Free self-hosted STT for VRChat. https://git.yummers.dev/TaSTT.git/atom?h=v0.11.0 2023-04-24T03:52:36+00:00 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. 2023-03-08T23:36:46+00:00 yum yum.food.vr@gmail.com 2023-03-08T23:36:46+00:00 urn:sha1:12b6447a87da8077c7dd12b92eefc27dcf7f0818 A user saw an error like `ModuleNotFoundError: No module named _socket`. StackOverflow blames this on PYTHONPATH, so let's try setting it. * Fix latent bug in Scripts/transcribe.py. PyAudio.open() positional parameters must be specified in correct order, even when telling it which parameter is which. *shrug* 2023-02-23T05:54:39+00:00 yum yum.food.vr@gmail.com 2023-02-23T05:49:58+00:00 urn:sha1:718319ee7b79d7cdbead5d765769b50c25e968f4 This reverts commit cece1ee8f1b985c2a89adb661dd02c6d44787f67. This does *not* in fact result in improved temporal stability. It makes makes things so unstable that even single-sentence messages fail to ever stabilize. 2023-02-23T05:49:22+00:00 yum yum.food.vr@gmail.com 2023-02-19T22:15:30+00:00 urn:sha1:cece1ee8f1b985c2a89adb661dd02c6d44787f67 Per the Whisper source code, this should result in better temporal stability. 2023-02-19T20:10:13+00:00 yum yum.food.vr@gmail.com 2023-02-19T19:46:43+00:00 urn:sha1:52f743e43a9ef582e04d7a363fbda19824db6cc7 Allows sustained exponential backoff when not transcribing. Used to cap out at 1s. * Add more items to README TODO list * Adjust emote metadata * Emotes bugfix: Non-existent emote map doesn't cause transcription engine to bail out. 2023-02-13T22:36:25+00:00 yum yum.food.vr@gmail.com 2023-02-03T02:00:18+00:00 urn:sha1:1cb5bdfe8cba6fe4647448cd3cf0c63ecbd7dfc2 Emotes require 2 bytes per char. They're encoded into the region [0xE000, infinity). The texture is 4k, and uses 1k vertical pixels per emote segment, for a maximum of 32 segments. * Reduce volume of noise indicator by 90%. Quiet is probably better. Might want to add a volume slider idk. * Bugfix: emotes without a transparency channel now work * Address a couple Unity performance complaints about the shader 2023-02-13T22:36:20+00:00 yum yum.food.vr@gmail.com 2023-02-02T09:02:03+00:00 urn:sha1:7c6894614dcc3ebc5d4c8839b64f4da761b5ccf0 Done: * Users can add images to Fonts/Emotes/ * The basename of that image ('clueless.png' becomes 'clueless') is the keyword to make the image show up in game. * Fix a bug in the shader where letters on the 2nd texture and later would have UV outside of [0.0, 1.0] Not yet implemented: * transcribed words are encoded using emotes mapping 2023-02-04T23:26:41+00:00 yum yum.food.vr@gmail.com 2023-02-04T21:16:37+00:00 urn:sha1:92fea304613bacfa014e1fbaf9fddb82e4f33d62 * Reduce noise on/off indicator volume by 50% 2023-01-25T20:38:28+00:00 yum yum.food.vr@gmail.com 2023-01-25T20:38:28+00:00 urn:sha1:227ff7aa0ed2fd03c54ae53aa01430012ff3f7d0 We use a button to start/stop transcription. Previously this was hardcoded to left joystick. Now users can pick from {left, right} x {joystick, a, b}. 2023-01-22T23:35:00+00:00 yum yum.food.vr@gmail.com 2023-01-22T23:05:54+00:00 urn:sha1:1c056bf385d2c48f6e4f77da513060c04415252c VRChat exposes a built-in chatbox which can be seen by anyone who has it enabled. This was not the case when I started this project: the chatbox would only be visible to friends. Since this is clearly useful, enabling the STT on public models, let's enable sending data to it. Caveats: * The built-in chatbox has anti-spam tech which limits us to updating about once every 2 seconds. The custom chatbox has no such limitation and is thus typically much faster.