An open API service providing package, version and dependency metadata of many open source software ecosystems and registries.

crates.io "nlp" keyword

View the packages on the crates.io package registry that are tagged with the "nlp" keyword.

tekken-rs 0.1.1
Rust implementation of Mistral Tekken tokenizer with audio support
2 versions - Latest release: about 1 hour ago - 146 downloads total - 0 stars on GitHub - 1 maintainer
kalosm-model-types 0.4.0 💰
Shared types for Kalosm models
1 version - Latest release: 6 months ago - 2.9 thousand downloads total - 1,950 stars on GitHub - 1 maintainer
kalosm-language-model 0.4.1 💰
A common interface for language models/transformers
9 versions - Latest release: 5 months ago - 6 dependent packages - 15 thousand downloads total - 938 stars on GitHub - 1 maintainer
kalosm 0.4.0 💰
A simple interface for pretrained AI models
8 versions - Latest release: 6 months ago - 12.9 thousand downloads total - 472 stars on GitHub - 1 maintainer
kalosm-learning 0.4.0 💰
A simplified machine learning library for building off of pretrained models.
8 versions - Latest release: 6 months ago - 7.85 thousand downloads total - 938 stars on GitHub - 1 maintainer
kalosm-sample 0.4.1 💰
A common interface for token sampling and helpers for structered llm sampling
7 versions - Latest release: 5 months ago - 5 dependent packages - 13.3 thousand downloads total - 938 stars on GitHub - 1 maintainer
kalosm-parse-macro 0.4.1 💰
A macro to derive kalosm parsing traits
4 versions - Latest release: 5 months ago - 8.75 thousand downloads total - 938 stars on GitHub - 1 maintainer
kalosm-learning-macro 0.4.0 💰
A macro to derive kalosm learning traits
6 versions - Latest release: 6 months ago - 1 dependent package - 6.24 thousand downloads total - 938 stars on GitHub - 1 maintainer
opus-parse 0.0.3
Library to parse OPUS
3 versions - Latest release: over 7 years ago - 4.43 thousand downloads total - 1 stars on GitHub - 1 maintainer
jieba-macros 0.7.1 💰
jieba-rs proc-macro
1 version - Latest release: 7 months ago - 92.9 thousand downloads total - 835 stars on GitHub - 1 maintainer
Top 4.6% on crates.io
jieba-rs 0.7.4 💰
The Jieba Chinese Word Segmentation Implemented in Rust
45 versions - Latest release: 15 days ago - 15 dependent packages - 303 dependent repositories - 929 thousand downloads total - 835 stars on GitHub - 1 maintainer
sakurs-core 0.1.0 💰
High-performance sentence boundary detection using Delta-Stack Monoid algorithm
1 version - Latest release: about 19 hours ago - 0 downloads total - 1 stars on GitHub - 1 maintainer
sakurs-cli 0.1.0 💰
Command-line interface for Sakurs sentence boundary detection
1 version - Latest release: about 19 hours ago - 0 downloads total - 1 stars on GitHub - 1 maintainer
myanmar_util 0.1.0
A collection of tools for processing Myanmar text including syllable breaking and other utilities
1 version - Latest release: 3 months ago - 451 downloads total - 1 stars on GitHub - 1 maintainer
abbreviation_extractor 0.1.4
A library for extracting abbreviations from text.
5 versions - Latest release: 11 months ago - 5.37 thousand downloads total - 1 stars on GitHub - 1 maintainer
nlprule-build 0.6.4
Build tools for a fast, low-resource Natural Language Processing and Error Correction library.
12 versions - Latest release: over 4 years ago - 2 dependent packages - 3 dependent repositories - 77.7 thousand downloads total - 639 stars on GitHub - 1 maintainer
Top 8.8% on crates.io
nlprule 0.6.4
A fast, low-resource Natural Language Processing and Error Correction library.
