Free self-hosted STT for VRChat. https://git.yummers.dev/TaSTT.git/atom?h=master 2022-12-18T01:51:12+00:00 2022-12-18T01:51:12+00:00 yum yum.food.vr@gmail.com 2022-12-18T01:51:12+00:00 urn:sha1:ee8213d1d2c2008d2d996929500c9e87dac325a3 GUI can now download all TaSTT dependencies and install them into a virtual environment. * Add buttons to check embedded python version & install dependencies * Add class to wrap interacting with embedded Python * Put all TaSTT python scripts into a folder 2022-12-15T07:04:29+00:00 yum yum.food.vr@gmail.com 2022-12-15T05:45:30+00:00 urn:sha1:8326dee0bf01956b450858212cbdba3403b32b0d Shave off ~500ms due to locking. Acquiring a threading.Lock takes hundreds of milliseconds and the global interpreter lock already takes care of most crashy race conditions, so just remove the locks. Avoid writing audio to disk, saving more time (and disk wear / IOPS). Add basic profiling to transcribe(). Omit timestamps, since we don't use them (maybe we should!) Shorten noise indicators to 350ms The whisper behavior where it repeats tokens causes certain transcriptions to take many seconds. I haven't thought about how to fix this, yet. 2022-11-26T01:57:42+00:00 yum yum.food.vr@gmail.com 2022-11-26T01:57:42+00:00 urn:sha1:89a929fe76e4dbd56436288055366d9416c13e74 Now we have a visual and auditory indicator for transcription. The auditory indicator is only heard by the user, and can be used to reset the state of the board prior to displaying. 2022-11-23T20:25:05+00:00 yum yum.food.vr@gmail.com 2022-11-23T20:24:07+00:00 urn:sha1:ae9ac5ba5942447f47d8d996d2d340381e730c33 Use a single indicator with 3 states: 1. green: actively speaking 2. orange: waiting for paging 3. red: up-to-date Use slightly nicer colors. 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. 2022-11-23T02:21:49+00:00 yum yum.food.vr@gmail.com 2022-11-23T02:21:49+00:00 urn:sha1:0f95401b7f7388b7ce3b6bf4d4aa1694f484db11 Coarse locking was causing audio frames to drop, severely degrading transcription quality. We really need a spoken word integration test. 2022-11-23T02:13:18+00:00 yum yum.food.vr@gmail.com 2022-11-22T23:36:19+00:00 urn:sha1:bd8b63a357bb374f5875f0fedf2d677589419810 Press joystick once to start recording, again to stop. When you start recording, any previous text on the board is cleared. Add 2 visual indicators: one to indicate speech, another to indicate that audio is paging. 2022-11-16T08:45:09+00:00 yum yum.food.vr@gmail.com 2022-11-16T08:45:09+00:00 urn:sha1:d2e06445c42b22d2b75f5da1980b7a8d833a9c5b Works a little better on longer transcriptions while maintaining the same improved performance on short transcriptions. We really need a benchmark to evaluate performance mechanically. 2022-11-15T05:36:13+00:00 yum yum.food.vr@gmail.com 2022-11-15T05:30:50+00:00 urn:sha1:2505a5cc486cd913db50a475e45c3701b9710282 After re-reading the paper, I noticed that they apply a couple optimizations I wasn't using. Use the top-level `whisper.transcribe` method, which is a little slower, but more accurate than the one I was using. Although this method is slower, it has better temporal stability due to the increased quality, which I think should make for an overall more responsive UX. Lower transcription quality means the paging layer has to waste time updating earlier cells. Also, drop the auto-commit stuff and go back to string stitching. I think it's better to let the user manually commit. A rework of the hand controls is probably coming soon. Finally, update README. 2022-11-12T23:02:34+00:00 yum yum.food.vr@gmail.com 2022-11-12T23:02:34+00:00 urn:sha1:9921697816c9f9473bac54444793f702e54d24a6 Board would lock up if you reset after the first page. osc_ctrl.clear() was assigning the wrong member :) Tweak continuous transcription logic: now we only commit if the transcription remains identical for N seconds.