alexkroman / tiny-audio
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.
Why this job: says: free course; topics: tutorial
What it does
It is deliberately simple. For production speech recognition, use a mature toolkit or a hosted API. This repo is for understanding how the pieces fit, and for running cheap experiments of your own.
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Active
- Last commit 17 days ago
- Stars
- 179
- On GitHub
- Licence
- MIT
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- None yet
- No releases
- Built with
- Python
- 100% of the code
Is it looked after?
- Contributors
- 2
- Last 90 days
- Issues
- 100% closed
- 0 still open
- Pull requests
- 168 merged
- 4 waiting
- Releases
- None
- Never published
- Contributing guide (opens in new tab)
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| wq2012 / awesome-diarization | 1,916 | 14 days ago | Apache-2.0 | No downloads |
| mahimairaja / voiceai | 339 | 12 days ago | MIT | No downloads |
More: languages, topics, project record and preview image
Languages
- Python 100%
- Shell <1%
Topics
- asr
- audio-llm
- forced-alignment
- huggingface
- llm
- lora
- multimodal
- pipecat
- pytorch
- qwen
- runpod
- speaker-diarization
Project record
- JobLists and guides
- StatusListed
- Commits169
- Forks19
- Watching2
- Stars in 28 days+10
- CreatedOct 14, 2025
- First seen by usNov 7, 2026
- CheckedNov 7, 2026