pohanchi

CPC_audio

An implementation of the Contrast Predictive Coding (CPC) method to train audio features in an unsupervised fashion.

pysox

Python wrapper around sox.

TaylorGAN

HybridQA

Dataset and code for EMNLP2020 paper "HybridQA: A Dataset of Multi-Hop Question Answeringover Tabular and Textual Data"

awesome-semi-supervised-learning

😎 An up-to-date & curated list of awesome semi-supervised learning papers, methods & resources.

H264-Encoder

Implementation of a subset of CBP of h.264 encoder

MPM

Simulating on GPU using Material Point Method and rendering.

pytorch-dual-learning

Implementation of Dual Learning NMT on PyTorch

universal-vocoder

A PyTorch implementation of the universal neural vocoder

dvector

Speaker embedding (d-vector) trained with GE2E loss

simpletransformers

Transformers for Information Retrieval, Text Classification, NER, QA, Language Modelling, Language Generation, T5, Multi-Modal, and Conversational AI

FastSpeech2

Multi-Speaker Pytorch FastSpeech2: Fast and High-Quality End-to-End Text to Speech :fist:

GPT2sQA

Fine-tuning GPT-2 Small for Question Answering

dialoglue

DialoGLUE: A Natural Language Understanding Benchmark for Task-Oriented Dialogue

datasets

🤗 The largest hub of ready-to-use datasets for ML models with fast, easy-to-use and efficient data manipulation tools

jiant

jiant is an nlp toolkit

awesome-mlss

🤖 Machine Learning Summer School deadlines

audio

Data manipulation and transformation for audio signal processing, powered by PyTorch

delight

DeLighT: Very Deep and Light-Weight Transformers

Tiwan-2020coupons

deformer

[ACL 2020] DeFormer: Decomposing Pre-trained Transformers for Faster Question Answering

nq-open

acl2020-openqa-tutorial

ACL2020 Tutorial: Open-Domain Question Answering

MRQA-Shared-Task-2019

Resources for the MRQA 2019 Shared Task

neural-tangents

Fast and Easy Infinite Neural Networks in Python

contrastive-predictive-coding

Keras implementation of Representation Learning with Contrastive Predictive Coding

voice_datasets

🔊 A comprehensive list of open-source datasets for voice and sound computing (95+ datasets).

SymbolicMathematics

Deep Learning for Symbolic Mathematics

UniversalVocoding

A PyTorch implementation of "Robust Universal Neural Vocoding"

fairseq

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.