fgaim Goto Github PK

artext

Probabilistic Noising of Natural Language

asyncio-cache

A python library for asyncio caches (like functools cache and lru_cache)

awesome-lang

Awesome list, curated language learning resources

biosses

BIOSSES: a semantic sentence similarity estimation system for the biomedical domain

bleualign

BLUE score based sentence alignment tool for parallel text

cld3

docker_deep_learning_notebook

Docker containers for Deep Learning and NLP

fastbpe

Fast BPE

geezlab-ocr-dataset

A Text Recognition (TR) and Optical Character Recognition (OCR) dataset for the Tigrinya language.

geezswitch

Language identification library for 60 languages including five Ge'ez script based ones.

geezswitch-data

A dataset for language identification in five low-resource Ge'ez based languages

glove

GloVe model for distributed word representation

gpustat

📊 A simple command-line utility for querying and monitoring GPU status

gpuview

A lightweight web dashboard for monitoring GPU usage

hornmorpho

Morphological analysis and generation of Amharic, Oromo, and Tigrinya

hornvecs

Subword informed Word Embedding for Templatic Languages: Tigrinya, Amharic, Arabic ...

incubator-joshua

Mirror of Apache Joshua (Incubating)

jquery.ime

jQuery based input methods library

kenlm

KenLM: Faster and Smaller Language Model Queries

keras

Deep Learning for humans

langchain

⚡ Building applications with LLMs through composability ⚡

langid.py

Stand-alone language identification system

lingua

Natural language detection library for Java and the JVM, suitable for long and short text alike

masakhane

Let's put Africa on the Machine Translation Map!

memgraph

Build modern, graph-based applications on top of your streaming data in minutes

minichain

mosesdecoder

Moses, the machine translation system

mteval

Collection of Evaluation Metrics and Algorithm for Machine Translation

multeval

Multi metric MT evaluation toolkit based on Jonathan Clark's multeval https://github.com/jhclark/multeval

nlp-progress

Repository to track the progress in Natural Language Processing (NLP), including the datasets and the current state-of-the-art for the most common NLP tasks.