Free self-hosted STT for VRChat. https://git.yummers.dev/TaSTT.git/atom?h=v0.12.0 2023-05-31T02:13:25+00:00 2023-05-31T02:13:25+00:00 yum yum.food.vr@gmail.com 2023-05-31T02:01:56+00:00 urn:sha1:0bda49279ec80187d49a922ff2a47141ffb2fd8f NLLB needs its input to be split up into sentences. I use the sentence_splitter Python package to do this. It supports ~20 Western European languages, but notably, no Asian languages. * Sort spoken language list. English is still at the top. * Remove 'Translation source' dropdown. Infer this from the spoken language. * Add lang_compat.py to map language codes between the various libraries (whisper, nllb, sentence_splitter). * Fix bug where old text would appear in textbox when you first bring it up. 2023-05-26T05:00:56+00:00 yum yum.food.vr@gmail.com 2023-05-26T04:45:09+00:00 urn:sha1:84f09e1fdf15644d1ea5f955889581932e4f6a8e Use Meta's No Language Left Behind (NLLB) algorithm to provide translation capabilities into 200 languages. Obviously most are very untested. This requires either 4.1 or 7.1 GB of RAM and significiantly increases transcription latency. 2023-05-25T06:07:07+00:00 yum yum.food.vr@gmail.com 2023-05-25T06:07:07+00:00 urn:sha1:eed2e8915d83796679c0b7a3ea9121d329ceddab Add 3 filters: * Remove trailing period * Convert to uppercase * Convert to lowercase All may be composed. Upper/lower just overwrite each other so just use one. 2023-05-25T05:44:34+00:00 yum yum.food.vr@gmail.com 2023-05-25T05:44:34+00:00 urn:sha1:3dd5e839449f5056ca9493c0eab6a3e02fe1e86e I forgor to put them into ApplyConfigToInputFields. The reason this is necessary: we need to create the text field where we log things before we can deserialize the config. To keep the code structure "clean" I just wrote another function to apply the config (ApplyConfigToInputFields). However I have to remember to update it when I add new fields. 2023-05-25T05:34:55+00:00 yum yum.food.vr@gmail.com 2023-05-25T05:34:55+00:00 urn:sha1:ebab21e22dea7931a8a7db05ff26d60cec4f5b5b UI now has a checkbox for the uwu filter. Does not materially affect resource usage or latency when enabled. 2023-05-25T01:39:27+00:00 yum yum.food.vr@gmail.com 2023-05-25T01:39:27+00:00 urn:sha1:156a592f35ced01008516e559b62db8829baa787 Use UwwwuPP to translate your boring old speech into uwu-ified version. Still need to add a UI toggle for this. 2023-05-23T19:28:01+00:00 yum yum.food.vr@gmail.com 2023-05-23T19:28:01+00:00 urn:sha1:0f08da58a59a126f5307395e822fd140f15f8b36 Remove the button. This is a big source of confusion for new users. Now it happens automatically upon starting any task that needs it. * Begin removing CPP implementation of Whisper. faster-whisper is a much easier/better solution. * Flip default of `clear OSC configs` from false to true. 2023-05-22T11:04:09+00:00 yum yum.food.vr@gmail.com 2023-05-22T10:59:45+00:00 urn:sha1:8fafea9d026b2b65599456e70d3f5aa61ef073d1 Users can now configure a keybind to start/stop/dismiss the STT when in desktop mode. The default keybind is ctrl+x, since by default VRC doesn't use 'x' for anything. 2023-05-22T04:27:50+00:00 yum yum.food.vr@gmail.com 2023-05-22T04:27:50+00:00 urn:sha1:2d544407e64bed9328ee493d3daa095b20445b52 Useful on devices with multiple GPUs, such as gaming laptops. * Update GUI/README.md. 2023-04-25T21:27:23+00:00 yum yum.food.vr@gmail.com 2023-04-25T21:27:23+00:00 urn:sha1:8534d17ab00de729867bb482ab204854127ed2a1 Affinity mask no longer affects performance. String matching is still needed for temporal stability in fast-paced long-form transcription tasks.