A speech-to-text system you can train for $25. A frozen speech encoder and a Qwen LLM joined by a small trained projector, with word timestamps, speaker diarization, a batched HTTP server, a live demo, and a free course.
alexkroman/tiny-audio has 174 GitHub stars. It gained 0 stars over 2 recorded days in the last 7 days (snapshots through Oct 23, 2026).
It currently ranks #36515 daily, #36731 weekly, #37843 monthly by momentum on Trending Repos; its best-ever rank is #12881.
Trending Repos first recorded it on Oct 14, 2026.
| Date | Stars gained | Total stars | Forks gained |
|---|---|---|---|
| 0 | 174 | +1 | |
| 0 | 173 | 0 |