14 versions - Latest release: over 4 years ago - 4 dependent packages - 4 dependent repositories - 88.3 thousand downloads total - 639 stars on GitHub - 1 maintainer
treebender 0.1.1
An HDPSG inspired symbolic NLP library for Rust
2 versions - Latest release: over 4 years ago - 2.57 thousand downloads total - 55 stars on GitHub - 1 maintainer
kalosm-language 0.4.1 💰
A set of pretrained language models
11 versions - Latest release: 5 months ago - 1 dependent package - 15.6 thousand downloads total - 938 stars on GitHub - 1 maintainer
rphi 0.3.2 💰
A simple interface for Phi models
5 versions - Latest release: 12 months ago - 1 dependent package - 8.68 thousand downloads total - 938 stars on GitHub - 1 maintainer
rbert 0.4.0 💰
A simple interface for Bert embeddings
7 versions - Latest release: 6 months ago - 2 dependent packages - 11.9 thousand downloads total - 938 stars on GitHub - 1 maintainer
kalosm-llama 0.4.2 💰
A simple interface for Llama models
11 versions - Latest release: 30 days ago - 2 dependent packages - 14.7 thousand downloads total - 938 stars on GitHub - 1 maintainer
bistring 0.0.0
Bidirectionally transformed strings
1 version - Latest release: about 4 years ago - 1.52 thousand downloads total - 367 stars on GitHub - 1 maintainer
tokeneer 0.1.0
Another tokenizer crate
4 versions - Latest release: 5 months ago - 3.88 thousand downloads total - 1 stars on GitHub - 1 maintainer
seal 0.1.6
Implementation of Needleman-Wunsch & Smith-Waterman sequence alignment.
7 versions - Latest release: about 1 month ago - 1 dependent package - 1 dependent repositories - 21.5 thousand downloads total - 21 stars on GitHub - 1 maintainer
simstring_rust 0.3.0
A native Rust implementation of the SimString algorithm
9 versions - Latest release: 24 days ago - 3.04 thousand downloads total - 1 stars on GitHub - 1 maintainer
lexmatch 0.3.0
This is a simple lexicon matching tool that, given a lexicon of words or phrases, identifies all ...
3 versions - Latest release: about 1 year ago - 3.61 thousand downloads total - 2 stars on GitHub - 1 maintainer
stam-tools 0.11.1
Command-line tools for working with stand-off annotations on text (STAM)
26 versions - Latest release: 3 days ago - 22.6 thousand downloads total - 3 stars on GitHub - 1 maintainer
cfasttext-sys 0.7.8 💰
fastText ffi binding
23 versions - Latest release: almost 2 years ago - 1 dependent package - 3 dependent repositories - 316 thousand downloads total - 61 stars on GitHub - 1 maintainer
fasttext 0.7.8 💰
fastText Rust binding
22 versions - Latest release: almost 2 years ago - 2 dependent packages - 3 dependent repositories - 319 thousand downloads total - 61 stars on GitHub - 1 maintainer
tu 0.3.0 💰
CLI tool to convert a natural language date/time string to UTC
4 versions - Latest release: 4 months ago - 3.3 thousand downloads total - 243 stars on GitHub - 1 maintainer
nlpo3 1.4.0
Thai natural language processing library, with Python and Node bindings
8 versions - Latest release: 9 months ago - 1 dependent package - 1 dependent repositories - 17.6 thousand downloads total - 35 stars on GitHub - 2 maintainers
cjieba-sys 0.1.1 💰
unsafe ffi to cppjieba
2 versions - Latest release: almost 5 years ago - 1 dependent package - 4.36 thousand downloads total - 7 stars on GitHub - 1 maintainer
waken_snowball 0.1.0
Rust implementation of Snowball stemming algorithms for 33 languages
1 version - Latest release: 4 days ago - 0 downloads total - 802 stars on GitHub - 1 maintainer
valentinus 1.0.0
Next generation vector database built with LMDB bindings
24 versions - Latest release: 29 days ago - 17.7 thousand downloads total - 14 stars on GitHub - 1 maintainer
rusty
Rust bindings for the spaCy Python NLP package.
4 versions - Latest release: 4 days ago - 5.46 thousand downloads total - 24 stars on GitHub - 1 maintainer
gte-rs 0.9.1
Text embedding and re-ranking pipelines
2 versions - Latest release: 5 months ago - 1.11 thousand downloads total - 2 stars on GitHub - 1 maintainer
nlpo3-cli 0.2.0
Command line interface for nlpO3, a Thai natural language processing library
3 versions - Latest release: almost 4 years ago - 3.57 thousand downloads total - 35 stars on GitHub - 2 maintainers
text-splitter 0.27.0
Split text into semantic chunks, up to a desired chunk size. Supports calculating length by chara...
55 versions - Latest release: 2 months ago - 5 dependent packages - 1 dependent repositories - 480 thousand downloads total - 455 stars on GitHub - 1 maintainer
kfst-rs 0.1.4
Fast and portable HFST-compatible finite-state transducers.
4 versions - Latest release: 17 days ago - 826 downloads total - 3 stars on GitHub - 1 maintainer
lumberjack-utils 0.3.1
Read and modify constituency trees.
