Seq2seq Python Packages

sockeye

Sequence-to-sequence framework with a focus on Neural Machine Translation based on PyTorch

transformers4rec

Transformers4Rec is a flexible and efficient library for sequential and session-based recommendation and works with PyTorch.

classy-core

classy is a simple-to-use library for building high-performance Machine Learning models in NLP.

bert4torch

An elegent pytorch implement of transformers

bert-seq2seq

pytorch实现 Bert 做seq2seq任务，使用unilm方案,现在也可以做自动摘要，文本分类，情感分析，NER，词性标注等任务,支持t5模型，支持GPT2进行文章续写。

redco

NAACL '24 (Best Demo Paper RunnerUp) / MlSys @ NeurIPS '23 - RedCoast: A Lightweight Tool to Automate Distributed Training and Inference

joeynmt

Minimalist NMT for educational purposes

genienlp

GenieNLP: A versatile codebase for any NLP task

kashgari

Simple, Keras-powered multilingual NLP framework, allows you to build your models in 5 minutes for named entity recognition (NER), part-of-speech tagging (PoS) and text classification tasks. Includes BERT, GPT-2 and word2vec embedding.

distilbert-punctuator

A small seq2seq punctuator tool based on DistilBERT

aocr

Optical character recognition model for Tensorflow based on Visual Attention.

lsg-converter

Efficient Attention for Long Sequence Processing

tfts

tfts: Time Series Deep Learning Models in TensorFlow

nmtpytorch

Sequence-to-Sequence Framework in Pytorch

tsts

toolset for time series forecasting

seq2seqsharp

Seq2SeqSharp is a tensor based fast & flexible deep neural network framework written by .NET (C#). It has many highlighted features, such as automatic differentiation, different network types (Transformer, LSTM, BiLSTM and so on), multi-GPUs supported, cross-platforms (Windows, Linux, MacOS), multimodal model for text and images and so on.

txt2txt

Extremely easy to use sequence to sequence library with attention, for text to text conversion tasks.

pytorch-beam-search

A simple library that implements search algorithms for sequence models written in PyTorch.

textgen

Text Generation Model

kashgari-tf

Kashgari is a production-level NLP Transfer learning framework built on top of tf.keras for text-labeling and text-classification, includes Word2Vec, BERT, and GPT2 Language Embedding.

copynet-tf

CopyNet with TensorFlow 2.0

deepcorrect

Text Correction wth deep learning

aichatbot

Python library for building custom AI chatbot with just one line of code.

deep-keyphrase

seq2seq based keyphrase generation model sets, including copyrnn copycnn and copytransfomer