PrototypeCommon
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.
- Owner
- alexkroman (personal account)
- Stars
- Stars: 178
- Forks
- Forks: 19
- Language
- Python
- License
- MIT
- Created
- 2025
- Topics
- asraudio-llmforced-alignmenthuggingfacellmloramultimodalpipecatpytorchqwen
- Tier
- Prototype (100 to 249 ★) What this tier means
Nearby in Python
All Python repos- ThinkFlowLab/system1-agentsStars: 178PythonPrototype
- liguozheng-ac/japanese-speech-xrayStars: 178PythonPrototype
- vibe-motion/soundStars: 178PythonPrototype
- jbalogh/jingoStars: 178PythonPrototype
- turian/neural-language-modelStars: 178PythonPrototype
- flupke/pypotraceStars: 178PythonPrototype