Pinned Loading

1. Qwen3-Omni Qwen3-Omni Public

   Forked from QwenLM/Qwen3-Omni

   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.

   Jupyter Notebook

2. Qwen2.5-Omni Qwen2.5-Omni Public

   Forked from QwenLM/Qwen2.5-Omni

   Qwen2.5-Omni is an end-to-end multimodal model by Qwen team at Alibaba Cloud, capable of understanding text, audio, vision, video, and performing real-time speech generation.

   Jupyter Notebook

3. SoulX-Podcast SoulX-Podcast Public

   Forked from Soul-AILab/SoulX-Podcast

   SoulX-Podcast is an inference codebase by the Soul AI team for generating high-fidelity podcasts from text.

   Python

4. OSUM OSUM Public

   Forked from ASLP-lab/OSUM

   OSUM: Open Speech Understanding Model, open-sourced by ASLP@NPU.

   Python

5. valle-audiodec valle-audiodec Public

   Inference code for Audiodec-Valle-Wenetspeech4TTS

   Python 50 2