zeinsh

seamless_communication

Foundational Models for State-of-the-Art Speech and Text Translation

KandinskyVideo

KandinskyVideo — multilingual end-to-end text2video latent diffusion model

nlp-roadmap

ROADMAP(Mind Map) and KEYWORD for students those who have interest in learning NLP

DALLE2-pytorch

Implementation of DALL-E 2, OpenAI's updated text-to-image synthesis neural network, in Pytorch

lex-glue

LexGLUE: A Benchmark Dataset for Legal Language Understanding in English

embeddings

Knowledge Base Embeddings for DBpedia

LegalCrawler

LegalCrawler: A tool for automated scraping of English legal corpora

character-bert

Main repository for "CharacterBERT: Reconciling ELMo and BERT for Word-Level Open-Vocabulary Representations From Characters"

TextFlow

pytorch-normalizing-flows

Normalizing flows in PyTorch. Current intended use is education not production.

flowtron

Flowtron is an auto-regressive flow-based generative network for text to speech synthesis with control over speech variation and style transfer

arabert

Pre-trained Transformers for Arabic Language Understanding and Generation (Arabic BERT, Arabic GPT2, Arabic ELECTRA)

Sinai-corpus

A clean Fusha Arabic tagged corpus.

Arabycia

Arabic NLP tool used to perform Text Search, POS tagging, Translation, auto-diacritization, etc..

TensorFlowTTS

:stuck_out_tongue_closed_eyes: TensorFlowTTS: Real-Time State-of-the-art Speech Synthesis for Tensorflow 2 (supported including English, French, Korean, Chinese, German and Easy to adapt for other languages)

TextAttack

TextAttack 🐙 is a Python framework for adversarial attacks, data augmentation, and model training in NLP https://textattack.readthedocs.io/en/master/

BLINK

Entity Linker solution

NeuralNLP-NeuralClassifier

An Open-source Neural Hierarchical Multi-label Text Classification Toolkit

xfspell

xfspell — the Transformer Spell Checker

datasets

🤗 The largest hub of ready-to-use datasets for ML models with fast, easy-to-use and efficient data manipulation tools

gpt-3

GPT-3: Language Models are Few-Shot Learners

LASER

Language-Agnostic SEntence Representations

Multi-Tacotron-Voice-Cloning

Phoneme multilingual(Russian-English) voice cloning based on

Bert-Russian-punctuation

Простая модель расстановки запятых на основе BERT

Texygen

A text generation benchmarking platform

PyTorch-GAN

PyTorch implementations of Generative Adversarial Networks.

Arabic-BERT

Arabic edition of BERT pretrained language models

tokenizers

💥 Fast State-of-the-Art Tokenizers optimized for Research and Production

bertviz

BertViz: Visualize Attention in NLP Models (BERT, GPT2, BART, etc.)

transformers

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.