Open Platform for Embodied Agents

A Fundamental End-to-End Speech Recognition Toolkit

MMeRAG is an open-source RAG (Retrieval-Augmented Generation), Provides a parser for audio and video data to implement RAG for audio and video. MMeRAG是一个开源的RAG项目，提供了一种用于音频和视频数据的解析器，用来实现音视频的RAG。

A Simple and Efficient Implementation Of Fast Fourier Transform For Audio Denoise

Code for "AnyGPT: Unified Multimodal LLM with Discrete Sequence Modeling"

心理健康大模型、LLM、The Big Model of Mental Health、Finetune、InternLM2、InternLM2.5、Qwen、ChatGLM、Baichuan、DeepSeek、Mixtral、LLama3、GLM4、Qwen2、LLama3.1

An Open-Sourced LLM-empowered Foundation TTS System

VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs

A diffusers pipeline for zero shot stylised couples portrait creation

Omni SenseVoice: High-Speed Speech Recognition with words timestamps 🗣️🎯

✨✨Latest Advances on Multimodal Large Language Models

OmniControl: Control Any Joint at Any Time for Human Motion Generation, ICLR 2024

A 3DGS framework for omni urban scene reconstruction and simulation.

An ASR model for transcribing laughter and speech-laugh in conversational speech

实时语音交互数字人，支持端到端语音方案（GLM-4-Voice - THG）和级联方案（ASR-LLM-TTS-THG）。可自定义形象与音色，无须训练，支持音色克隆，首包延迟低至3s。Real-time voice interactive digital human, supporting end-to-end voice solutions (GLM-4-Voice - THG) and …

SignAvatars: A Large-scale 3D Sign Language Holistic Motion Dataset and Benchmark

[SIGGRAPH Asia 2024] PuzzleAvatar: Assembling 3D Avatars from Personal Albums

Animatable Gaussian textured Avatar

[ICCV 2023]ToonTalker: Cross-Domain Face Reenactment

[ICML 2024] 🍅HumanTOMATO: Text-aligned Whole-body Motion Generation

A tool to tranform the flame texture space,shape and pose paramerter into SMPL or SMPLX model 's head(or face).

Towards Open-source GPT-4o with Vision, Speech and Duplex Capabilities。

20 high-performance LLMs with recipes to pretrain, finetune and deploy at scale.

Official implementation of EMOPortraits: Emotion-enhanced Multimodal One-shot Head Avatars

ViViD: Video Virtual Try-on using Diffusion Models

[ECCV'24] TalkingGaussian: Structure-Persistent 3D Talking Head Synthesis via Gaussian Splatting

Talk to your database as if you were chatting with a friend. Turn natural language into powerful SQL queries effortlessly, and get your answers back in a language you understand. No technical jargo…

First Place Winner at Delta Hacks 5. Analyses speech, hand gestures, and facial expressions and gives both real-time feedback as well as a summary of results at the end.