Open-source alternatives to ToolGood.Words

SnowNLP is a Python library for Chinese natural language processing. It provides tools for text segmentation, sentiment analysis, document classification, and phonetic transliteration. The library includes capabilities for training and saving custom machine learning models for tokenization and sentiment analysis using raw training datasets. It covers a range of linguistic processing areas, including parts of speech tagging, sentence splitting, and text similarity measurement. The toolkit also provides utilities for extracting key information through text summarization and calculating word im

This is a dictionary-based Chinese Pinyin transliteration library used to convert Chinese characters into Pinyin with support for various tone styles and formats. It provides specialized utilities for polyphonic character resolution to manage multiple pronunciations and a generator for extracting the first letter of characters to create searchable index strings. The library includes a formatter for converting names into Pinyin following official international travel document and passport spelling standards. It also features a tool for transforming Chinese text into hyphenated or dotted string

This is a Chinese text segmentation library that converts Chinese characters into their phonetic pinyin representation. It functions as a polyphone disambiguation tool, resolving ambiguous pronunciations for multi-sound characters using word segmentation and context analysis, and also serves as a pinyin sorting utility for ordering Chinese strings alphabetically. The library distinguishes itself through surname-aware pronunciation switching, applying specialized phonetic rules for Chinese surnames with non-standard pronunciations in name contexts. It supports pluggable word segmentation algor

UserScripts is a collection of JavaScript browser userscripts designed to modify website behavior and add custom functionality to web browsers. It serves as a multi-purpose toolset for web page content automation, web interface enhancement, and specialized web scraping and downloading. The project distinguishes itself through a wide range of specialized utilities, including a browser-based text transformer for character encoding and terminology mapping, and tools for bypassing content censorship. It provides advanced web scraping capabilities such as deciphering obfuscated download links, agg

This project is a high-performance Java library and content moderation framework designed to detect and mask prohibited words in text. It utilizes a Deterministic Finite Automaton (DFA) scanner to implement efficient longest-match word detection. The engine distinguishes itself through a text normalization pipeline and noise-filtering preprocessor that standardize character casing, scripts, and widths while removing interspersed special characters to prevent filter evasion. It supports dynamic dictionary management, allowing blacklists and allow-lists to be updated in the background without r

This project provides a collection of processed Chinese conversational datasets and preprocessing workflows designed for training and instruction tuning of large language models. It functions as a training corpus of cleaned, standardized Chinese text formatted as query-answer pairs. The repository includes a preprocessing pipeline and dataset aggregator that combine multiple public chat sources into unified files. These tools normalize text by converting traditional Chinese characters to simplified characters and transforming complex dialogue threads into a standardized sequence of single tur

GoldenDict-ng is a multi-source dictionary application and offline dictionary reader that enables users to search for word definitions across local files, DICT servers, and web sources in a single interface. It functions as a web-based definition browser, rendering entries using a browser engine to support HTML, CSS, and JavaScript for rich content presentation. The project distinguishes itself by integrating with Anki flashcard systems to facilitate language learning workflows and offering specialized translation tools that support clipboard monitoring and character set conversion. It also p

LLM Guard is a security firewall and guardrail framework designed to scan and sanitize inputs and outputs for large language models. It functions as a proxy gateway and security layer to block prompt injections, toxicity, and sensitive data leakage while ensuring that model interactions remain compliant with organizational policies. The system distinguishes itself through a modular scanner pipeline that utilizes local model orchestration to eliminate external network dependencies. It supports real-time security filtering via streaming chunk analysis and implements a fail-fast execution model

