Compressed text paging over OSC. https://git.yummers.dev/FastTextPager.git/atom?h=master 2025-07-24T03:43:25+00:00 2025-07-24T03:43:25+00:00 yum yum.food.vr@gmail.com 2025-07-24T03:43:25+00:00 urn:sha1:043a447133695bfd2285a534b941db972873a692 2025-07-24T02:05:15+00:00 yum yum.food.vr@gmail.com 2025-07-24T02:05:15+00:00 urn:sha1:9bf33a4cad8196bfe7253c841ab5c35ffdbc0173 Segment metadata can now be logged to a json as the app runs. The goal is to identify the params that heavily correlate with hallucinations. Also: * use 7zip for compression in build, speeding things up * log dll download progress every few seconds * shrink package 2025-07-24T00:41:49+00:00 yum yum.food.vr@gmail.com 2025-07-24T00:41:49+00:00 urn:sha1:790c91d7ad515c3c0a22ca1341316265b8f0d779 * fix model acquisition * fix local beepsnd * fix volume control 2025-05-31T04:31:05+00:00 yum yum.food.vr@gmail.com 2025-05-31T04:31:05+00:00 urn:sha1:73de7cb2d8fb964e7f76ab55420e9bc331bf7bea - add desktop and vr input threads - add audio feedback for input - add volume control for audio feedback - add UI for custom chatbox/built in chatbox - add ability to dismiss built in chatbox (sync empty messages) - limit lines in python console - limit length of each transcript 2025-05-30T20:34:23+00:00 yum yum.food.vr@gmail.com 2025-05-30T20:32:36+00:00 urn:sha1:7fb9c575aea4d318e9c14b82174d1b323171b62b - fix unicode output from python terminal - fix cpu inference - add filters - add beam search params to UI - DRY up config definition in UI 2025-05-30T09:50:55+00:00 yum yum.food.vr@gmail.com 2025-05-30T09:50:55+00:00 urn:sha1:e1b3f638a1ea448de9691f69eb62ebf4c3944c9f - Filters actually get applied now, huge accuracy boost - Use silero-vad python library instead of rolling our own - Expose prompt parameter - Auto setup venv on launch - Clean up python output - Auto acquire all dependencies on launch - Add icon 2025-05-30T02:45:48+00:00 yum yum.food.vr@gmail.com 2025-05-30T02:45:48+00:00 urn:sha1:f97cef182de55b6dbae8d2bc0477acfca6cc1f66 1. main STT app works in new project structure 2. UI dumps mics on startup to populate mic list 3. add missing deps (hf-xet, wave) 4. normalize audio volume when transcribing. Probably still wrong tbqh. 5. add checkbox to save audio segments & improve logic so only segments with speech get saved. 6. add default config settings 2025-05-18T06:54:56+00:00 yum yum.food.vr@gmail.com 2025-05-18T06:41:20+00:00 urn:sha1:f8e95c0b85288a10f435e0edabf43defa0c303ac