Wiktionary dump file parser and multilingual data extractor
Python package for WikiMedia dump processing (Wiktionary, Wikipedia etc). Wikitext parsing, template expansion, Lua module execution. For data extraction, bulk syntax checking, error detection, and offline formatting.
A language model trained from scratch through fly-connectome recurrence. ChatFLM: local conversations, live neural state, and controlled language and behavior studies.
Convert LibreOffice Writer Documents to Wikitext markup
Wikicompiler is a fully extensible python library that compile and evaluate text from Wikipedia dump. You can extract text, do text analysis or even evaluate the AST(Abstract Syntax Tree) yourself
Selected data processing scripts including language agnostic multilingual wiktionary parser
Claude Code and Codex skill for AI-tell audits, artifact cleanup, fidelity checks, and restrained prose edits. Local, no API calls.
French Lexicon Ontology.
A Python package to parse and extract data from the German Wiktionary. It allows users to access wikitext content, either by fetching it directly online or by loading a dump file locally.
Seq2Seq model that restores punctuation on English input text.
Complete GPT implementation from scratch with BPE tokenizer, transformer architecture, and trained models on Shakespeare and WikiText. Achieves perplexity 7.84 on WikiText-2 with 12.6M parameters.
A multilanguage bot for publishing featured Wikipedia articles to a Telegram chat/user/channel
BPE tokenizer from scratch on WikiText-2: 30K vocab, special tokens, TemplateProcessing → PreTrainedTokenizerFast
R2IE (Recursive Relativistic Information Engine): a small research-prototype language-model architecture (compressive Mass Compressor + DTF transformation field + Hebbian condensation memory) with a reproducible WikiText-2 benchmark.
A lightweight Python toolkit for turning MediaWiki content into structured, reusable data
LSTM and QRNN Language Model Toolkit for PyTorch (adapted to fast.ai version)
To associate your repository with the wikitext topic, visit your repo's landing page and select "manage topics."