FunASR is an open-source end-to-end speech recognition toolkit (ASR) led by Alibaba DAMO Academy. It supports ASR, voice activity detection (VAD), punctuation restoration, speaker verification/diarization, multi-talker ASR, emotion recognition and more. FunASR provides many industrial-grade pretrained models, inference scripts, and deployment runtimes for research and production use.
Qwen-Agent is an open-source agent framework from the Qwen team (Alibaba) for building LLM applications on top of Qwen models (Qwen >= 3.0). It supports function/tool calling, MCP, RAG, code interpreter, and ships with example apps like browser assistants and code-interpreter assistants.
Qwen-Image is an open-source image foundation model family (20B MMDiT) from QwenLM/Alibaba that excels at complex text rendering and precise image editing. It provides text-to-image and image-editing pipelines, HuggingFace/Diffusers support, multiple released checkpoints (e.g. Qwen-Image-2512 / Qwen-Image-Edit-2511), community acceleration tooling and LoRA integrations. Licensed under Apache-2.0.
