

Python Web Crawler implementing Iterative Deepening Depth Search

web-crawler python3 feature-extraction iterative-deepening-search unigram
  • Updated Aug 24, 2023
  • Python

erfanghasemi / poet_detector

Star 3

We have implemened an NLP Project to recognize the correct poets. In the project, we have used the bigram, unigram and backoff model for smoothing.

nlp smoothing hafez unigram bigram ferdowsi backoff-model molavi
  • Updated Feb 16, 2021
  • Jupyter Notebook

VaasuDevanS / Natural-Language-Processing-Assignments

Star 3

UNB Fall-2018 NLP Assignments 💬

nlp sentiment-analysis baseline bigrams language-models hidden-markov-model python27 unb unigram information-retrieval-based-chatbot
  • Updated Feb 25, 2019
  • Python

motiurinfo / sentiment_classification

Star 3

Performance evaluation of sentiment classification on movie reviews

natural-language-processing sentiment classification tf-idf bigrams unigram ensemble-machine-learning
  • Updated May 26, 2018
  • Python

AdrienPoupa / comp6721

Sponsor
Star 2

COMP6721: Introduction to Artificial Intelligence Assignments (GOFAI, Machine Learning, NLP)

nlp intelligence ai artificial ngram scikit unigram concordia bigram comp6721 comp472
  • Updated Dec 7, 2018
  • HTML

Add this topic to your repo

To associate your repository with the unigram topic, visit your repo's landing page and select "manage topics."

Learn more

You are visitor 01402503 — GeezerVison does not store the pages you look up.
Best viewed with Netscape Navigator 4.7 or Internet Explorer 6 at 800×600. No cookies required.