603 Open source projects that are alternatives of or similar to Asr

Fiction generator with Tensorflow. 模仿王小波的风格的小说生成器

Source code for the NAACL 2019 paper "SEQ^3: Differentiable Sequence-to-Sequence-to-Sequence Autoencoder for Unsupervised Abstractive Sentence Compression"

A PyTorch-based model pruning toolkit for pre-trained language models

A neural network architecture for prediction on sets

でぃーぷらーにんぐを無限にやってディープラーニングでDeepLearningするための実装CheatSheet

PaccMann models for protein language modeling

PyTorch implementation of a 2D-LSTM Seq2Seq Model for NMT.

(TPAMI2022) Salient Object Detection via Integrity Learning.

Fast implementation of BERT inference directly on NVIDIA (CUDA, CUBLAS) and Intel MKL

Implementation of the GBST block from the Charformer paper, in Pytorch

[CVPR 2021, Oral] PREDATOR: Registration of 3D Point Clouds with Low Overlap.

Predict materials properties using only the composition information!

SOVA ASR (Automatic Speech Recognition)

SOTA Semantic Segmentation Models in PyTorch

Data Augmentation by Backtranslation (DAB) ヽ( •_-)ᕗ

a collection of visualization function

Further developed as SyntaxDot: https://github.com/tensordot/syntaxdot

Official PyTorch implementation of Time-aware Large Kernel (TaLK) Convolutions (ICML 2020)

Graphormer is a deep learning package that allows researchers and developers to train custom models for molecule modeling tasks. It aims to accelerate the research and application in AI for molecule science, such as material design, drug discovery, etc.

Sequence to Sequence Models with PyTorch

KitanaQA: Adversarial training and data augmentation for neural question-answering models

Implementation of seq2seq word-level model using keras

Sequence to sequence learning using TensorFlow.

Korean text normalization and language preparation package for LM in Kaldi-based ASR system

Implementation of Linformer for Pytorch

JSON API transformer outputting valid (PSR-7) API Responses.

[Preprint] "TransGAN: Two Transformers Can Make One Strong GAN", Yifan Jiang, Shiyu Chang, Zhangyang Wang

Transformer related optimization, including BERT, GPT

Mutate Laravel attributes

Tensorflow Implementation of Stochastic Wasserstein Autoencoder for Probabilistic Sentence Generation (NAACL 2019).

On-device streaming speech-to-text engine powered by deep learning

[ICCV 2021] TRAR: Routing the Attention Spans in Transformers for Visual Question Answering -- Official Implementation

Open-source benchmark datasets and pretrained transformer models in the Filipino language.

Basis expansion transformers in sklearn style.

💬 An On-Premises, Streaming Speech Recognition System

proc(ess)-that - easy extendable ETL tool for Node.js. Written in TypeScript.

State-of-the-art NLP through transformer models in a modular design and consistent APIs.

Several basic neural machine translation models implemented by PyTorch & TensorFlow

BERT for Multitask Learning

S2VT (seq2seq) video captioning with bahdanau & luong attention implementation in Tensorflow

a simple and complete pytorch implementation of neural machine translation system

Official implementation of the Keyword Transformer: https://arxiv.org/abs/2104.00769

Implementation of FontRNN [Computer Graphics Forum, 2019].

SincNet is a neural architecture for efficiently processing raw audio samples.

Simple transformer implementation from scratch in pytorch.

Source code for transferable dialogue state generator (TRADE, Wu et al., 2019). https://arxiv.org/abs/1905.08743

自然语言处理常见任务（主要包括文本分类，序列标注，自动问答等）解决方案试验田

rxjava scheduler transformer tools for android

Source code for our "TitleStylist" paper at ACL 2020

Code for the paper "Are Sixteen Heads Really Better than One?"

fairseq: Convolutional Sequence to Sequence Learning (Gehring et al. 2017) by Chainer

list of efficient attention modules

A simple open domain generative based chatbot based on Recurrent Neural Networks

Implementation of Transformer Model in Tensorflow

Laravel 5 HAL+JSON API Transformer Package

NLP: Relation extraction with position-aware self-attention transformer

LightSeq: A High Performance Inference Library for Sequence Processing and Generation

viewpager with parallax pages, together with vertical sliding (or click) and activity transition

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

Grapheme to phoneme conversion with deep learning.