Astra identifies sounds from mel spectrograms zero-shot, and users say we've barely scratched the surface
TomLikesRobots · x · 2026-09-07
Developer maxxrubin reports that Astra can identify sounds directly from mel spectrograms in a zero-shot setting, and notes this was achieved with only light reasoning. He argues the model's audio understanding capabilities are far from fully explored, suggesting we've barely scratched the surface of what it can do.
More from Models
- User: Opus 4.8 nails UI work while OpenAI lacks focus for everyday coding needs — aloncarmel · 2026-09-07
- Netherlands builds 'Dutch AI' by finetuning Qwen 3.5 27B in subsidized datacenter — teortaxesTex · 2026-09-07
- Abacus.AI CEO: DeepSeek Handles 80% of Everyday Tasks at 100x Lower Cost — bindureddy · 2026-09-07
- Users Report Day-One Bans Over 'Distilling' as Opaque Moderation Draws Fire — QuixiAI · 2026-09-07
- Naval's bike analogy for SFT vs RL explains why DeepSeek R1 shocked the industry — McDonaghMatthew · 2026-09-07
- DeepSeek-R1 grew reasoning with pure RL, no SFT — and that's what changed everything — McDonaghMatthew · 2026-09-07