Stars
RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.
Langchain-Chatchat（原Langchain-ChatGLM）基于 Langchain 与 ChatGLM, Qwen 与 Llama 等语言模型的 RAG 与 Agent 应用 | Langchain-Chatchat (formerly langchain-ChatGLM), local knowledge based LLM (like ChatGLM, Qwen and…
Start building LLM-empowered multi-agent applications in an easier way.
dify-connector is a tool to publish Dify apps to various IM platforms. | dify-connector 是一个将 Dify 发布到各种 IM 平台的工具。
分享一些好用的 Dify DSL 工作流程，自用、学习两相宜。 Sharing some Dify workflows.
ai副业赚钱大集合，教你如何利用ai做一些副业项目，赚取更多额外收益。The Ultimate Guide to Making Money with AI Side Hustles: Learn how to leverage AI for some cool side gigs and rake in some extra cash. Check out the English versi…
Repository for the paper "Towards duration robust weakly supervised sound event detection"
The official code for "One Fits All: Power General Time Series Analysis by Pretrained LM (NeurIPS 2023 Spotlight)"
Code for our SIGKDD'22 paper Pre-training-Enhanced Spatial-Temporal Graph Neural Network For Multivariate Time Series Forecasting.
Code for Yun Wang's PhD Thesis: Polyphonic Sound Event Detection with Weak Labeling
Reading list for research topics in Sound AI
PyTorch implementation of the LEAF audio frontend
PyTorch Lightning + Hydra. A very user-friendly template for ML experimentation. ⚡🔥⚡
🍀 Pytorch implementation of various Attention Mechanisms, MLP, Re-parameter, Convolution, which is helpful to further understand papers.⭐⭐⭐
🔊 A comprehensive list of open-source datasets for voice and sound computing (95+ datasets).
A No-Recurrence Sequence-to-Sequence Model for Speech Recognition
Implementation of Visual Transformer for Small-size Datasets
Transfer learning / domain adaptation / domain generalization / multi-task learning etc. Papers, codes, datasets, applications, tutorials.-迁移学习
Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch
[CVPR 2020 VL3] The repository for meta fine-tuning in cross-domain few-shot learning.
This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".
ESC-50: Dataset for Environmental Sound Classification
Code for the Interspeech 2021 paper "AST: Audio Spectrogram Transformer".