grit1024 Goto Github PK

2021bytedancesecurityaicompetition_track1

2021字节跳动安全AI挑战赛赛道一亚军—— 基于文本和多模态数据的风险识别 题目名称：色情导流用户识别

ai-complete

annotated_deep_learning_paper_implementations

🧑‍🏫 59 Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠

asr-conformer

Conformer: Convolution-augmented Transformer for Speech Recognition

av-phoneme

Continous Phoneme Recognition based on Audio-Visual Modality Fusion

avsr

conformer

PyTorch implementation of "Conformer: Convolution-augmented Transformer for Speech Recognition" (INTERSPEECH 2020)

ctcdecoder

Connectionist Temporal Classification (CTC) decoding algorithms: best path, beam search, lexicon search, prefix search, and token passing. Implemented in Python.

dsp-audio-collector

Web app created to collect audios for course project

e2e_lfmmi

E2E system with LF-MMI; word N-gram for Mandarin

end2end-asr-pytorch

End-to-End Automatic Speech Recognition on PyTorch

fish_aistudy

learn AI…code save…

fontclean

汉字图像数据清洗工具，两个功能：字体文件转汉字图像，书法作品文字分割

free-spoken-digit-dataset

A free audio dataset of spoken digits. Think MNIST for audio.

fullsubnet-plus

The official PyTorch implementation of "FullSubNet+: Channel Attention FullSubNet with Complex Spectrograms for Speech Enhancement".

fullycnnspeechenhancement

全卷积网络进行语音降噪

gmm_digital_voice_recognition

基于GMM与MFCC特征进行数字0-9的语音识别，GMM，MFCC，语音识别，中文数据，sklearn，Digital Voice Recognition。

govspeechrecognition

hmm_digital_voice_recognition

基于HMM与MFCC特征进行数字0-9的语音识别，HMM，GMMHMM，MFCC，语音识别，sklearn，Digital Voice Recognition。

hog_svm

使用HOG+SVM进行图像分类

id_speech_recognition

isolated-words-speech-classification

基于普通话的孤立词识别，模型使用神经网络(VGG)，采取Web展示。Based on the isolated word recognition in Mandarin, the model uses neural network (VGG) and adopts Web display.

knnhandwritingrecg

KNN手写数字识别示例程序，基于文本

learn-an-effective-lip-reading-model-without-pains

The PyTorch Code and Model In "Learn an Effective Lip Reading Model without Pains", (https://arxiv.org/abs/2011.07557), which reaches the state-of-art performance in LRW-1000 dataset.

lipreading

PyTorch models for lipreading words and sentences

lipreading-hog-grid

Models for performing visual speech recognition, i.e. lip reading from video.

lipreading_using_temporal_convolutional_networks

ICASSP'21 Towards Practical Lipreading with Distilled and Efficient Models; ICASSP'20 Lipreading using Temporal Convolutional Networks

mnist_char

MINIST train character(手写英文字母识别）

mnist_dnn

深度学习mnist入门实验

mvit

Code Release for MViTv2 on Image Recognition.