TaSTT.git, branch v0.13.1Free self-hosted STT for VRChat.https://git.yummers.dev/TaSTT.git/atom?h=v0.13.12023-07-07T09:35:51+00:00Enforce a stricter avg_logbprob than default2023-07-07T09:35:51+00:00yumyum.food.vr@gmail.com2023-07-07T09:30:18+00:00urn:sha1:7a576bcac1c37c3c5a59fadf172aa70b15ff83c8
Common hallucinations sneak in around -0.9 avg_logprob.
Also:
* Limit temperatures to just 0.0. Multiple values cause latency to
occasionally spike.
Filter out segments based on avg_log_prob & no_speech_prob2023-07-07T08:58:45+00:00yumyum.food.vr@gmail.com2023-07-07T08:57:56+00:00urn:sha1:2793ac9dd31059f2fc29f7978bcb688a7de664ed
Surprisingly, these args do not cause transcribe() to omit those
segments from the result, so we have to manually filter them out.
Hallucinated phrases generally have one or both of these params set
high.
Use 16-bit ints with generated silence2023-07-07T08:44:28+00:00yumyum.food.vr@gmail.com2023-07-07T08:44:28+00:00urn:sha1:742eb86d652d7689bbf3ae8b286bf0a6b1c2380d
Each sample of audio data is a 16-bit int, not an 8-bit int.
Fix performance regression2023-07-07T08:27:02+00:00yumyum.food.vr@gmail.com2023-07-07T08:27:02+00:00urn:sha1:cdc4889cb5e752d00f7f8933a5486f4f3441f6e9
Each chunk of audio samples should be encoded as a binary string, not as
a list.
Enforce minimum 5.0 second duration on audio buffer2023-07-07T00:36:14+00:00yumyum.food.vr@gmail.com2023-07-07T00:36:14+00:00urn:sha1:d0d3b18ad0a859e5e7a1cc5b8a569349b505c924
New commit logic would reduce buffer to a size smaller than this,
causing it to hallucinate things like:
* "See you next time!"
* "Thanks for watching!"
* "Bye!"
The hope is that by keeping the buffer at least 5.0 seconds long, as
described in the paper, this will cut down on these events.
Begin work on proxy server2023-07-04T02:36:13+00:00yumyum.food.vr@gmail.com2023-07-04T01:44:43+00:00urn: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.
Add profanity filter2023-07-02T23:45:07+00:00yumyum.food.vr@gmail.com2023-07-02T23:45:07+00:00urn:sha1:7888ccc96d001512dd3bdc01f299856e86c876f5
Forgot to check this in, oops!
Add visual commit indicator to OBS browser source2023-07-01T02:46:17+00:00yumyum.food.vr@gmail.com2023-07-01T02:44:27+00:00urn: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.
Bugfix: trailing period filter ignores ellipses2023-07-01T01:55:12+00:00yumyum.food.vr@gmail.com2023-07-01T01:55:12+00:00urn:sha1:9ab500036bdfa87215e9a05fc167c4d9dea8e437
... also print out "Ready!" when the STT is done loading.
Merge pull request #3 from jsopn/fix-gpu-device-index2023-06-30T07:15:50+00:00yum-food114886918+yum-food@users.noreply.github.com2023-06-30T07:15:50+00:00urn:sha1:ab1d4499e1b3198b387a1e2d7333a93f694cdfae
Set GPU device index in whisper model