This project is a Unicode text repair tool and mojibake correction library designed to fix encoding glitches and restore original characters from mangled strings. It functions as a text encoding detector and a Unicode normalization tool to resolve issues where text has been incorrectly decoded. The library specializes in reversing multi-layered encoding errors and repairing complex mojibake patterns. It includes capabilities for detecting lossy encoding sequences, guessing byte encodings, and decoding non-standard UTF-8 variants. The toolset covers a broad range of text cleaning and normaliz

sqlean is a collection of SQLite extension libraries implemented as C-based shared libraries. It provides a suite of additional scalar and table-valued functions that expand the native capabilities of the SQLite database engine. The project provides specialized toolsets for cryptography, advanced mathematics, networking, and filesystem access. These include binary hashing and encoding, statistical analysis, IP address validation, and the ability to map CSV files or filesystem paths as virtual tables. The library also includes comprehensive text processing tools such as regular expressions, f

TinyPinyin is a Java and Android compatible library used for converting Chinese characters into Pinyin phonetic representations. It provides utilities for Chinese character detection to identify whether text belongs to the Chinese writing system. The library includes a polyphonic character resolver that determines the correct pronunciation for characters with multiple sounds through contextual analysis. It is designed for low memory usage on mobile devices.

Chinese-Vicuna is a Chinese large language model and instruction-following AI based on the LLaMA architecture. It is specifically designed for natural language understanding and generation in the Chinese language, utilizing an instruction-tuned model to follow complex user prompts across conversations. The project provides a LoRA fine-tuning framework and quantization systems to enable model adaptation and inference on consumer hardware. It implements quantized inference to reduce memory usage on both CPUs and GPUs, supported by a low-level C++ implementation to minimize system resource requi

Fengshenbang-LM is a Chinese language model ecosystem and pre-training framework designed for the development and fine-tuning of billion-parameter large language models. It serves as a natural language processing pipeline and cross-modal AI platform capable of generating content across different modalities, including text-to-image generation and protein structure prediction. The project provides a domain-specific model adapter for applying pretrained models to specialized industries such as healthcare, finance, and law. It utilizes a distributed configuration system and data sharding to manag

JioNLP is a Chinese natural language processing toolkit designed for cleaning, normalizing, and extracting structured information from unstructured text. It functions as a linguistic analyzer for Chinese characters and a rule-based named entity extractor, providing a specialized system for sentiment scoring and synthetic data generation for machine learning workflows. The project features a lexicon-based sentiment analysis engine that computes numerical emotional tone scores and a data augmentation library that uses back-translation and synonym replacement to expand training datasets. It incl

LAC is a Chinese lexical analysis engine and toolkit designed for joint word segmentation, part-of-speech tagging, and named entity recognition. It functions as a high-performance system that identifies word boundaries and grammatical categories using trained machine learning models. The project features a lightweight, compiled native runtime that enables on-device natural language processing and embedding into mobile applications. It includes model compression and conversion to optimize for resource-constrained environments and supports multi-threaded parallel execution to increase throughpu

Sensitive-lexicon is a sensitive word detection service and content moderation tool designed to identify prohibited text. It utilizes a curated lexicon of thousands of categorized terms and a fuzzy matching text scanner to detect restricted words and phrases. The project features specialized filters for Chinese language content across political, social, and adult domains. It supports approximate string matching to identify terms that use noise characters or whitespace to evade standard keyword filters. The system includes a network interface for hosting the detection service, allowing for re

Synonyms is a natural language processing library and semantic similarity engine specifically designed for Chinese text. It functions as a word embedding toolkit and tokenizer that extracts semantic meaning and identifies synonyms by calculating the conceptual closeness between words and sentences. The system provides a toolkit for Chinese word embedding and synonym discovery, allowing for the retrieval of semantically similar words to expand vocabulary. It distinguishes itself through a configuration-driven approach to model loading, which supports the integration of custom word embeddings t

This is a Chinese natural language processing toolkit providing a suite of tools for word segmentation, part-of-speech tagging, and named entity recognition. It includes a neural dependency parser for analyzing syntactic and semantic relationships between words and a machine learning training suite for creating custom linguistic models using annotated datasets. The toolkit distinguishes itself through its deployment flexibility, offering a dockerized server and a web service interface that exposes processing capabilities via API. It supports the use of pretrained models and allows for the int

