Pinned Repositories
ASR_Theory
语音识别理论,论文和PPT
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。
ASRFrame
An Automatic Speech Recognition Frame ,一个中文语音识别的完整框架, 提供了多个模型
classic-convolution-network
里面会保存许多优秀的卷积神经网络结构,这些结构可以帮助我们更好的设计网络。
DeepSpeechRecognition
A Chinese Deep Speech Recognition System 包括基于深度学习的声学模型和基于深度学习的语言模型
DRB_method
DRB:Discarding redundant blocks to speed up Transformer decoding for speech recognition
espnet
End-to-End Speech Processing Toolkit
kaldi
This is now the official location of the Kaldi project.
Keras-Semantic-Segmentation
Keras-Semantic-Segmentation
masr
中文语音识别; Mandarin Automatic Speech Recognition;
three-sheep's Repositories
three-sheep/classic-convolution-network
里面会保存许多优秀的卷积神经网络结构,这些结构可以帮助我们更好的设计网络。
three-sheep/DeepSpeechRecognition
A Chinese Deep Speech Recognition System 包括基于深度学习的声学模型和基于深度学习的语言模型
three-sheep/masr
中文语音识别; Mandarin Automatic Speech Recognition;
three-sheep/ASR_Theory
语音识别理论,论文和PPT
three-sheep/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。
three-sheep/ASRFrame
An Automatic Speech Recognition Frame ,一个中文语音识别的完整框架, 提供了多个模型
three-sheep/DRB_method
DRB:Discarding redundant blocks to speed up Transformer decoding for speech recognition
three-sheep/espnet
End-to-End Speech Processing Toolkit
three-sheep/kaldi
This is now the official location of the Kaldi project.
three-sheep/Keras-Semantic-Segmentation
Keras-Semantic-Segmentation
three-sheep/LAS_mandarin
Listen, attend and spell Model for Mandarin
three-sheep/MathModel
研究生数学建模,本科生数学建模、数学建模竞赛优秀论文,数学建模算法,LaTeX论文模板,算法思维导图,参考书籍,Matlab软件教程,PPT
three-sheep/MHPinYin2Hanzi
模糊拼音转汉字,主要可用于中文ASR语言模型
three-sheep/mygemm
test code
three-sheep/Statistical-Learning-Method_Code
手写实现李航《统计学习方法》书中全部算法
three-sheep/tensorflow-wavenet
speech recognition based on tensorflow 1.0.0
three-sheep/TensorflowASR
集成了Tensorflow 2版本的端到端语音识别模型,并且RTF(实时率)在0.1左右/Mandarin State-of-the-art Automatic Speech Recognition in Tensorflow 2
three-sheep/wenet
Production First and Production Ready End-to-End Speech Recognition Toolkit