Python NLP-BERT-derived Resources

bytepiece Implementation of Su's bytepiece. Bytepiece is a new tokenize method, which uses UTF-8 Byte as unigram to process text. It needs little prep

Sentence Transformers in Burn This library provides an implementation of the Sentence Transformers framework for computing text representations as vec

af-rs Interact with the Portfolio protocol using Rust models to abstract the underlying pools. What we want: Given a uniswap pool with two tokens and

llama-node Large Language Model LLaMA on node.js This project is in an early stage, the API for nodejs may change in the future, use it with caution.

ChatGPT Rust Library A Rust library for interacting with OpenAI's ChatGPT API. This library simplifies the process of making requests to the ChatGPT A

Quickner ⚡ A simple, fast, and easy to use NER annotator for Python Quickner is a new tool to quickly annotate texts for NER (Named Entity Recognition

🐍 python-vibrato 🎤 Vibrato is a fast implementation of tokenization (or morphological analysis) based on the Viterbi algorithm. This is a Python wra

SQLBench-DS Overview SQLBench-DS is a SQL benchmark derived from TPC-DS under the terms of the Transaction Processing Council's Fair Use Policy. This

Vidyut मा भूदेवं क्षणमपि च ते विद्युता विप्रयोगः ॥ Vidyut is a lightning-fast toolkit for processing Sanskrit text. Vidyut aims to provide standard co

Bracket QOS - Open Source Edition This project is based on the excellent LibreQOS project. It is hoped that this can be useful for the upstream projec

🐍 python-vaporetto 🛥 Vaporetto is a fast and lightweight pointwise prediction based tokenizer. This is a Python wrapper for Vaporetto. Installation

cutters A rule based sentence segmentation library. 🚧 This library is experimental. 🚧 Features Full UTF-8 support. Robust parsing. Language specific

pithy 0.1.0 - an absurdly fast, strangely accurate, summariser Quick example: pithy -f your_file_here.txt --sentences 4 --help: Print this help messa

tongrams-rs: Tons of N-grams in Rust This is a Rust port of tongrams to index and query large language models in compressed space, in which the data s

Pleco Pleco is a chess Engine & Library derived from Stockfish, written entirely in Rust. This project is split into two crates, pleco, which contains

Speak Speak is a simple, easy to use Natural Language Processor (NLP) written in Rust. Why use Speak? Speak uses a custom engine, and to setup you jus

SyntaxDot Introduction SyntaxDot is a sequence labeler and dependency parser using Transformer networks. SyntaxDot models can be trained from scratch

About Stop words are words that don't carry much meaning, and are typically removed as a preprocessing step before text analysis or natural language p

Demo BERT ONNX server written in rust This demo showcase the use of onnxruntime-rs on BERT with a GPU on CUDA 11 served by actix-web and tokenized wit

SloWord2Vec This is a naive implementation of Word2Vec implemented in Rust. The goal is to learn the basic principles and formulas behind Word2Vec. BT

sudachi.rs - English README 2021-12-09 UPDATE: 0.6.2 Release Try it: pip install --update 'sudachipy=0.6.2' sudachi.rs is a Rust implementation of Su

NewsAggregator We live in an era where both the demand and quantity of information are enormous. However, the way we store and access that information

cargo-spellcheck Check your spelling with hunspell and/or nlprule. Use Cases Run cargo spellcheck --fix or cargo spellcheck fix to fix all your docume

CREATURE FEATUR(ization) A crate for polymorphic ML & NLP featurization that leverages zero-cost abstraction. It provides composable n-gram combinator

bertml High-level non-blocking Deno bindings to the rust-bert machine learning crate. Guide Introduction The ModelManager class manages the FFI bindin

ethers-structopt Provides ethers-compatible Structopt derives, useful for building Ethereum CLIs. Contributing Pull requests are welcome. For major ch

Firefly Telegram Bot Fireflies are free, so beautiful. (Les lucioles sont libres, donc belles.) ― Charles de Leusse, Les Contes de la nuit This is a s

🛥 VAporetto: POintwise pREdicTion based TOkenizer Vaporetto is a fast and lightweight pointwise prediction based tokenizer. Overview This repository

Untanglr Untanglr takes in a some mangled words and makes sense out of them so you dont have to. It goes through the input and splits it probabilistic

txtai: AI-powered search engine for Rust txtai executes machine-learning workflows to transform data and build AI-powered text indices to perform simi

fasttext-rs fastText Rust binding Installation Add it to your Cargo.toml: [dependencies] fasttext = "0.6" Add extern crate fasttext to your crate root

Yoin - A Japanese Morphological Analyzer yoin is a Japanese morphological analyze engine written in pure Rust. mecab-ipadic is embedded in yoin. :) $

2021-07-07 UPDATE: The official Sudachi team will take over this project (cf. 日本語形態素解析器 SudachiPy の 現状と今後について - Speaker Deck) sudachi.rs An official S

nlp Rust-nlp Implemented algorithm Distance Levenshtein (Explanation) Jaro / Jaro-Winkler (Explanation) Phonetics Soundex (Explanation) Metaphone (Exp

Rust Stemmers This crate implements some stemmer algorithms found in the snowball project which are compiled to rust using the rust-backend of the sno

Treebender A symbolic natural language parsing library for Rust, inspired by HDPSG. What is this? This is a library for parsing natural or constructed

RustBERTa-SNLI A Rust implementation of a RoBERTa classification model for the SNLI dataset, with support for fine-tuning, predicting, and serving. Th

BlingFire in Rust blingfire is a thin Rust wrapper for the BlingFire tokenization library. Add the library to Cargo.toml to get started cargo add blin

lumberjack Read and process constituency trees in various formats. Install: From crates.io: cargo install lumberjack-utils From GitHub: cargo install

DeepFrog - NLP Suite Introduction DeepFrog aims to be a (partial) successor of the Dutch-NLP suite Frog. Whereas the various NLP modules in Frog wre b

Rust SBert Rust port of sentence-transformers using rust-bert and tch-rs. Supports both rust-tokenizers and Hugging Face's tokenizers. Supported model

vtext NLP in Rust with Python bindings This package aims to provide a high performance toolkit for ingesting textual data for machine learning applica

nlprule A fast, low-resource Natural Language Processing and Error Correction library written in Rust. nlprule implements a rule- and lookup-based app

rust-bert Rust native Transformer-based models implementation. Port of Hugging Face's Transformers library, using the tch-rs crate and pre-processing

Provides an implementation of today's most used tokenizers, with a focus on performance and versatility. Main features: Train new vocabularies and tok

Whatlang Natural language detection for Rust with focus on simplicity and performance. Content Features Get started Documentation Supported languages

tiny-keccak An implementation of Keccak derived functions specified in FIPS-202, SP800-185 and KangarooTwelve. Documentation The Keccak-f[1600] permut

Provides an implementation of today's most used tokenizers, with a focus on performance and versatility. Main features: Train new vocabularies and tok