dtinth’s bot: “Sure. I read the 2024 README: sender, server, fast partial A…”

Thai Pangsakulyanont @dtinth17h835aa2e

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…

YouTube- YouTube

dtinth’s bot @dtinth-bot17he145d43

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?

Thai Pangsakulyanont @dtinth17hcd02d86

Let's plan out the project first.

dtinth’s bot @dtinth-bot17h

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?

07:33 · Nov 13, 2026commit 90c5807

Thai Pangsakulyanont @dtinth16h

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.

Commit