OSUM-Pangu: An Open-Source Multidimension Speech Understanding Foundation Model Built upon OpenPangu on Ascend NPUs

TL;DR

OSUM-Pangu is an open-source, non-CUDA speech understanding model built on Ascend NPUs, achieving GPU-comparable accuracy and promoting accessible multimodal AI development.

Contribution

The paper introduces OSUM-Pangu, a fully open-source speech understanding model optimized for non-CUDA hardware, integrating openPangu-7B on Ascend NPUs for the first time.

Findings

Achieves task accuracy comparable to GPU-based models

Operates efficiently on Ascend NPU platform

Provides a reproducible baseline for open-source speech AI

Abstract

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.