Xilai Li's starred repositories
japanese-numbers-python
A parser for Japanese number (Kanji, arabic) in the natural language.
Convert-Numbers-to-Japanese
Converts Arabic numerals, or 'western' style numbers, to a Japanese context.
Llama-Chinese
Llama中文社区,Llama3在线体验和微调模型已开放,实时汇总最新Llama3学习资料,已将所有代码更新适配Llama3,构建最好的中文Llama大模型,完全开源可商用
Awesome-Chinese-LLM
整理开源的中文大语言模型,以规模较小、可私有化部署、训练成本较低的模型为主,包括底座模型,垂直领域微调及应用,数据集与教程等。
SummaryMixing
This repository implements SummaryMixing, a simpler, faster and much cheaper replacement to self-attention for automatic speech recognition (see: https://arxiv.org/abs/2307.07421). The code is ready to be used with the SpeechBrain toolkit).
ConvNeXt-V2
Code release for ConvNeXt V2 model
Squeezeformer
[NeurIPS'22] Squeezeformer: An Efficient Transformer for Automatic Speech Recognition
Res2Net-PretrainedModels
(ImageNet pretrained models) The official pytorch implemention of the TPAMI paper "Res2Net: A New Multi-scale Backbone Architecture"
multistream-cnn
Multistream CNN for Robust Acoustic Modeling
Fastformer
A pytorch &keras implementation and demo of Fastformer.
Fastformer-PyTorch
Unofficial PyTorch implementation of Fastformer based on paper "Fastformer: Additive Attention Can Be All You Need"."
Focal-Transformer
[NeurIPS 2021 Spotlight] Official code for "Focal Self-attention for Local-Global Interactions in Vision Transformers"
Best_AI_paper_2020
A curated list of the latest breakthroughs in AI by release date with a clear video explanation, link to a more in-depth article, and code