OPEN
homi
homi is egma-ai's open audio decision model, based on Qwen3-Omni-30B-A3B. It returns option probabilities from audio without a transcript.
By egma-ai · Hugging Face weights upload: 27 Oct 2026
An open decision model that listens instead of reading: give it an audio clip and a typed question (how does the speaker feel? does the pitch rise?) and it returns a probability for every option, without a transcript. It is Qwen3-Omni-30B-A3B with frozen weights and a decision head in place of the text output. The date is when the weights went up on Hugging Face.
Facts
- Base
- Qwen3-Omni-30B-A3B-Instruct, frozen, with a decision head and 17M parameters of LoRA
- Licence
- Apache-2.0
- Inputs
- Audio clip plus Noul, Choice or Score questions
Claims and sources
- 73.9 on VocalGrad against 63.0 for Gemini 3.8 Flash, and 83.1 on MMSU against Gemini's 85.7. Cost per 10,000 MMSU questions: an estimated $0.28 of batched GPU time on one H200 at $4.54/hour, against $14.80 in Gemini API charges at promotional pricing vendor reportedsource
Links
Source: GitHub → Source: Hugging Face → Source: Show HN →
Related projects
No related projects are listed in the registry.