Free self-hosted STT for VRChat. https://git.yummers.dev/TaSTT.git/atom?h=v0.17.0 2023-12-09T02:15:03+00:00 2023-12-09T02:15:03+00:00 yum yum.food.vr@gmail.com 2023-12-09T02:15:03+00:00 urn:sha1:859caec3d5c1b6aa9eee98571af3324b6ed1bd21 Paging is now slower but more reliable. 2023-12-09T02:13:56+00:00 yum yum.food.vr@gmail.com 2023-12-09T02:13:32+00:00 urn:sha1:15368618a109eeec69209a6693839eb359ecd190 2023-11-07T23:05:29+00:00 yum yum.food.vr@gmail.com 2023-11-07T23:05:29+00:00 urn:sha1:dbb2f72792e2af3ff220313f84bf76a9a1ddbeb4 I converted distil-whisper-medium.en to CTranslate2 format and uploaded it to huggingface. This model is exceptionally fast and light compared to the non-distilled version, at the cost of some accuracy. 2023-10-06T01:28:42+00:00 yum yum.food.vr@gmail.com 2023-10-06T01:22:55+00:00 urn:sha1:add7bd8ef86ec21cd1327eb45bcb739aa54f7db8 When hot-miking into the built-in chatbox, there are sometimes long pauses in conversation. After these pauses, it's undesirable to show the transcript generate before the pause. This feature makes it so that those transcripts can be dropped. Also: * Limit number of segments sent to browser source to 10. Allow this to grow up to 10 segments before dropping the first 5 segments. * Silence warnings generated by `install_in_venv`, used by e.g. translation codepath. * Enable audio normalization to improve accuracy when speaking softly, at the cost of some accuracy when speaking normally. Credit: user endo0269 on Discord suggested this feature. 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 2023-09-17T20:05:29+00:00 yum yum.food.vr@gmail.com 2023-09-17T20:05:29+00:00 urn:sha1:b037e158065bec98d91231c0c6443b63f45ec7ea Default is normal prio. 2023-09-16T22:49:55+00:00 yum yum.food.vr@gmail.com 2023-09-16T22:49:55+00:00 urn:sha1:d4c85f4ac4cb627e2611359d18615d76eda29c90 * uwu filter no longer adds extra whitespace before/after segments. This would defeat commit logic. * disabling phonemes works again - path to prefab was being quoted twice, breaking the codepath. 2023-09-14T04:55:05+00:00 yum yum.food.vr@gmail.com 2023-09-14T04:43:33+00:00 urn:sha1:703e183e430f15aff6005d38aefcacf91e2314cd Remove unused proxy code, curl, and images. 2023-09-12T22:33:18+00:00 yum yum.food.vr@gmail.com 2023-09-12T22:33:18+00:00 urn:sha1:8fcc6c248554a0b08ecd4b43cc0971b78810c080 Oops :) 2023-09-11T22:41:26+00:00 yum yum.food.vr@gmail.com 2023-09-11T22:41:26+00:00 urn:sha1:0912622c443acd5c80b8cf87367a8dc1c9463636