Pinned Repositories
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。
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_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
espnet
End-to-End Speech Processing Toolkit
image-recognition
采用深度学习方法进行刀具识别。
kaggle-cats-and-dogs
采用深度学习方法进行图像识别，数据集为kaggle数据集中的猫与狗数据集。
video-action-recognition
视频动作识别，基于C3D网络构建
zw76859420's Repositories
zw76859420/ASR_Syllable
基于卷积神经网络的语音识别声学模型的研究
zw76859420/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
zw76859420/bert
TensorFlow code and pre-trained models for BERT
zw76859420/DNN-HMM-Course
DNN-HMM related Experiments for THUHCSI Course : <Digital Processing of Speech Signals>
zw76859420/NeuralSpeech
zw76859420/SparseSelfAttention
Sparse Attention Mechanism, accepted in KSC 2019
zw76859420/AIF-PyTorch
(NOT Official) Implementation Auto-regressive Integrate-and-Fire (AIF)
zw76859420/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
zw76859420/athena-decoder
zw76859420/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"
zw76859420/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。
zw76859420/CTC-OptimizedLoss
Computes the MWER (minimum WER) Loss with CTC beam search. Knowledge distillation for CTC loss.
zw76859420/cudafst
Standalone implementation of the CUDA-accelerated WFST Decoder available in Riva
zw76859420/decoder
Minimize kaldi nnet3 chain decoder
zw76859420/DFSMN-Based-Lightweight-Speech-Enhancement
Deep Feedforward sequential memory networks(FSMN)
zw76859420/emoASR
End-to-end MOdeling of ASR (Automatic Speech Recognition)
zw76859420/gfcc
gfcc features
zw76859420/ksponspeech
Pre-processing KsponSpeech corpus (Korean Speech dataset) provided by AI Hub.
zw76859420/KWS_pytorch
Keyword spotting, Speech wake_up, by pytorch, DNN, CNN, TDNN, DFSMN, LSTM
zw76859420/neurst
Neural end-to-end Speech Translation Toolkit
zw76859420/OpenTransformer
A No-Recurrence Sequence-to-Sequence Model for Speech Recognition
zw76859420/pkwrap
A pytorch wrapper for LF-MMI training and parallel training in Kaldi
zw76859420/pychain
PyTorch implementation of LF-MMI for End-to-end ASR
zw76859420/sentencepiece
Unsupervised text tokenizer for Neural Network-based text generation.
zw76859420/SimilarCharacter
对常用的6700个汉字进行音、形比较，输出音近字、形近字的列表。 # 相近字
zw76859420/snowfall
zw76859420/warp-rna
Recurrent Neural Aligner
zw76859420/wenet
Production First and Production Ready End-to-End Speech Recognition Toolkit
zw76859420/whisper
zw76859420/whisper-finetune
Fine-tune and evaluate Whisper models for Automatic Speech Recognition (ASR) on custom datasets or datasets from huggingface.