Profiling Whisper AI Model on RISC V: Live demo at RISC V Summit Europe 2025

Описание: This demo, done by one of our founders Tan Siret AKINCI in collaboration with DeepComputing, presents a practical performance profiling of the Whisper speech-to-text model running on DeepComputing’s latest DC-ROMA RISC-V AI PC and Andes Voyager prototype board. We demonstrate Whisper.cpp and Qwen LLM working together to generate subtitles for videos in real time on a single RISC-V platform, showcasing the flexibility and performance of RISC-V-based AI hardware.

Chapters:
00:00 Introduction
01:23 Whisper.cpp demo on DC ROMA AI PC
2:37 Call on community
3:20 Setup of Andes Voyager motherboard with prototype IP
5:17 VLC real time subtitles (Whisper.cpp + Qwen LLM) demo on Andes Voyager