Free self-hosted STT for VRChat. https://git.yummers.dev/TaSTT.git/atom?h=master 2023-07-04T02:36:13+00:00 2023-07-04T02:36:13+00:00 yum yum.food.vr@gmail.com 2023-07-04T01:44:43+00:00 urn:sha1:76ae7c28ea6224b2c919122d5dc71bcc00a0ecaa Create a simple server with 3 endpoints: * /create_session: Create a session and return its identifier. * /set_transcript: Update a session's transcript. * /get_transcript: Fetch a session's transcript. Right now the session ID provides authentication *and* authorization. There is no public/private ID so you have to trust whoever you share your ID with. IDs are long and generated by the server, so it should be somewhat secure against low-effort hacking. Other updates: * Drop whisper_requirements.txt - no longer needed. * Vendor curl to make it easier to interact with the server. TODO: * Fuzz test the server. 2023-02-23T05:49:29+00:00 yum yum.food.vr@gmail.com 2023-02-21T21:19:43+00:00 urn:sha1:9a97fbc3c583ccd518d838faaaa36ed9aa5558e1 Use Const-me/Whisper to perform transcription. This implementation is vastly more efficient: CPU usage, memory usage, and VRAM usage are all dramatically reduced. It's slightly less accurate when comparing the same model (due to the lack of beam search decoding), but since you can use larger models, the impact is largely a wash.