AI Legend's repositories
optimization_learning
newton,quasi-newton,DFP,BFGS,accurate_line_search,Cholesky_decomposition,FR_conjugate_gradient_method,Wolfe,BB_method,armijo,gradient_descent,Goldstein
sudo_rm_rf
Code for SuDoRm-Rf networks for efficient audio source separation. Chinese no work
AAAI-EEG-To-Text
code for AAAI2022 paper "Open Vocabulary Electroencephalography-To-Text Decoding and Zero-shot Sentiment Classification"
asteroid_speech_separation
The PyTorch-based audio source separation toolkit for researchers
EEG_video_matching
match-mismatch prediction of eeg and video pair
audio-diffusion-pytorch
Unconditional audio generation using diffusion models, in PyTorch.
AUDIO_GAN
some traditional gans transferred from image to audio
awesome-videochatbot
collections of video chatbot
benke-NPU-Thesis
西北工业大学本科毕业设计论文模版 | Thesis Template for Northwestern Polytechnical University
freak.github.io
Being a freak is good.
McNet
The official repo: "McNet: Fuse Multiple Cues for Multichannel Speech Enhancement" submitted to ICASSP 2023
NLP_ability
总结梳理自然语言处理工程师(NLP)需要积累的各方面知识，包括面试题，各种基础知识，工程能力等等，提升核心竞争力
notablog-starter
The official starter project for Notablog.
NotionNext
使用 NextJS + Notion API 实现的，支持多种部署方案的静态博客，无需服务器、零门槛搭建网站，为Notion和所有创作者设计。 (A static blog built with NextJS and Notion API, supporting multiple deployment options. No server required, zero threshold to set up a website. Designed for Notion and all creators.)
paper
Read papers
PDVC
End-to-End Dense Video Captioning with Parallel Decoding (ICCV 2021)
Shuobo-LaTeX-Template-for-NPU-Thesis
西北工业大学硕博学位论文模版 | Yet Another Thesis Template for Northwestern Polytechnical University
speechSeperation
A PyTorch-based Speech Toolkit
SpeechTokenizer
This is the code for the SpeechTokenizer presented in the SpeechTokenizer: Unified Speech Tokenizer for Speech Language Models. Samples are presented on
streamlit-example
Example Streamlit app that you can fork to test out share.streamlit.io
StyleT2I
stylegan,text2img
vad
coding based on others' research
video-diffusion-pytorch-ddim
Implementation of Video Diffusion Models, Jonathan Ho's new paper extending DDPMs to Video Generation - in Pytorch
Whisper-Finetune
Fine-tune the Whisper speech recognition model to support training without timestamp data, training with timestamp data, and training without speech data. Accelerate inference and support Web deployment, Windows desktop deployment, and Android deployment