Free self-hosted STT for VRChat. https://git.yummers.dev/TaSTT.git/atom?h=v0.20.0 2024-07-12T23:20:40+00:00 2024-07-12T23:20:40+00:00 yum yum.food.vr@gmail.com 2024-07-12T23:20:40+00:00 urn:sha1:6dc21f859e2443a80e7b46a5ed890a198af38ef9 Use some js magic to deduce the hostname instead of hardcoding localhost. If you used the browser source under 127.0.0.1, then you'd get XSS blocked from making the ajax calls. This fixes that. 2024-07-12T22:53:19+00:00 yum yum.food.vr@gmail.com 2024-07-12T22:53:19+00:00 urn:sha1:861df4f98db7c8a87fd11f9081b0c8c6d6d40f29 2023-09-19T04:23:14+00:00 yum yum.food.vr@gmail.com 2023-09-19T04:00:56+00:00 urn:sha1:c2bc70c18d2fd1c3601b32f2a93b3b4a704786a5 BrowserSource now fades text out continuously over time. TODO * Delete C++ webserver, browsersource, transcript code * Add UI for text age fading 2023-09-10T06:18:32+00:00 yum yum.food.vr@gmail.com 2023-09-10T06:18:32+00:00 urn:sha1:9924a141b0b1266671915be12e21df6c8f4c5366 Improves viewer experience. 2023-07-01T02:46:17+00:00 yum yum.food.vr@gmail.com 2023-07-01T02:44:27+00:00 urn:sha1:4f3131b4a36d8e1557edb31d3754a431717dab7b Circle goes red when speaking, grey when done. Ideally it would be in the top right portion of the browser source, but this is a good start. Also, hard-cap transcripts to 4096 chars. This prevents the STT from lagging during long sessions. 2023-06-27T08:50:40+00:00 yum yum.food.vr@gmail.com 2023-06-27T08:47:53+00:00 urn:sha1:8ff761153b7de23a9556f2af179ab3bf4b9849a5 Should improve legibility. * Update README 2023-06-26T08:46:42+00:00 yum yum.food.vr@gmail.com 2023-06-26T07:58:58+00:00 urn:sha1:0ed379f2c99ac5c126a6f101965ef1eaa58c017b Transcription output now streams to localhost:8097. In OBS: * Create a browser source. * url: localhost:8097 * width: 2200 * height: 400 TODO: * Put behind toggle. * Create input field for port. Misc cleanup: * transcribe.py: Drop frames from audio capture thread instead of the transcription thread. Doing it the other way would result in occasional data loss. 2023-04-24T03:52:36+00:00 yum yum.food.vr@gmail.com 2023-04-24T03:52:36+00:00 urn:sha1:b4bb6524652e0f76834ca26a4afa232855ca1348 This is a much faster, lower-VRAM reimplementation of Whisper in Python. Early testing is extremely promising: fast transcription speed, extremely low resource usage (CPU/RAM/VRAM), high accuracy. 2023-02-26T00:46:34+00:00 yum yum.food.vr@gmail.com 2023-02-26T00:46:34+00:00 urn:sha1:a8d1b69d2afbb6ba43c3f97e383dc71b097f69fd * Implement HTTPMapper classes * Browser source respects user-configured source port 2023-02-24T22:35:02+00:00 yum yum.food.vr@gmail.com 2023-02-24T22:35:02+00:00 urn:sha1:8170273eb786d52aa9a9c1cdbef1357c32d95471 It's a crashy mess, but it sort of works. * Add Transcript class to send transcription segments between layers