Synonyms is a Chinese natural language processing tool focused on semantic analysis. It provides capabilities for Chinese word segmentation, part-of-speech tagging, and the retrieval of synonyms based on semantic proximity. The project converts words and sentences into numerical vector representations to calculate similarity scores. This allows for the determination of semantic proximity between different phrases and the identification of chatbot intent through sentence comparison. The system also includes tools for automated keyword extraction and importance ranking to identify significant

MNBVC is a dataset pipeline and toolkit designed for the collection, cleaning, and normalization of massive text and code corpora used to train large language models. It provides specialized tools for harvesting source code, commit histories, and repository metadata from version control platforms, alongside a multilingual text corpus collector for gathering parallel text and academic papers. The project distinguishes itself through comprehensive capabilities for processing diverse document types, including a PDF-to-text converter that transforms complex layouts and formulas into structured JS

Trime is a customizable text input framework and engine based on the Rime input method. It enables the entry of characters across multiple languages using phonetic markers and shape-based patterns. The project functions as a cross-platform input method, providing the necessary logic to build and deploy text input tools for both mobile and desktop devices. It also serves as a Chinese text converter for translating traditional Chinese characters into simplified Chinese to create localized resource files.

This project is a CJK input method framework and configuration set designed for the Rime input engine. It provides a comprehensive system of schemas and dictionary packs to optimize Chinese character entry through pinyin and double-pinyin workflows. The framework is distinguished by its use of Lua-powered extensions that add dynamic utilities, such as inline mathematical calculators, automated timestamps, and text formatting, directly to the input interface. It also features refined word libraries and language models specifically tuned to improve prediction accuracy and first-choice hit rates

KnowledgeGraphData is a collection of structured datasets and corpora designed to provide a foundational layer for cognitive intelligence and artificial intelligence systems. It primarily consists of large-scale Chinese knowledge graph datasets, including entity-relation data and NLP training sets used to drive semantic understanding and automated question answering. The project focuses on the construction and export of massive entity-attribute-value graphs, organizing knowledge into portable formats. It provides specialized domain partitioning to tailor information retrieval for professional

Pretrained-Language-Model is a machine learning library and natural language processing toolkit designed for pretraining, tokenizing, and compressing large language models using transformer architectures and specialized optimization techniques. It supports Chinese and multilingual natural language processing tasks, including text classification and conversational response generation. The framework provides specialized capabilities for training large-scale autoregressive and contextual language models, alongside model compression techniques like knowledge distillation and quantization to reduc

This project is a PyTorch-based Chinese text classification framework. It provides a transformer-based pipeline designed to categorize Chinese language sequences into predefined labels using deep learning models. The implementation supports both BERT and ERNIE language models for processing and tagging complex Chinese text. These models are used to perform tasks such as sentiment analysis and general text categorization. The system utilizes transformer-based text encoding and attention-weighted sequence pooling to convert raw characters into document vectors. It employs pre-trained model fin

This is a large-scale collection of curated Chinese text corpora designed for training natural language processing models. The project provides a variety of datasets, including a deduplicated archive of millions of news articles with titles and keywords, high-quality categorized question-and-answer pairs, and parallel translation corpora. The collection includes millions of aligned Chinese and English sentence pairs used for cross-lingual model training and machine translation development. It also contains filtered question-and-answer data organized by label for the construction of knowledge-

Chinese-BERT-wwm is a pre-trained transformer model and encoder designed for Chinese natural language processing. It converts Chinese text into dense vector representations to be used across various natural language processing applications. The model utilizes a whole word masking strategy during pre-training, masking entire words rather than individual characters. This approach is designed to improve the capture of semantic meaning and language structure within Chinese datasets. The project covers a range of downstream tasks including text classification, sequence labeling, and reading compr