MOSS-Audio is an open-source foundation model for unified audio understanding, enabling speech, sound, music, captioning, QA, and reasoning in real-world scenarios.

First foundation ASR built for the real world - 7 atomic acoustic conditions, 54 compound scenarios, 2.6M samples, and up to ~30% gains over SOTA where every other model falls apart. **You'll come …

仅需Python基础，从0构建自己的具身智能机器人；从0逐步构建VLA/OpenVLA/SmolVLA/Pi0， 深入理解具身智能

A Large-scale Wu Dialect Speech Corpus with Multi-dimensional Annotations

A lightweight suite of motion imitation methods for training controllers.

Murmur: An Efficient Inference System for Long-Form ASR

Official repository for the WenetSpeech-Chuan dataset.

A Code Release for Mip-NeRF 360, Ref-NeRF, and RawNeRF

Contrastive Language-Audio Pretraining

📚 《从零开始构建智能体》——从零开始的智能体原理与实践教程

Open-Source Frontier Voice AI

Qwen3-ASR is an open-source series of ASR models developed by the Qwen team at Alibaba Cloud, supporting stable multilingual speech/music/song recognition, language detection and timestamp prediction.

A toolkit for speaker diarization.

Claude Code v2.1.88 Source Code

A visual, example-driven guide to Claude Code — from basic concepts to advanced agents, with copy-paste templates that bring immediate value.

Agent harness built with LangChain and LangGraph. Equipped with a planning tool, a filesystem backend, and the ability to spawn subagents - well-equipped to handle complex agentic tasks.

An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of…

来自于文章Paraformer-v2: An improved non-autoregressive transformer for noise-robust speech recognition

Variational Bayes HMM over x-vectors diarization

An Efficient and User-Friendly Scaling Library for Reinforcement Learning with Large Language Models

Open-source LLM-based ASR model family for Chinese, dialect, accent, and multilingual speech, with FunASR, vLLM, streaming, and llama.cpp runtimes.

🤗 R1-AQA Model: mispeech/r1-aqa

SALMONN family: A suite of advanced multi-modal LLMs

Qwen3-omni is a natively end-to-end, omni-modal LLM developed by the Qwen team at Alibaba Cloud, capable of understanding text, audio, images, and video, as well as generating speech in real time.

Official code release for "Efficient Perspective-Correct 3D Gaussian Splatting Using Hybrid Transparency"