TaSTT.git/Images, branch v0.20.0 Free self-hosted STT for VRChat. https://git.yummers.dev/TaSTT.git/atom?h=v0.20.0 2022-12-19T03:11:47+00:00 Add ability to select model 2022-12-19T03:11:47+00:00 yum yum.food.vr@gmail.com 2022-12-19T03:11:47+00:00 urn:sha1:b7b2b112a106138d99dda3f259620b350c896f1a * icon now works when pinned to taskbar * add model selection * add script to dump mic devices * whisper models now download into the virtual environment Add logo 2022-12-17T00:05:43+00:00 yum yum.food.vr@gmail.com 2022-12-17T00:04:33+00:00 urn:sha1:f368e34070331c5c7900d98e10fddccf7c9fd0ff * GUI now shows logo * Add package.ps1 to generate distributable application bundle * Rename ~GUI to GUI * Add ScopeGuard class Shorten audio window to 10 seconds 2022-11-23T03:01:01+00:00 yum yum.food.vr@gmail.com 2022-11-23T03:01:01+00:00 urn:sha1:9f87674d1b484a2e61e87ad53d8ebcf9985dce6b This helps with temporal stability in long-running transcriptions, and lets us get rid of that hack where we refuse to update old pages. Update STT demo 2022-11-23T02:34:42+00:00 yum yum.food.vr@gmail.com 2022-11-23T02:34:42+00:00 urn:sha1:a7a52b884061b154eaae6b0a8c0d5b443cbb8abe Zero mistranscribed words. One minor hiccup caused by instability in the (very long) transcription. I think the paging indicator is also buggy. String matching no longer relies on spaces 2022-11-06T20:50:38+00:00 yum yum.food.vr@gmail.com 2022-11-06T20:50:38+00:00 urn:sha1:7146acb9d4ad751fc5ced411a2990d0aad17d08f Add a `matchStrings` which does basically the same thing as `matchStringList` except it doesn't split the input at space boundaries. I think this should work better for Japanese and Chinese, since they don't use spaces. Doesn't seem to cause any accuracy regressions for English. Also update the README. OSC controller uses one sync per region instead of 2 2022-11-05T20:20:28+00:00 yum yum.food.vr@gmail.com 2022-11-05T20:19:47+00:00 urn:sha1:da8e8d93813ca85a78653587ed23c90820763e69 My theory as to why this seems to work: VRChat batches parameter updates together and applies them simultaneously. Thus we don't run into the expected failure mode where we update the prior region before paging over to the next region. * Fix beep feature * update the STT demo Add speech-to-text demo 2022-11-04T07:20:25+00:00 yum yum.food.vr@gmail.com 2022-11-04T07:20:25+00:00 urn:sha1:ca10de9a5cb2a9b360bc0cd2c357f8d0041f0fca Add LICENSE 2022-10-03T00:24:19+00:00 yum yum.food.vr@gmail.com 2022-10-03T00:24:19+00:00 urn:sha1:d4556af258ae3911c83ece4b817335e8c5a2a2d2 * Update README with contribution instructions & design details. * Add text-to-text demo gif * Document known Unity landmines in generate.sh.