LightSeq: A High Performance Library for Sequence Processing and Generation
-
Updated
Feb 16, 2023 - C++
LightSeq: A High Performance Library for Sequence Processing and Generation
Connectionist Temporal Classification (CTC) decoding algorithms: best path, beam search, lexicon search, prefix search, and token passing. Implemented in Python.
PyTorch CTC Decoder bindings
A chatbot implemented in TensorFlow based on the seq2seq model, with certain rules integrated.
Image to LaTeX (Seq2seq + Attention with Beam Search) - Tensorflow
Sequence to sequence learning using TensorFlow.
Pytorch seq2seq chatbot
Seq2seq chatbot with attention and anti-language model to suppress generic response, option for further improve by deep reinforcement learning.
基于seq2seq模型的简单对话系统的tf实现,具有embedding、attention、beam_search等功能,数据集是Cornell Movie Dialogs
Image Captioning using InceptionV3 and beam search
End-to-End speech recognition implementation base on TensorFlow (CTC, Attention, and MTL training)
Pytorch implementation of "A Deep Reinforced Model for Abstractive Summarization" paper and pointer generator network
Explains nlp building blocks in a simple manner.
基于Pytorch的中文聊天机器人 集成BeamSearch算法
A neural network to generate captions for an image using CNN and RNN with BEAM Search.
Tensorflow based Neural Conversation Models
Chinese Poetry Generation
基于seq2seq模型的简单对话系统的tf实现,具有embedding、attention、beam_search等功能,数据集是Cornell Movie Dialogs
A fast LSTM Language Model for large vocabulary language like Japanese and Chinese
Add a description, image, and links to the beam-search topic page so that developers can more easily learn about it.
To associate your repository with the beam-search topic, visit your repo's landing page and select "manage topics."