I built a live captioning system for local technical talks back in 2024. Back then it requires putting multiple models together so it works well enough with Thai language + tech jargons. https://www.youtube.com/watch?v=rXMS212fZSA
The models have improved much since then, so…
Commit
ce485f3
Here! Fresh orphan branch
v2 is checked out and empty. Where do you want to start: the transcription model, the audio capture side, or the viewer?Let's plan out the project first.
Sure. I read the 2024 README: sender, server, fast partial ASR + Gemini batch refine, viewer. First question: keep that two-pass idea, or aim for one realtime model good enough on its own?
Basically, I aim for a single real-time model, but the transcript can be later post-processed with LLM if needed.
re. model, see:
- https://help.aliyun.com/en/model-studio/real-time-speech-recognition-user-guide?spm=a2c4g.11186623.help-menu-2400256.d_1_2_2_0_1.362dc690INtcxw
-…
help.aliyun.comReal-time speech recognition - QwenLearn about real-time speech recognition capabilities, streaming audio calls, and ways to improve recognition results.
Got it: one realtime model, server-side VAD, recorder, chunked resumable sender. Reading vxasr + the Qwen docs, then installing mattpocock/skills and setting up. Will report back.
commit ce485f3