TaSTT.git/Scripts/transcribe_v2.py, branch v0.15.2Free self-hosted STT for VRChat.https://git.yummers.dev/TaSTT.git/atom?h=v0.15.22023-09-11T20:53:14+00:00Pin huggingface_hub to 0.16.42023-09-11T20:53:14+00:00yumyum.food.vr@gmail.com2023-09-11T20:46:57+00:00urn:sha1:0447f37fb744a1b350f6b92e4d140dbdb1c8d3ec
0.17.x are breaking faster_whisper's ability to download models.
Also:
* Start using frozen requirements.txt.
* Conditionally install torch & legacy whisper only when doing
mechanical optimization.
Introduce notion of PresentationFilter2023-09-11T05:52:52+00:00yumyum.food.vr@gmail.com2023-09-11T05:51:16+00:00urn:sha1:d3c325c4c4dd954a75267b013f33f5f3c5d041bc
... and restructure RemoveTrailingPeriod as a filter instead of as a
plugin.
Plugins have the power to change transcription data as it comes along,
but don't have access to the entire transcript. Filters have access to
the entire transcript but can't durably change it.
TODO
* This does not work with data passed through OSC
Fix paging bug2023-09-11T01:33:08+00:00yumyum.food.vr@gmail.com2023-09-11T01:29:59+00:00urn:sha1:920d6dfeeac132488c85311512fe9e5da505c4a8
OSC was paging using incorrect board resolution. Use cfg to provide this
data.
Fix local audio indicators2023-09-10T22:41:25+00:00yumyum.food.vr@gmail.com2023-09-10T22:41:25+00:00urn:sha1:4a4909919223a7446944c6248472c7f71a30307cAdd plugin interface2023-09-10T21:45:45+00:00yumyum.food.vr@gmail.com2023-09-10T21:45:45+00:00urn:sha1:2dc2f63686fc0137931f675f579d3e528861433d
... and use it to implement translation and text filters.
Also fix display of non-English characters in browser src.
Bugfix: only cap display of transcript at 4K chars2023-09-10T10:50:46+00:00yumyum.food.vr@gmail.com2023-09-10T10:50:46+00:00urn:sha1:da360bcd1870650848daa034aa31b8a337caecc7
Actually retain the whole transcript to avoid breaking the OSC pager.
Also constrain the UI buffer size by characters instead of lines. Since
some lines can be massive and others short, characters are a better way
of consistently keeping the UI memory in check.
Add UI for transcription loop delay2023-09-10T07:29:04+00:00yumyum.food.vr@gmail.com2023-09-10T07:28:03+00:00urn:sha1:4ee396584c348c11e0272f0c2842f6a5d3175586
Allows users to directly modulate the performance-latency tradeoff.
Also:
* Bump up UI buffer to 1k lines.
* Fix browser source reset. It now also resets preview text.
Browser source now shows preview text as slightly transparent2023-09-10T06:18:32+00:00yumyum.food.vr@gmail.com2023-09-10T06:18:32+00:00urn:sha1:9924a141b0b1266671915be12e21df6c8f4c5366
Improves viewer experience.
Add UI for max speech duration2023-09-10T05:32:35+00:00yumyum.food.vr@gmail.com2023-09-10T05:26:09+00:00urn:sha1:ae866f553d3db67030e37ce315707d72982f4063
Also fix bug when not using previews. Audio buffer no longer grows
without bound while there's no speech.
Constrain log file, UI text field, and transcript sizes2023-09-10T04:46:10+00:00yumyum.food.vr@gmail.com2023-09-10T04:41:36+00:00urn:sha1:286dcae5e087db817f3350cf442145107b25bc9c
Log file is constrained to 1 MB and UI to 100-200 lines. 1k lines is too
high to keep the UI from lagging.
Transcript is constrained to 4k characters.
Also put a 5 ms sleep in the transcription hot path.