GitHub · Python
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.
- Stars
- 179
- Forks
- 19
- Stars gained in 24 hours
- 0
- Forks gained in 24 hours
- 0
Topics: asr, audio-llm, forced-alignment, huggingface, llm, lora, multimodal, pipecat, pytorch, qwen
Latest data point: Nov 21, 2026 · 179 stars · 19 forks