Seq2seq Python Packages

bert4torch

An elegent pytorch implement of transformers

5K 1K 168

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。

4K 1K 208

transformers4rec

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

4K 1K 159

sockeye

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

3K 1K 320

distilbert-punctuator

A small seq2seq punctuator tool based on DistilBERT

2K 54 8

classy-core

A powerful tool to train and use your classification models.

2K 87 3

genienlp

GenieNLP: A versatile codebase for any NLP task

1K 89 26

joeynmt

Minimalist NMT for educational purposes

838 710 224

aocr

A Tensorflow model for text recognition (CNN + seq2seq with visual attention) available as a Python package and compatible with Google Cloud ML Engine.

769 1K 251

nmtpytorch

Sequence-to-Sequence Framework in PyTorch

648 392 51

delta-nlp

DELTA is a deep learning based natural language and speech processing platform. LF AI & DATA Projects: https://lfaidata.foundation/projects/delta/

611 2K 284

tfts

tfts: Time Series Deep Learning Models in TensorFlow

593 889 169

mim-nlp

A Python package with ready-to-use models for various NLP tasks and text preprocessing utilities. The implementation allows fine-tuning.

569 2 0

redco

No description available

553 69 7

pytorch-beam-search

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

537 59 7

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.

529 211 43

textgen

Text Generation Model

527 979 113

kashgari

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.

496 2K 432