Fast and High-Quality Zero-Shot Text-to-Speech with Flow Matching

Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.

清华大学第八届人工智能挑战赛电子系赛道（原电子系第 26 届队式程序设计大赛 teamstyle26）

MiniCPM-V 4.5: A GPT-4o Level MLLM for Single Image, Multi Image and High-FPS Video Understanding on Your Phone

State-of-the-art audio codec with 90x compression factor. Supports 44.1kHz, 24kHz, and 16kHz mono/stereo audio.

A demo project for starters to learn website coding

Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation

Generative models for conditional audio generation

Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audio codec.

Mamba SSM architecture

清华大学第七届人工智能挑战赛电子系赛道（原电子系第 25 届队式程序设计大赛 teamstyle25）

Sentence recognition based on six-axis accelerometer mpu6500 using Conformer and CTC decoding

Mamba-Chat: A chat LLM based on the state-space model architecture 🐍

2023 THU EESAST 软件部暑期培训 MAUI作业1 calculator

清华大学第六届人工智能挑战赛电子系赛道（原电子系第 24 届队式程序设计大赛 teamstyle24）

2023 THU EESAST 软件部暑期培训 多线程作业

2023 THU EESAST 软件部暑期培训 CSharp作业