awesome-repositories.com
Blog
MCP
awesome-repositories.com

Découvrez les meilleurs dépôts open-source grâce à notre recherche par IA.

ExplorerRecherches sélectionnéesAlternatives open sourceLogiciels auto-hébergésBlogPlan du site
ProjetServeur MCPÀ proposNotre méthodologiePresse
Mentions légalesConfidentialitéConditions d'utilisation
© 2026 Bringes Technology SRL·VAT RO45896025·hello@awesome-repositories.com
·

36 dépôts

Awesome GitHub RepositoriesText Processing Pipelines

Modular workflows for transforming raw text into structured linguistic data through tokenization and normalization.

Distinct from Text Sequence Processing: None of the candidates fit; the existing candidates are either speech-specific or optimization-focused, whereas this is a general-purpose linguistic processing framework.

Explore 36 awesome GitHub repositories matching data & databases · Text Processing Pipelines. Refine with filters or upvote what's useful.

Awesome Text Processing Pipelines GitHub Repositories

Trouvez les meilleurs dépôts grâce à l'IA.Nous recherchons les dépôts les plus pertinents grâce à l'IA.
  • explosion/spacyAvatar de explosion

    explosion/spaCy

    33,688Voir sur GitHub↗

    spaCy is a Python natural language processing framework designed for industrial-scale text processing. It converts raw text into structured data for machine learning pipelines through a combination of statistical language model trainers, transformer-based text processors, and syntactic dependency parsers. The project enables the integration of pretrained transformer architectures to perform complex linguistic analysis and multi-task learning. It also provides a specialized system for neural named entity recognition to identify and categorize key entities within text. The framework covers a b

    Provides modular pipelines that incrementally add linguistic annotations to shared document objects.

    Pythonaiartificial-intelligencecython
    Voir sur GitHub↗33,688
  • voltagent/awesome-claude-code-subagentsAvatar de VoltAgent

    VoltAgent/awesome-claude-code-subagents

    21,906Voir sur GitHub↗

    This project provides a framework for managing multi-agent systems, designed to automate complex software development, infrastructure, and business workflows. It functions as a multi-agent workflow orchestrator that routes tasks to domain-specific workers while maintaining state persistence and infrastructure automation. By leveraging large language models, the system decomposes high-level objectives into actionable plans, ensuring that complex operations are executed with consistency and reliability. The framework distinguishes itself through its hierarchical agent registry and policy-driven

    Constructs scalable text processing workflows for linguistic data transformation.

    Shellai-agent-frameworkai-agent-toolsai-agents
    Voir sur GitHub↗21,906
  • zincsearch/zincsearchAvatar de zincsearch

    zincsearch/zincsearch

    17,862Voir sur GitHub↗

    Zincsearch is a high-performance, self-hosted full-text search engine and database written in Go. It provides a lightweight infrastructure for indexing and searching unstructured text data, specializing in log and event analysis through a schemaless indexing model. The system is designed as a resource-efficient alternative to heavier search infrastructure, featuring an API surface compatible with Elasticsearch for indexing and querying documents. It distinguishes itself by packaging the entire server and its built-in web search interface into a single statically linked binary. The engine cov

    Implements a modular pipeline using tokenizers and filters to prepare raw text for efficient indexing.

    Goelasticsearchgogolang
    Voir sur GitHub↗17,862
  • xenova/transformers.jsAvatar de xenova

    xenova/transformers.js

    16,141Voir sur GitHub↗

    Transformers.js is a JavaScript library and web machine learning framework designed to run pretrained transformer models directly in the browser. It serves as a client-side inference engine and a wrapper for the ONNX Runtime, enabling the execution of multimodal AI tasks on user devices without the need for a backend server. The library distinguishes itself by providing a unified toolkit for processing text, image, and audio data locally. This architecture supports privacy-preserving model inference and reduces latency by performing all computations on the client's hardware. Its capabilities

    Implements structured tokenizers and feature extractors to convert raw multimodal input into numerical tensors.