3 versions - Latest release: about 6 years ago - 4.24 thousand downloads total - 10 stars on GitHub - 1 maintainer
postagger 0.0.3 💰
NLTK-inspired parts-of-speech tagger
3 versions - Latest release: over 1 year ago - 3.39 thousand downloads total - 7 stars on GitHub - 1 maintainer
ipopt-src 0.2.3+3.14.16
Redistribution of Coin-OR Ipopt as a crate
3 versions - Latest release: over 1 year ago - 2 dependent packages - 4.37 thousand downloads total - 1 stars on GitHub - 1 maintainer
human_name 2.0.4
A library for parsing and comparing human names
34 versions - Latest release: 10 months ago - 1 dependent package - 5 dependent repositories - 1.63 million downloads total - 47 stars on GitHub - 1 maintainer
scirs2-text 0.1.0-alpha.6
Text processing module for SciRS2
6 versions - Latest release: about 1 month ago - 1.76 thousand downloads total - 40 stars on GitHub - 1 maintainer
pragmatic-segmenter 0.1.3
Rust port of pySBD v3.1.0.
4 versions - Latest release: about 2 years ago - 7.88 thousand downloads total - 11 stars on GitHub - 1 maintainer
Top 3.8% on crates.io
whatlang 0.16.4
Fast and lightweight language identification library for Rust.
34 versions - Latest release: over 1 year ago - 16 dependent packages - 293 dependent repositories - 987 thousand downloads total - 958 stars on GitHub - 1 maintainer
mmseg 0.3.0 💰
Chinese word segmenation algorithm MMSEG in Rust
5 versions - Latest release: almost 3 years ago - 7.01 thousand downloads total - 7 stars on GitHub - 1 maintainer
cargo-spellcheck 0.15.5 💰
Checks all doc comments for spelling mistakes
111 versions - Latest release: 4 months ago - 225 thousand downloads total - 317 stars on GitHub - 1 maintainer
tocken 0.1.0 💰
Clustering algorithms.
1 version - Latest release: 7 months ago - 2.51 thousand downloads total - 0 stars on GitHub - 1 maintainer
llms-from-scratch-rs 0.1.5
Rust (candle) code for Build a LLM From Scratch by Sebastian Raschka
11 versions - Latest release: about 2 months ago - 6.16 thousand downloads total - 219 stars on GitHub - 1 maintainer
doc-chunks 0.2.1 💰
Clusters of doc comments and dev comments as coherent view.
8 versions - Latest release: 5 months ago - 1 dependent package - 1 dependent repositories - 52.1 thousand downloads total - 317 stars on GitHub - 1 maintainer
automated 0.1.0
The purpose of this crate to invoke kernel process
3 versions - Latest release: about 2 years ago - 3.65 thousand downloads total - 1 maintainer
eliza 2.0.1
A rust implementation of ELIZA - a natural language processing program developed by Joseph Weizen...
10 versions - Latest release: over 1 year ago - 2 dependent repositories - 15.7 thousand downloads total - 52 stars on GitHub - 1 maintainer
fasttext-serving 0.7.0 💰
fastText model serving API server
34 versions - Latest release: over 2 years ago - 43.6 thousand downloads total - 58 stars on GitHub - 1 maintainer
chat-splitter 0.1.1 💰
Never exceed OpenAI's chat models' maximum number of tokens when using the async_openai Rust crate
2 versions - Latest release: almost 2 years ago - 2.5 thousand downloads total - 3 stars on GitHub - 1 maintainer
wordfreq 0.2.3
Yet another Rust port of wordfreq for looking up the frequencies of words in many languages
6 versions - Latest release: about 2 years ago - 2 dependent packages - 7.45 thousand downloads total - 7 stars on GitHub - 1 maintainer
wordfreq-model 0.2.3
Model loaders for wordfreq-rs
6 versions - Latest release: about 2 years ago - 6.81 thousand downloads total - 7 stars on GitHub - 1 maintainer
nlpcloud 0.0.3
NLP Cloud serves high performance pre-trained and custom models for NER, sentiment-analysis, clas...
