🎓Automatically Update speech Papers Daily using Github Actions (Update Every 12th hours)

FSA/FST algorithms, differentiable, with PyTorch compatibility.

A CRF-based ASR Toolkit

Charsiu: A neural phonetic aligner.

Xception1d implementation for audio categorization

Speech Enhancement: Tensorflow 2.x implementation of the stacked dual-signal transformation LSTM network (DTLN) for Noise Suppression.

Transformer based ASR Engine.

End-to-end speech recognition using RNN Transducers in Tensorflow 2.0

pytorch-kaldi is a project for developing state-of-the-art DNN/RNN hybrid speech recognition systems. The DNN part is managed by pytorch, while feature extraction, label computation, and decoding a…

key word spotting GRU/DNN/DSCNN

PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume, CVPR 2018 (Oral)

Depth-Aware Video Frame Interpolation (CVPR 2019)

This is tensorflow implementation for paper "Deep Image Matting"

Tensors and Dynamic neural networks in Python with strong GPU acceleration

Implementation Code for OFF

This repository is intended to host tools and demos for ActivityNet

Caffe: a fast open framework for deep learning.

Deep Pose Estimation implemented using Tensorflow with Custom Architectures for fast inference.

CNN+LSTM+CTC based OCR implemented using tensorflow.

ObamaNet : Photo-realistic lip-sync from audio (Unofficial port)

Caffe implementation for "Hidden Two-Stream Convolutional Networks for Action Recognition"

Models and examples built with TensorFlow

Machine Learning、Deep Learning、PostgreSQL、Distributed System、Node.Js、Golang