<feed xmlns='http://www.w3.org/2005/Atom'>
<title>TaSTT.git/Scripts/lang_compat.py, branch v1.0.0-beta01</title>
<subtitle>Free self-hosted STT for VRChat.</subtitle>
<id>https://git.yummers.dev/TaSTT.git/atom?h=v1.0.0-beta01</id>
<link rel='self' href='https://git.yummers.dev/TaSTT.git/atom?h=v1.0.0-beta01'/>
<link rel='alternate' type='text/html' href='https://git.yummers.dev/TaSTT.git/'/>
<updated>2025-07-24T05:53:08+00:00</updated>
<entry>
<title>Delete unused files</title>
<updated>2025-07-24T05:53:08+00:00</updated>
<author>
<name>yum</name>
<email>yum.food.vr@gmail.com</email>
</author>
<published>2025-07-24T05:53:08+00:00</published>
<link rel='alternate' type='text/html' href='https://git.yummers.dev/TaSTT.git/commit/?id=4539f87e36cb3ca554e1e174c19206b552107c57'/>
<id>urn:sha1:4539f87e36cb3ca554e1e174c19206b552107c57</id>
<content type='text'>
</content>
</entry>
<entry>
<title>Finish translation for Western European language speakers</title>
<updated>2023-05-31T02:13:25+00:00</updated>
<author>
<name>yum</name>
<email>yum.food.vr@gmail.com</email>
</author>
<published>2023-05-31T02:01:56+00:00</published>
<link rel='alternate' type='text/html' href='https://git.yummers.dev/TaSTT.git/commit/?id=0bda49279ec80187d49a922ff2a47141ffb2fd8f'/>
<id>urn:sha1:0bda49279ec80187d49a922ff2a47141ffb2fd8f</id>
<content type='text'>
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.
</content>
</entry>
</feed>