3 versions - Latest release: over 4 years ago - 3.58 thousand downloads total - 1 maintainer
libtqsm 0.6.1
Sentence segmenter that supports ~300 languages
1 version - Latest release: over 1 year ago - 1 dependent package - 1.75 thousand downloads total - 2 stars on GitHub - 1 maintainer
kitoken 0.10.1 💰
Fast and versatile tokenizer for language models, supporting BPE, Unigram and WordPiece tokenization
2 versions - Latest release: 7 months ago - 6.03 thousand downloads total - 26 stars on GitHub - 1 maintainer
yitizi 0.1.0
異體字查詢 Get variant Chinese characters
1 version - Latest release: about 1 year ago - 1.19 thousand downloads total - 3 stars on GitHub - 1 maintainer
viterbi_pos_tagger 0.1.0
A part-of-speech (POS) tagger using the Viterbi algorithm.
1 version - Latest release: 7 months ago - 728 downloads total - 1 stars on GitHub - 1 maintainer
saku 0.1.6
A simple yet efficient rule-based Japanese Sentence Tokenizer.
6 versions - Latest release: over 3 years ago - 1 dependent repositories - 6.63 thousand downloads total - 2 stars on GitHub - 1 maintainer
drug-extraction-core 0.1.2
A core library for extracting drugs from text records
3 versions - Latest release: almost 3 years ago - 1 dependent package - 4 thousand downloads total - 3 stars on GitHub - 1 maintainer
katana 1.0.2
A fast and accurate rule-based sentence segmentation tool for Rust. A port from Louie Mullie's Sc...
3 versions - Latest release: over 9 years ago - 10.9 thousand downloads total - 3 stars on GitHub - 1 maintainer
gutenberg-rs 0.1.4
This crate is used to get information and data from gutenberg (https://www.gutenberg.org/)
5 versions - Latest release: over 2 years ago - 5.51 thousand downloads total - 1 stars on GitHub - 1 maintainer
tiniestsegmenter 0.3.0
Compact Japanese segmenter
4 versions - Latest release: 10 months ago - 4.56 thousand downloads total - 3 stars on GitHub - 1 maintainer
bytepiece_rs 0.2.2
The Bytepiece Tokenizer Implemented in Rust
7 versions - Latest release: over 1 year ago - 1 dependent package - 10 thousand downloads total - 14 stars on GitHub - 1 maintainer
cicero-sophia 0.6.3
High-performance NLU (natural language understanding) engine built in Rust for speed, accuracy, a...
4 versions - Latest release: 3 months ago - 1.48 thousand downloads total - 10 stars on GitHub - 1 maintainer
lumberjack 0.3.1
Read and modify constituency trees.
4 versions - Latest release: about 6 years ago - 1 dependent package - 6.07 thousand downloads total - 10 stars on GitHub - 1 maintainer
yake-rust 1.0.3
Yake (Yet Another Keyword Extractor) in Rust
14 versions - Latest release: 5 months ago - 12.2 thousand downloads total - 9 stars on GitHub - 2 maintainers
berlin-core 0.2.6
Identify locations and tag them with UN-LOCODEs and ISO-3166-2 subdivisions.
6 versions - Latest release: over 1 year ago - 8.12 thousand downloads total - 1 maintainer
yozuk 0.22.11
Chatbot for Programmers
58 versions - Latest release: almost 3 years ago - 2 dependent packages - 2 dependent repositories - 59.7 thousand downloads total - 38 stars on GitHub - 1 maintainer
yozuk-core-skillset 0.22.11
Set of default Yozuk skills
58 versions - Latest release: almost 3 years ago - 1 dependent package - 2 dependent repositories - 60.4 thousand downloads total - 38 stars on GitHub - 1 maintainer
yozuk-helper-platform 0.20.2
Platform-dependent utilities for Yozuk
6 versions - Latest release: about 3 years ago - 3 dependent packages - 2 dependent repositories - 8.43 thousand downloads total - 38 stars on GitHub - 1 maintainer
yozuk-helper-preprocessor 0.20.6
Preprocessor utilities for Yozuk
24 versions - Latest release: about 3 years ago - 2 dependent packages - 1 dependent repositories - 25.4 thousand downloads total - 38 stars on GitHub - 1 maintainer
yozuk-helper-filetype 0.22.11
Filetype detection for Yozuk
6 versions - Latest release: almost 3 years ago - 2 dependent packages - 2 dependent repositories - 8.52 thousand downloads total - 38 stars on GitHub - 1 maintainer
yozuk-helper-english 0.22.11
English NLP utilities for Yozuk
13 versions - Latest release: almost 3 years ago - 3 dependent packages - 2 dependent repositories - 16.9 thousand downloads total - 38 stars on GitHub - 1 maintainer