    JavaScript
    Voir sur GitHub↗16,141
  • qwenlm/qwen3-coderAvatar de QwenLM

    QwenLM/Qwen3-Coder

    15,615Voir sur GitHub↗

    Qwen3-Coder is a specialized large language model designed for software development, technical reasoning, and automated code synthesis. Built on transformer-based sequence modeling, it functions as a multilingual programming assistant capable of generating, completing, and debugging source code across more than one hundred programming languages. The model distinguishes itself through its capacity to process and maintain logical coherence across massive datasets, supporting context windows of up to one million tokens. This allows for repository-scale reasoning, enabling the model to analyze co

    Analyzes extensive codebases and technical documentation using native support for massive token windows.

    Python
    Voir sur GitHub↗15,615
  • nltk/nltkAvatar de nltk

    nltk/nltk

    14,649Voir sur GitHub↗

    This project is a comprehensive Python toolkit designed for natural language processing, research, and education. It functions as a linguistic data processor that provides a standardized framework for managing, cleaning, and analyzing large collections of annotated text corpora and lexical resources. The library distinguishes itself through its integration of both symbolic and statistical methods, allowing users to perform complex tasks ranging from rule-based grammar parsing to machine learning-driven classification. It offers a modular pipeline for text processing, enabling the transformati

    Sequences modular transformation steps like tokenization and normalization to convert raw unstructured text into structured linguistic data.

    Pythonmachine-learningnatural-language-processingnlp
    Voir sur GitHub↗14,649
  • flairnlp/flairAvatar de flairNLP

    flairNLP/flair

    14,378Voir sur GitHub↗

    Flair is a transformer-based natural language processing framework used to build and train models for text classification and sequence tagging. It provides a specialized library for generating contextual text embeddings and performing linguistic analysis. The framework includes dedicated tools for named entity recognition, including the identification of specialized biomedical entities across multiple languages. It further supports entity linking to map identified text mentions to unique entries within general or biomedical knowledge bases. The project covers a broad range of language analys

    Supports processing large collections of documents in bulk using modular linguistic processing workflows.

    Python
    Voir sur GitHub↗14,378
  • nextapps-de/flexsearchAvatar de nextapps-de

    nextapps-de/flexsearch

    13,727Voir sur GitHub↗

    Flexsearch is a full-text search library designed to execute complex indexing and retrieval operations directly within the web browser. By operating entirely on the client side, it enables rapid information lookup without requiring a backend server, ensuring that search functionality remains self-contained and private. The library distinguishes itself through a highly configurable text processing pipeline that allows developers to tailor tokenization and normalization to specific language requirements. To maintain interface responsiveness during large-scale queries, it utilizes background thr

    Applies modular transformation steps like tokenization and normalization to raw input data before it is committed to the index.

    JavaScriptelasticsearchfull-text-searchfulltext-search
    Voir sur GitHub↗13,727
  • nvidia/tensorrt-llmAvatar de NVIDIA

    NVIDIA/TensorRT-LLM

    12,913Voir sur GitHub↗

    TensorRT-LLM is a platform and toolkit designed for compiling, optimizing, and serving transformer-based models on accelerated hardware. It functions as a framework that transforms machine learning models into efficient execution graphs, providing an engine to refine these models for specific hardware to maximize throughput and minimize latency during text generation. The project distinguishes itself through advanced execution strategies that manage the entire inference pipeline. It utilizes kernel-level fusion and static graph execution to optimize mathematical operations and computational f

    Allocates and retains memory for attention mechanisms to support processing long sequences and data reuse.

    Pythonblackwellcudallm-serving
    Voir sur GitHub↗12,913
  • pipecat-ai/pipecatAvatar de pipecat-ai

    pipecat-ai/pipecat

    12,846Voir sur GitHub↗

    Pipecat is a framework and software development kit for building real-time multimodal AI agents and speech-to-speech systems. It utilizes a frame-based data pipeline to route audio, video, and text through a modular sequence of processors, enabling the orchestration of low-latency conversational AI. The project is distinguished by its ability to coordinate complex multimodal services, including speech-to-text, language models, and text-to-speech, within a single pipeline. It features semantic voice activity detection for natural turn-taking, state-machine conversation flows for dialogue manag

    Routes text through modular workflows to be consumed by aggregators, speech services, or processors.

