vyraun

TransformerDissection

[EMNLP'19] Summary for Transformer Understanding

pytorch-softdtw

An implementation of SoftDTW for PyTorch.

Contrastive-Predictive-Coding-PyTorch

Contrastive Predictive Coding for Automatic Speaker Verification

kornia

Geometric Computer Vision Library for Spatial AI

DAFT

Code for the NeurIPS 2019 paper: "Learning Dynamics of Attention: Human Prior for Interpretable Machine Reasoning"

pytorch-struct

Fast, general, and tested differentiable structured prediction in PyTorch

higher

higher is a pytorch library allowing users to obtain higher order gradients over losses spanning training loops rather than individual training steps.

DeepSpeaker-pytorch

Speaker embedding(verification and recognition) using Pytorch

g2p

g2p: English Grapheme To Phoneme Conversion

clutrr

Diagnostic benchmark suite to explicitly test logical relational reasoning on natural language

DPC

Video Representation Learning by Dense Predictive Coding. Tengda Han, Weidi Xie, Andrew Zisserman.

speech-reading-list

A speech recognition research reading list maintained by Ramon Sanabria

L2T-ww

Learning What and Where to Transfer (ICML 2019)

PLMpapers

Must-read Papers on pre-trained language models.

multi-retrieval

Code for Unsupervised Discovery of Multimodal Links in Multi-Image/Multi-Sentence Documents

transducer

A Fast Sequence Transducer Implementation with PyTorch Bindings

DANN-keras

A simple implementation of domain adversarial training with GAN loss in Keras

AVE-ECCV18

Audio-Visual Event Localization in Unconstrained Videos, ECCV 2018

Audio-Visual-Event-Localization-in-Unconstrained-Videos

awesome-grounding

awesome grounding: A curated list of research papers in visual grounding

MAC

MAC: Mining Activity Concepts for Language-based Temporal Localization

ABLR_code

The source code of the paper: "To Find Where You Talk: Temporal Sentence Localization in Video with Attention Based Location Regression"

multi-speakerID

AudioCaption

Dataset and baseline for the first Audiocaption task

DreamTime

InceptionTime: Finding AlexNet for Time Series Classification

delta

DELTA is a deep learning based natural language and speech processing platform.

flashtorch

Visualization toolkit for neural networks in PyTorch! Demo -->

universal-triggers

Universal Adversarial Triggers for Attacking and Analyzing NLP (EMNLP 2019)

HiCE

Code for ACL'19 "Few-Shot Representation Learning for Out-Of-Vocabulary Words"

roi_pooling

ROIPooling for pytorch