Split large Markdown files into token-bounded chunks for LLM context windows
A package for extracting keywords from large text very quickly (much faster than regex and the original flashtext package
Identification and conversion functions for Chinese text processing
('Core libraries for natural language processing',)
Omnilingual ASR Modeling Library
A command to manage a header section for a source code tree
Aspose.PSD for Python via .NET is a standalone API to read, write, process, convert Adobe Photoshop PSD, PSB formats without needing to install Adobe Photoshop® and AI files without Adobe Illustrator®
Python binding for nlpO3 Thai language processing library in Rust
Low-precision BF16/FP16 deep learning optimizer (LuminaV) and text data processing engine with native Rust SIMD, Vulkan, and Triton acceleration.
A neural network intent parser
A fast Voice Activity Detection and Transcription System
Fast CPU/GPU ONNX inference for GLiNER, GLiNER2, GLiClass, GLiFormer, and System One.
The goal of the Indic NLP Library is to build Python based libraries for common text processing and Natural Language Processing in Indian languages. This fork is specialized for IndicTrans2.
Phrase Tree from Natural Language Toolkit
Next-generation Punkt sentence and paragraph boundary detection with zero dependencies
Extract structured data and insights from documents using LLMs and decision models
openai/whisper speech to text model + extra features
A text-to-intent parsing framework.
Python ctypes bindings for reliq
Any Texts Statistics: the language-independent core of text statistics libraries
Lao Natural Language Processing library
A high-accuracy, rule-based Sentence Boundary Detector (SBD) with a drop-in adapter for pysbd, delivering faster and more accurate segmentation.
GP regression + BALD active-learning engine over text embeddings, shared by OpenOutFind and OpenOutNews.
Probabilistically split concatenated words. Now with more functionality and languages!
Standalone, standard-library-only multilingual text normalization for TTS
SMASHED is a toolkit designed to apply transformations to samples in datasets, such as fields extraction, tokenization, prompting, batching, and more. Supports datasets from Huggingface, torchdata iterables, or simple lists of dictionaries.
Open Source Thai Text-to-speech library in Python
A library for calculating a variety of features from text using spaCy
Python interface for eunjeon project & mecab based morphological analyzer.
Real-time processing and delivery of sentences from a continuous stream of characters or text chunks.
Extract complete video transcripts — speech AND on-screen text — from TikTok, YouTube, Instagram and more.
Convert technical books (native-text PDFs) into clean, chapter-split, LLM-ready Markdown using a dual-pass MinerU pipeline plus fidelity-preserving post-processing.
Python port of open source text processing library for Turkish, zemberek-nlp
Algorithmic text humanization with AI detection, tone analysis, paraphrasing, and spinning — 38-stage pipeline, 25 languages, SentenceValidator™, PHANTOM™
A simple standard for sharing literal mappings
Nonsense String Evaluator
Text processing with pandas DataFrames.
Linear-time regex engine for Python - no catastrophic backtracking, no ReDoS, with the native engine bundled in the wheel.
Python bindings for MeTA
Extended Python Standard Library
A high-level NLP toolkit built on top of modern LLMs.
Tamil language text processing tools for Python v3
Speaker Helper — speech synthesis that runs in your process: say a sentence, stream a reply, or narrate a document with the timed track that lets a page follow along. Kokoro by default (no server), voice cloning through OpenVoice and Chatterbox. The inverse of vocal-helper: text in, speech out. Library + CLI + REST API + MCP + skill, with a built-in evaluation gate.
A text-to-intent parsing framework.
Unified Next-Gen Hardware Orchestration & AI Acceleration Runtime for Mobile & Edge