    Pythonaichatbot-frameworkchatbots
    Voir sur GitHub↗12,846
  • hillya51/lunatranslatorAvatar de HIllya51

    HIllya51/LunaTranslator

    12,030Voir sur GitHub↗

    LunaTranslator is a real-time translation tool designed for visual novels and games. It functions as a multi-engine translation hub and text extractor that captures dialogue via memory hooking or optical character recognition to convert it into a target language. The project distinguishes itself through specialized linguistic tools, including a Japanese text analyzer for sentence segmentation and phonetic readings. It also operates as a digital dictionary aggregator, querying multiple online and offline databases simultaneously to provide comprehensive vocabulary definitions for language lear

    Processes raw extracted text through a sequence of cleaning and optimization filters before final output.

    C++galgameocrreverse-engineering
    Voir sur GitHub↗12,030
  • lyogavin/airllmAvatar de lyogavin

    lyogavin/airllm

    11,508Voir sur GitHub↗

    Airllm is a framework designed to execute and fine-tune large language models on consumer-grade hardware. By employing layer-wise model decomposition and memory-efficient loading techniques, the engine enables the operation of massive models that would otherwise exceed available system or video memory. The project distinguishes itself through a suite of optimization strategies that balance memory footprint with performance. It utilizes block-wise weight quantization and asynchronous layer prefetching to reduce resource consumption and hide data transfer latency. Additionally, the framework su

    Analyzes and answers questions based on massive text inputs up to 100,000 tokens by utilizing memory-efficient sequence processing techniques.

    Jupyter Notebookchinese-llmchinese-nlpfinetune
    Voir sur GitHub↗11,508
  • blevesearch/bleveAvatar de blevesearch

    blevesearch/bleve

    10,986Voir sur GitHub↗

    Bleve is a search indexing engine library written in Go, designed to provide full-text search and document retrieval capabilities for embedded application data. It functions as a framework for indexing structured or unstructured information, allowing developers to build searchable collections that support complex query logic and data analysis. The engine distinguishes itself through a pluggable analysis pipeline that normalizes text before indexing, alongside support for vector similarity search to identify semantically related content. It utilizes finite-state transducer automata for efficie

    Provides a configurable pipeline for tokenization and normalization of raw text before indexing.

    Go
    Voir sur GitHub↗10,986
  • huggingface/tokenizersAvatar de huggingface

    huggingface/tokenizers

    10,825Voir sur GitHub↗

    This project is a high-performance library for converting raw text into tokens and IDs for machine learning models. It functions as a fast text encoder and a text preprocessing pipeline designed to transform strings into numerical representations with high throughput for research and production. The library includes a subword tokenizer trainer used to analyze text datasets and create custom vocabularies using algorithms such as byte-pair encoding and wordpiece. It provides capabilities for subword vocabulary training and text alignment, allowing character offsets to be tracked during normaliz

    Utilizes a modular pipeline to sequentially apply normalization, pre-tokenization, and splitting for structured text processing.

    Rustbertgptlanguage-model
    Voir sur GitHub↗10,825
  • stanfordnlp/corenlpAvatar de stanfordnlp

    stanfordnlp/CoreNLP

    10,085Voir sur GitHub↗

    CoreNLP est une bibliothèque Java de traitement du langage naturel conçue pour convertir du texte brut en données structurées. Elle utilise une suite d'annotateurs linguistiques pour analyser le texte via un pipeline, extrayant ainsi les structures grammaticales, les sentiments et les modèles linguistiques. Le projet inclut un moteur de résolution de coréférence qui lie les mentions multiples d'une même entité pour maintenir la cohérence contextuelle entre les documents. Il fournit également des outils de reconnaissance d'entités nommées pour catégoriser les personnes, les entreprises et les lieux, ainsi qu'un étiqueteur morphosyntaxique pour assigner des catégories grammaticales et des formes de base aux mots. La bibliothèque couvre en outre l'analyse de sentiment pour évaluer le ton émotionnel et prend en charge la sérialisation des données linguistiques traitées dans des formats standardisés pour le stockage ou l'échange externe.

