1.karpathy / minbpe
Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.
Ranked by Attention Score: stars gained over the last 30 complete days
30 repositories by Attention Score · Oct 7, 2026 – Nov 5, 2026 (UTC)
Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.
tiktoken is a fast BPE tokeniser for use with OpenAI's models.
💫 Industrial-strength Natural Language Processing (NLP) in Python
Open-source offline translation library written in Python
TranslatedJieba (结巴, "stutter") Chinese word segmentation
Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities
TranslatedChinese characters to pinyin converter (pypinyin)
VADER Sentiment Analysis. VADER (Valence Aware Dictionary and sEntiment Reasoner) is a lexicon and rule-based sentiment analysis tool that is specifically attuned to sentiments expressed in social media, and works well on texts from other domains.
modest natural-language processing
Seamlessly integrate LLMs into scikit-learn.
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
The Classical Language Toolkit
📐 Compute distance between sequences. 30+ algorithms, pure python implementation, common interface, optional external libs usage.
An NLP library for building bots, with entity extraction, sentiment analysis, automatic language identify, and so more
Self-contained Japanese Morphological Analyzer written in pure Go
An Analysis Toolkit for Natural Language Generation (Translation, Captioning, Summarization, etc.)
TranslatedConvert Chinese characters to pinyin
Natural language detection
🚀 Catalyst is a C# Natural Language Processing library built for speed. Inspired by spaCy's design, it brings pre-trained models, out-of-the box support for training word and document embeddings, and flexible entity recognition models.
Ruby gem to calculate the similarity between texts using tf*idf
A Modern C++ Data Sciences Toolkit
Natural language detection library for Go
natural language processor powered by plugins part of the @unifiedjs collective
Neural question generation using transformers
Pragmatic Segmenter is a rule-based sentence boundary detection gem that works out-of-the-box across many languages.
🔤 Natural language detection for Elixir without AI