Search papers, labs, and topics across Lattice.
OSUM-Pangu, a speech understanding foundation model, was developed using a non-CUDA software and hardware stack by integrating an audio encoder with the openPangu-7B LLM backbone. The model was trained on Ascend NPUs using a sequential training process to bridge speech perception and user intent recognition. Results show OSUM-Pangu achieves comparable task accuracy to GPU-based models while maintaining natural language interaction capabilities.
A fully open-source speech understanding model, OSUM-Pangu, proves that competitive performance is achievable on non-CUDA hardware, challenging the dominance of GPU-centric ecosystems.
Recent advancements in Speech Large Language Models have significantly enhanced multi-dimensional speech understanding. However, the majority of high-performance frameworks are predominantly optimized for GPU centric ecosystems and proprietary backbones, creating a significant gap for deployment on non-CUDA computing infrastructures. In this paper, we present OSUM-Pangu, a fully open-source speech understanding foundation model developed on a completely non-CUDA software and hardware stack. By integrating an audio encoder with the openPangu-7B LLM backbone, we successfully implement the entire training and inference pipeline on the Ascend NPU platform. To facilitate efficient task alignment under non-CUDA resource constraints, we adopt a practical training process that sequentially bridges speech perception and user intent recognition. Experimental results demonstrate that OSUM-Pangu achieves task accuracy comparable to mainstream GPU-based models while maintaining robust natural language interaction capabilities. Our work provides a reproducible, non-CUDA baseline for the open-source speech community, promoting the independent evolution of multimodal intelligence.
