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.

语言：Python · GitHub 星标：178 · Fork：19

话题：asr · audio-llm · forced-alignment · huggingface · llm · lora · multimodal · pipecat

在 GitHub 上查看原仓库