    Transforms raw human language text into structured linguistic data through a modular pipeline.

    Java
    Voir sur GitHub↗10,085
  • akavel/upAvatar de akavel

    akavel/up

    8,836Voir sur GitHub↗

    Up is an interactive shell pipeline tool and Linux pipeline builder designed for prototyping text-processing sequences. It provides a terminal user interface for constructing chains of shell commands while displaying real-time data transformations. The tool allows for the iterative development of command sequences with an instant live preview of processing results. Once a sequence is finalized, it functions as a shell script generator that exports the completed pipeline into a reusable script file. The workspace includes capabilities for terminal data exploration and text processing workflow

    Facilitates the creation of complex command chains for filtering and transforming text data.

    Go
    Voir sur GitHub↗8,836
  • tingsongyu/pytorch_tutorialAvatar de TingsongYu

    TingsongYu/PyTorch_Tutorial

    8,018Voir sur GitHub↗

    This project is a comprehensive collection of educational examples and reference implementations for building vision and language models using PyTorch. It serves as a deep learning tutorial covering the end-to-end process of developing neural networks, from initial architecture definition to final production deployment. The repository provides detailed guides on implementing a wide range of domain-specific models, including convolutional neural networks for object detection and segmentation, as well as transformer and recurrent architectures for natural language processing. It emphasizes gene

    Provides routines for filtering sequences and concatenating documents with special tokens for model pre-training.

    Python
    Voir sur GitHub↗8,018
  • stanfordnlp/stanzaAvatar de stanfordnlp

    stanfordnlp/stanza

    7,809Voir sur GitHub↗

    Stanza is a Python natural language processing library designed for tokenization, lemmatization, and dependency parsing across many human languages using neural models. It provides a neural processing pipeline that converts raw text into structured linguistic data objects, alongside a specialized analyzer for extracting medical insights from clinical and biomedical language. The project includes a wrapper that connects Python scripts to Java-based natural language processing tools and remote annotation servers. This enables a bridge for extracting linguistic annotations and analysis data from

    Implements modular workflows that sequence annotators to transform raw text into structured linguistic data.

    Pythonartificial-intelligencecorenlpdeep-learning
    Voir sur GitHub↗7,809
  • soimort/translate-shellAvatar de soimort

    soimort/translate-shell

    7,472Voir sur GitHub↗

    Translate-shell is a command-line translation tool and terminal dictionary client. It allows for the translation of words, phrases, and sentences between multiple languages and provides dictionary definition retrieval and language metadata display directly within the terminal. The tool functions as a shell-based text translator that can process input from standard streams, local files, or URLs. It includes text-to-speech capabilities to play audio pronunciations of source and translated text and can automatically detect the source language of a given string. The system supports interactive s

    Integrates translation and dictionary lookups into shell scripts and pipelines for bulk processing.

    Awk
    Voir sur GitHub↗7,472
  • infrasys-ai/aiinfraAvatar de Infrasys-AI

    Infrasys-AI/AIInfra

    7,414Voir sur GitHub↗

    Splits long sequences into blocks distributed across devices in a ring topology for memory-efficient attention.

    Jupyter Notebookaiinfraaisystem
    Voir sur GitHub↗7,414
Préc.12Suivant
  1. Home
  2. Data & Databases
  3. Text Processing Pipelines

Explorer les sous-tags

  • Long-Context Sequence Processors4 sous-tagsSystems capable of processing massive input token windows through memory-efficient sequence management. **Distinct from Text Processing Pipelines:** Focuses on long-context processing for massive token windows, distinct from general text processing pipelines.
  • Multimodal Pre-Processing1 sous-tagPipelines that convert various data types like text, images, and audio into tensors. **Distinct from Text Processing Pipelines:** Expands beyond text-only processing to include image and audio feature extraction pipelines.
  • Pre-training Processing2 sous-tagsSpecialized text processing for preparing large-scale corpora for model pre-training. **Distinct from Text Processing Pipelines:** Focuses on pre-training specific needs like sequence filtering and document concatenation, unlike general linguistic normalization.