Dec 4, 2025

1. 02:48

   reduce buffer duration and adjust transcription parameters for lower latency

   mic3333
   8493d7f
2. 02:41

   improve sentence splitting to avoid breaking on common abbreviations like Mr., Ms., Dr., etc.

   mic3333
   649d6e6
3. 02:37

   remove live subtitle display and only show full transcript in the UI

   mic3333
   41e2ea2
4. 02:01

   improve near-duplicate detection to compare against all existing sentences instead of only the last one

   mic3333
   5db4d4b
5. 01:55

   add near-duplicate detection to suppress streaming variants of the same sentence

   mic3333
   67ce003
6. 01:46

   update live subtitle to persist last sentence when no incomplete audio

   mic3333
   8d1f680
7. 01:15

   refactor to use per-session state instead of global variables

   mic3333
   8a63ea7