alan101-tech Goto Github PK

asr-decoder

it's ASR decoder and make graph project

awesome-kaldi

This is a list of features, scripts, blogs and resources for better using Kaldi ( http://kaldi-asr.org/ )

complexpytorch

A high-level toolbox for using complex valued neural networks in PyTorch

conv_arithmetic

A technical report on convolution arithmetic in the context of deep learning

deepspeech

A TensorFlow implementation of Baidu's DeepSpeech architecture

deepspeech-1

A PaddlePaddle implementation of DeepSpeech2 architecture for ASR.

deepspeech.pytorch

Speech Recognition using DeepSpeech2.

distiller

Neural Network Distiller by Intel AI Lab: a Python package for neural network compression research. https://nervanasystems.github.io/distiller

e2e-asr

PyTorch Implementations for End-to-End Automatic Speech Recognition

eesen

The official repository of the Eesen project

emotion_recognition_cnn

end-to-end-asr-pytorch

This is an open source project (formerly named Listen, Attend and Spell - PyTorch Implementation) for end-to-end ASR implemented with Pytorch, the well known deep learning toolkit.

espnet

End-to-End Speech Processing Toolkit

espresso

Espresso: A Fast End-to-End Neural Speech Recognition Toolkit

fairseq

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

faster-rnnlm

Faster Recurrent Neural Network Language Modeling Toolkit with Noise Contrastive Estimation and Hierarchical Softmax

fsmn

Implementations for FSMN (Feedforward Sequential Memory Network), cFSMN, DFSMN, and PFSMN units

juicer

Juicer is a Weighted Finite State Transducer (WFST) based decoder for Automatic Speech Recognition (ASR).

kaldi

This is the official location of the Kaldi project.

kaldi-decoders

Custom decoders for Kaldi

kaldiio

A pure python module for reading and writing kaldi ark files

keyword-spotting-research-datasets

kws

An End-to-End Architecture for Keyword Spotting and Voice Activity Detection

libri_css

Libri-CSS: dataset and evaluation pipeline

listen-attend-spell

A PyTorch implementation of Listen, Attend and Spell (LAS), an End-to-End ASR framework.

lstmp.pytorch

The implementation of LSTM with projection layer by PyTorch

megatron-lm

Ongoing research training transformer language models at scale, including: BERT & GPT-2

models

Models and examples built with TensorFlow

nemo

NeMo: a toolkit for conversational AI

neural_sp

End-to-end ASR/LM implementation with pytorch.