Austin Xiao's repositories
Tutorial-on-PhD-Application
Tutorial on PhD Application
90DaysOfDevOps
This repository is my documenting repository for learning the world of DevOps. I started this journey on the 1st January 2022 and I plan to run to March 31st for a complete 90-day romp on spending an hour a day including weekends to get a foundational knowledge across a lot of different areas that make up DevOps.
Awesome-Incremental-Learning
Awesome Incremental Learning
Bilibili-plus
课程视频、PPT和源代码:侯捷C++系列;台大郭彦甫MATLAB
cleanlab
The standard package for data-centric AI and machine learning with label errors, finding mislabeled data, and uncertainty quantification. Works with most datasets and models.
Code-LMs
Guide to using pre-trained large language models of source code
composer
library of speed-up algorithms for model training
DESED
Repo associated to the DESED dataset, download and creation of data
EAGRNet
Edge-aware Graph Representation Learning and Reasoning for Face Parsing (ECCV 2020)
espnet
End-to-End Speech Processing Toolkit
google-research
Google Research
LeetCode-Python
My LeetCode solutions and notes.
Megatron-LM
Ongoing research training transformer models at scale
memory_profiler
Monitor Memory usage of Python code
ML-NLP
此项目是机器学习(Machine Learning)、深度学习(Deep Learning)、NLP面试中常考到的知识点和代码实现,也是作为一个算法工程师必会的理论基础知识。
multilingual_kws
Few-shot Keyword Spotting in Any Language and Multilingual Spoken Word Corpus
openmlsys-zh
机器学习系统设计与实现
proj_multilingual_text_classification
Explore multilingal text classification using embedding, bert and deep learning architecture
PyContinual
PyContinual (An Easy and Extendible Framework for Continual Learning)
PyTorch-GAN
PyTorch implementations of Generative Adversarial Networks.
RateMySupervisor
永久免费开源的导师评价数据、数据爬虫、无需编程基础的展示网页以及新信息补充平台
Torch-KWT
Unofficial PyTorch implementation of "Keyword Transformer: A Self-Attention Model for Keyword Spotting", Berg et al. 2021.
transformer-deploy
Efficient, scalable and enterprise-grade CPU/GPU inference server for 🤗 Hugging Face transformer models 🚀
wekws
Production First and Production Ready End-to-End Keyword Spotting Toolkit
wenet
Production First and Production Ready End-to-End Speech Recognition Toolkit
xtreme
XTREME is a benchmark for the evaluation of the cross-lingual generalization ability of pre-trained multilingual models that covers 40 typologically diverse languages and includes nine tasks.