TaSTT.git/Sounds, branch v0.15.4Free self-hosted STT for VRChat.https://git.yummers.dev/TaSTT.git/atom?h=v0.15.42023-09-01T08:06:44+00:00Various cleanup2023-09-01T08:06:44+00:00yumyum.food.vr@gmail.com2023-09-01T08:06:44+00:00urn:sha1:6753d81627d4467e649a6bb8dcb44c7eb8e42e1eBugfixes and tweaks2023-09-01T00:17:01+00:00yumyum.food.vr@gmail.com2023-09-01T00:11:11+00:00urn:sha1:3db4f81573d89f6ebefb5ec119c7d66affc1a4a0
* Temporarily restore normal process priority. Working on adding a UI
option to set STT prio.
* Give audio indicator phonemes a 1/3 chance to do nothing. Makes result
sound a little better imo.
* Quiet down steamVR thread when steamVR isn't running
* Fix use of `button_id` and `hand_id` in steamvr.py
* Increase amount of silence allowed before transcript from 1 to 5
seconds. You want enough buffer to allow for a few full transcripts,
else you risk spuriously dropping audio.
* Enable background loading in audio metadata (required by vrc sdk)
Continue work on in-game audio, revert steamvr.py2023-08-31T00:13:19+00:00yumyum.food.vr@gmail.com2023-08-31T00:13:19+00:00urn:sha1:358f3ed8c44bbe45d8f4546afeeb0afaae85ea8b
We now play arpeggiated *chords* of vowels instead of one, allowing for
a denser audio feedback mechanism.
Fix in-game audio indicator2023-08-30T06:29:04+00:00yumyum.food.vr@gmail.com2023-08-30T06:27:54+00:00urn:sha1:444914a701628ca2d1937f8d5cc9a714b478917c
Also fix prefab default size (no longer colossal).
TODO
* Add runtime & unity-time toggles
Add ability to type using STT2023-05-23T22:15:39+00:00yumyum.food.vr@gmail.com2023-05-23T22:12:04+00:00urn:sha1:78de7f02bc364606b0939d66903f02b2f91c141b
To use it, do a medium hold + long hold. Keep the long hold depressed
until you're done speaking. The transcription will be typed into the
currently selected input field.
* Add more audio feedback
* Make audio feedback play asynchronously so it doesn't slow down the
controller input state machine as much.
Built-in chatbox no longer shows empty messages2023-02-04T23:26:41+00:00yumyum.food.vr@gmail.com2023-02-04T21:16:37+00:00urn:sha1:92fea304613bacfa014e1fbaf9fddb82e4f33d62
* Reduce noise on/off indicator volume by 50%
Optimize transcription latency2022-12-15T07:04:29+00:00yumyum.food.vr@gmail.com2022-12-15T05:45:30+00:00urn: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.
Add on/off sound indicator (local)2022-11-26T01:57:42+00:00yumyum.food.vr@gmail.com2022-11-26T01:57:42+00:00urn: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.
redo speech noise2022-10-25T03:30:06+00:00yumyum.food.vr@gmail.com2022-10-25T03:30:06+00:00urn:sha1:4a5338bff2ed9e21b7011c87dfa21598e70e1b15add speech noise2022-10-25T01:19:53+00:00yumyum.food.vr@gmail.com2022-10-25T01:19:53+00:00urn:sha1:ddf0472f6c98f9cd9f0faa138f5bee9e5a2f674e