NeMo text processing for ASR and TTS

Ultra-fast, zero-copy text normalization for Rust NLP pipelines & tokenizers

Text Normalization on Learner Texts (South Tyrolean German as a L2)

🧹 Python package for text cleaning

Digestion Algorithm in Hierarchical Symbolic Forests: A Fast Text Normalization Algorithm and Semantic Parsing Framework for Specific Scenarios and Lightweight Deployment

A modern, actively maintained contractions library. Expands English contractions (you're → you are) with improved performance, type safety, and features like bulk dictionary imports and JSON loading. Includes 100% test coverage, full type hints, and works with both pip and uv.

Useful String extensions to save you time in production.

Comprehensive benchmark of OpenAI Whisper models for Bosnian, Croatian, and Serbian languages. Includes pipelines for audio transcription, rigorous text normalization, Levenshtein distance evaluation, and LLM-based post-processing.

Japanese text normalizer for mecab-neologd

Unicode-safe text cleaning & typographic normalization for Rust

Modern .NET 9 / C# 13 library to normalize text (emojis, currency, numbers, abbreviations, chat slang) for consistent and natural Text-to-Speech (TTS) synthesis, ideal for stream chat/donations.

Simple tool to check if Unicode text files are Unicode-normalized

Soe Vinorm: An Effective Text Normalization Toolkit for converting Vietnamese text to its spoken form.

Pipeline Python pour enrichir un dataset Arabe (MSA) → Darija (MA) depuis livres PDF & transcriptions YouTube ; normalisation, segmentation par tokens, génération (OpenAI ou règles) et export JSON. Projet de stage d’application chez YaneCode Digital.

A robust service that extracts and classifies financial amounts from medical bills and receipts using Tesseract.js OCR, normalization, and AI-powered context classification with Gemini API fallback.

Demonstrating specialized NLP preprocessing packages (lightlemma, emoticon-fix, contraction-fix) through Twitter sentiment analysis. Achieves 97% accuracy with PyTorch LSTM + attention model.

X.com Social Network Topic-Sentiment Analyzer - application that scrapes Twitter/X data, performs Polish-language text normalization and lemmatization, builds topic models with MALLET, and runs sentiment analysis for downstream analytics. Created as a project for Master Thesis.

Pipeline para finetuning automático de modelos de Text to Speech.

Nascanna idir Foclóir Uí Dhónaill agus DIL

Ferramentas úteis para aplicações de Text To Speech: normalização de textos, construção automática de dataset e métricas de avaliação.