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

Tensorflow implementation of "Listen, Attend and Spell" authored by William Chan. This project utilizes input pipeline and estimator API of Tensorflow, which makes the training and evaluation truly end-to-end.

Articulatory features estimation using Listen Attend and Spell architecture.

Implementation of the paper "Listen, Attend and Spell" Paper in Pytorch

This repository is a PyTorch implementation of NIPS 2019 Paper "Shallow RNNs: A Method for Accurate Time-series Classification on Tiny Devices"

PyTorch implementation of automatic speech recognition models.

tf 2.0 implementation of Listen, attend and spell

PyTorch implementation of Listen, Attend and Spell (LAS) speech recognition paper

Listen, Attend and spell model for E2E ASR. Implementation in Pytorch

Develop speech recognition models with Tensorflow 2

Tensorflow implement of LAS model

End-to-End Speech Recognition Using Tensorflow

Sistema conversor de habla a texto basado en redes neuronales

Listen, attend and spell Model and a Chinese Mandarin Pretrained model (中文-普通话 ASR模型)

A curated list of awesome papers on contextualizing E2E ASR outputs

A repo of all the fun deep learning projects I worked on for LTI-11685

OCR model made of using LAS's speller and image encoder.

一个执着于让CPU\端侧-Model逼近GPU-Model性能的项目，CPU上的实时率(RTF)小于0.1

ASR models implemented from scratch in PyTorch