Show HN: Homi, open decision model for audio, near Flash on MMSU and 50x cheaper

Category: ai-ml

Tags: audio, decision-model, qwen, benchmarking, multimodal

Score: 7.8/10 (Innovation: 8, Technical: 8, Documentation: 8, Utility: 7)

Homi is an open decision model for audio that answers typed questions (yes/no, multiple-choice, scored levels) about audio clips, using a Qwen3-Omni-based architecture with a decision head instead of text generation. It claims strong performance on VocalGrad and MMSU benchmarks at significantly lower cost than Gemini Flash, with a fully reproducible training and evaluation pipeline.

Target audience: machine learning engineers, audio researchers, data scientists

Repository: https://github.com/egma-ai/homi/ · Python · Apache-2.0 · 1 stars

View on Hacker News