zw76859420 Goto Github PK

-

硕士期间语音识别所学

-ppt-

本人研究生期间对于语音识别所学。

agriculture_recognition

AI挑战赛，农作物识别，已经做好数据处理，模型训练等部分，由于时间原因交由实验室师弟进行优化。

aif-pytorch

(NOT Official) Implementation Auto-regressive Integrate-and-Fire (AIF)

algorithm_interview_notes-chinese

2018/2019/校招/春招/秋招/算法/机器学习(Machine Learning)/深度学习(Deep Learning)/自然语言处理(NLP)/C/C++/Python/面试笔记

asr

中文语音识别系统，在西安电子科技大学某位大神的脚本上进行改进模型。

asr-1

asr-decode-simple

从Kaldi中裁剪的轻量级语音识别解码推理框架，目前实现了MFCC+GMM+Viterbi，不依赖OpenFST、OpenBLAS等库

asr-study

Implementation of all-neural speech recognition systems using Keras and Tensorflow

asr_phone

以音素建模构建NN-CTC声学模型

asr_syllable

基于卷积神经网络的语音识别声学模型的研究

asr_theory

语音识别理论、论文和PPT

asr_transformer

A Pytorch implementation of Speech Transformer, an End-to-End Automatic Speech Recognition with Transformer Network, Which directly converts acoustic features to character sequence using a signal neural network.

asr_word

采用端到端方法构建声学模型，以字为建模单元，采用DCNN-CTC网络结构。

asrt_speechrecognition

A Deep-Learning-Based Chinese Speech Recognition System 基于深度学习的中文语音识别系统

athena-decoder

attention

some attention implements

attention-is-all-you-need-keras

A Keras+TensorFlow Implementation of the Transformer: Attention Is All You Need

attention-translation-keras

Attention based sequence to sequence neural machine translation model built in keras.

audioset_classification

automatic_speech_recognition

End-to-end Automatic Speech Recognition for Madarian and English in Tensorflow

bayesian_tdnn

This repository contains the Kaldi LF-MMI implementation of the paper "Bayesian Learning of LF-MMI Trained Time Delay Neural Networks for Speech Recognition"

bert

TensorFlow code and pre-trained models for BERT

bert-keras

Keras implementation of BERT with pre-trained weights

c-_learning

C++提高 （看过c++基础之后再看）黑马培训课程，自己手打，路径 https://www.bilibili.com/video/av35939892/?p=3

chinese-speech-to-text

Chinese Speech To Text Using Wavenet

chinese-text-detection-and-recognition

Assignment of Image Analysis and Understanding

chinese-xinhua-important

:orange_book: 中华新华字典数据库。包括歇后语，成语，词语，汉字。

cloud-recognition

采用深度学习方法，进行6分类云彩识别，识别率为73.17%，比赛用

cn_speck_checker

中文单词自动纠错