Official implementation of paper "Knowledge Distillation from A Stronger Teacher", NeurIPS 2022

第一个支持中英文双语语音-文本多模态对话的开源可商用对话模型。便捷的语音输入将大幅改善以文本为输入的大模型的使用体验，同时避免了基于 ASR 解决方案的繁琐流程以及可能引入的错误。

Speech, Language, Audio, Music Processing with Large Language Model

PyTorch implementation of "Supervised Contrastive Learning" (and SimCLR incidentally)

Papers and codes collection for customized, personalized and editable generative models

🔨AI 方向好用的科研工具

Mamba SSM architecture

[ACL 2024] Official PyTorch code for extracting features and training downstream models with emotion2vec: Self-Supervised Pre-Training for Speech Emotion Representation

Deformable Speech Transformer (DST)

A collection of datasets for the purpose of emotion recognition/detection in speech.

[Information Fusion 2024] HiCMAE: Hierarchical Contrastive Masked Autoencoder for Self-Supervised Audio-Visual Emotion Recognition

Reading list for research topics in multimodal machine learning

Open-source KVM software

vits2 backbone with multilingual-bert

Make Acoustic and Visual Cues Matter: CH-SIMS v2.0 Dataset and AV-Mixup Consistent Module

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

Pytorch implementation for codes in Noise Imitation Based Adversarial Training for Robust Multimodal Sentiment Analysis (Accepted by IEEE Transactions on Multimedia).

✨✨Latest Advances on Multimodal Large Language Models

Code for the InterSpeech 2023 paper: MMER: Multimodal Multi-task learning for Speech Emotion Recognition

AD-TUNING: An Adaptive CHILD-TUNING Approach to Efficient Hyperparameter Optimization of Child Networks for Speech Processing Tasks in the SUPERB Benchmark. Interspeech 2023

2023年推免工作由线上转线下，夏令营数量众多易冲突，本仓库用于高效观察时间重合问题，方便制定策略

发布23年计算机保研夏令营和预推免通知，往年的保研经验帖；需要带保研或计算机保研资料联系qq：1585601434

Zero-shot multimodal punctuation insertion and truecasing using Whisper

A Unified Library for Parameter-Efficient and Modular Transfer Learning

注意力机制实践

Toolkits for Multimodal Emotion Recognition

The code repository for NAACL 2021 paper "Multimodal End-to-End Sparse Model for Emotion Recognition".