deeplearningsprint Goto Github PK

rnnoise

Recurrent neural network for audio noise reduction

ruby-pinyin

中文汉字转拼音,　支持中英文符号混合词语。Pinyin is a romanization system (phonemic notation) of Chinese characters, this gem helps you to convert Chinese characters into pinyin form.

scrnns

This is a self contained software accompanying the paper titled: Learning Longer Memory in Recurrent Neural Networks: http://arxiv.org/abs/1412.7753.

signalgraph

Matlab-based deep learning toolkit that supports arbitrary directed acyclic graphs (DAG). Support DNN, LSTM, CNN layers and many signal processing layers. Include recipes/examples of using the tool for various tasks.

snowboy

DNN based hotword and wake word detection toolkit

soundnet

SoundNet: Learning Sound Representations from Unlabeled Video. NIPS 2016

spanpsp

speech-vad-demo

集成Webrtc的VAD，用于切分音频文件

speech_recogntion

Repository for all codes related to speech recogntion projects

tensor2tensor

A library for generalized sequence to sequence models

tensorflow

Open source software library for numerical computation using data flow graphs.

tensorflow-examples

TensorFlow Tutorial and Examples for beginners

tensorflow-speech-recognition

Speech recognition using google's tensorflow deep learning framework, sequence-to-sequence neural networks

tensorflow_ctc_example

A short example of training a bidirectional LSTM model with connectionist temporal classification

tensorflowbook

tensorflowtts

:stuck_out_tongue_closed_eyes: TensorFlowTTS: Real-Time State-of-the-art Speech Synthesis for Tensorflow 2 (supported including English, French, Korean, Chinese, German and Easy to adapt for other languages)

torch-autograd

Autograd automatically differentiates native Torch code

torch-dataframe

Utility class to manipulate dataset from CSV file

torch-distlearn

A set of distributed learning algorithms for Torch

torch7

http://torch.ch

torchnet

Torch on steroids

vim

vim配置文件和插件

voxceleb_trainer

In defence of metric learning for speaker recognition

warp-ctc

Fast parallel CTC.

wav2letter

Facebook AI Research Automatic Speech Recognition Toolkit

wer_are_we

Attempt at tracking states of the arts and recent results (bibliography) on speech recognition.