yozuk-sdk 0.22.11
Types used in the Yozuk ecosystem
34 versions - Latest release: almost 3 years ago - 8 dependent packages - 2 dependent repositories - 39.4 thousand downloads total - 38 stars on GitHub - 1 maintainer
yozuk-helper-encoding 0.22.11
English NLP utilities for Yozuk
6 versions - Latest release: almost 3 years ago - 1 dependent package - 1 dependent repositories - 8.33 thousand downloads total - 38 stars on GitHub - 1 maintainer
typed-dialogflow 0.1.0
An easy-to-use typed Google Dialogflow client
1 version - Latest release: over 3 years ago - 1.43 thousand downloads total - 0 stars on GitHub - 1 maintainer
aristech-nlp-client 1.0.2
A Rust client library for the Aristech Natrual Language Processing API
3 versions - Latest release: 2 months ago - 1.54 thousand downloads total - 0 stars on GitHub - 1 maintainer
jieba-rs-siro 0.6.7 💰
The Jieba Chinese Word Segmentation Implemented in Rust
2 versions - Latest release: almost 3 years ago - 2.87 thousand downloads total - 0 stars on GitHub - 1 maintainer
langram 0.6.0
Natural language detection library
8 versions - Latest release: 29 days ago - 2.78 thousand downloads total - 1 stars on GitHub - 1 maintainer
timewarp 0.4.0
NLP library for parsing English and German natural language into dates and times.
5 versions - Latest release: over 1 year ago - 1 dependent package - 5.78 thousand downloads total - 1 stars on GitHub - 1 maintainer
semchunk-rs 0.1.1
A fast and lightweight Rust library for splitting text into semantically meaningful chunks.
2 versions - Latest release: 8 months ago - 1.23 thousand downloads total - 3 stars on GitHub - 1 maintainer
zuk 0.22.11
Yozuk command-line interface
54 versions - Latest release: almost 3 years ago - 61.8 thousand downloads total - 38 stars on GitHub - 1 maintainer
extractous 0.3.0
Extractous provides a fast and efficient way to extract content from all kind of file formats inc...
8 versions - Latest release: 7 months ago - 21.1 thousand downloads total - 1,183 stars on GitHub - 1 maintainer
byteforge 0.1.1
A next-generation byte-level transformer with multi-signal patching and SIMD optimization
2 versions - Latest release: 16 days ago - 370 downloads total - 1 stars on GitHub - 1 maintainer
drug-extraction-cli 1.3.0
A CLI for extracting drugs from text records
6 versions - Latest release: over 1 year ago - 8.41 thousand downloads total - 3 stars on GitHub - 1 maintainer
parattice 0.2.2
Recursive paraphrase lattice generator
2 versions - Latest release: about 5 years ago - 2.53 thousand downloads total - 1 stars on GitHub - 1 maintainer
token-counter 0.1.0
`wc` for tokens: count tokens in files with HF Tokenizers
1 version - Latest release: about 1 year ago - 1.12 thousand downloads total - 7 stars on GitHub - 1 maintainer
gecliht 0.2.0
A disparate collection of text manipulation and formatting algorithms.
2 versions - Latest release: over 1 year ago - 1 dependent package - 2.66 thousand downloads total - 1 maintainer
stam-python 0.11.0
STAM is a library for dealing with standoff annotations on text, this is the python binding.
10 versions - Latest release: 10 days ago - 8.39 thousand downloads total - 1 stars on GitHub - 1 maintainer
stam 0.17.0
STAM is a powerful library for dealing with stand-off annotations on text. This is the Rust library.
29 versions - Latest release: 10 days ago - 2 dependent packages - 28.6 thousand downloads total - 5 stars on GitHub - 1 maintainer
langid-rs 1.0.2
A fast and lightweight language identification library in Rust, inspired by py3langid.
3 versions - Latest release: 10 days ago - 0 downloads total - 1 maintainer
chinese2digits 1.0.0
The Best Tool of Chinese Number to Digits. A useful tool in NLP and robot project.
1 version - Latest release: over 3 years ago - 1.46 thousand downloads total - 367 stars on GitHub - 1 maintainer
chinese-ner 0.2.4 💰
A CRF based Chinese Named-entity Recognition Library written in Rust
8 versions - Latest release: over 4 years ago - 11.2 thousand downloads total - 14 stars on GitHub - 1 maintainer
seams 0.1.0
High-throughput sentence extractor for Project Gutenberg texts with dialog-aware detection
1 version - Latest release: 10 days ago - 0 downloads total - 1 maintainer