Highlights
Starred repositories
Mastering Diverse Domains through World Models
Chinese Standard Mahjong Competition hosted by AILab in Peking University.
A Japanese Mahjong AI, which can play Mahjong on two online Japanese Mahjong services. It can easily defeat other players in 一般 (Normal level) games and also plays well in 上級 (High level) games.
🦦 Otter, a multi-modal model based on OpenFlamingo (open-sourced version of DeepMind's Flamingo), trained on MIMIC-IT and showcasing improved instruction-following and in-context learning ability.
Muzic: Music Understanding and Generation with Artificial Intelligence
Audiocraft is a library for audio processing and generation with deep learning. It features the state-of-the-art EnCodec audio compressor / tokenizer, along with MusicGen, a simple and controllable…
Generate music based on natural language prompts using LLMs running locally
Python Fan calculator for Chinese Standard Mahjong
the BotZone AI in your own computer, with ~10s time limit!
Test your prompts, agents, and RAGs. Red teaming, pentesting, and vulnerability scanning for LLMs. Compare performance of GPT, Claude, Gemini, Llama, and more. Simple declarative configs with comma…
LLM Reasoning and Generation Benchmark. Evaluate LLMs in complex scenarios systematically.
Demo and samples for universal speech translator
Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.
SALMONN: Speech Audio Language Music Open Neural Network
Automating the Search for Artificial Life with Foundation Models!
Chat with any character you like: ChatGLM2+SadTalker+Voice Cloning | 和喜欢的角色沉浸式对话吧:ChatGLM2+声音克隆+视频对话
A Fundamental End-to-End Speech Recognition Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Recognition, Voice Activity Detection, Text Post-processing etc.
[ICLR 2024] Real-Fake: Effective Training Data Synthesis Through Distribution Matching
[ICLR 2024] Real-Fake: Effective Training Data Synthesis Through Distribution Matching
Unified framework for robot learning built on NVIDIA Isaac Sim
This repository contains tutorials and examples for Triton Inference Server
PyTorch/TorchScript/FX compiler for NVIDIA GPUs using TensorRT
Real-time Web Dashboard for Optuna.
Extension of ChatTTS, 3x Faster on Windows, Support Voice Cloning and Mobile Deployment