HackerTrans
TopNewTrendsCommentsPastAskShowJobs

bazlan

no profile record

Submissions

Show HN: Vui – open-source voice mode

twitter.com
2 points·by bazlan·letzten Monat·0 comments

[untitled]

1 points·by bazlan·letzten Monat·0 comments

Open Source Voice Mode

twitter.com
2 points·by bazlan·letzten Monat·0 comments

VUI – open-source Jarvis stack with a 300M TTS Model

twitter.com
11 points·by bazlan·vor 2 Monaten·9 comments

Open Source NotebookLM – 100M

twitter.com
18 points·by bazlan·letztes Jahr·5 comments

comments

bazlan
·vor 2 Monaten·discuss
What's the buisness?
bazlan
·vor 2 Monaten·discuss
thanks!
bazlan
·vor 2 Monaten·discuss
Haha yeah this is the idea
bazlan
·vor 2 Monaten·discuss
Definitely possible but tricky with stacks > 1B in params
bazlan
·vor 2 Monaten·discuss
[dead]
bazlan
·vor 10 Monaten·discuss
Sad to not see vui on the comparisons!

A 100M podcast model

https://huggingface.co/spaces/fluxions/vui-space
bazlan
·letztes Jahr·discuss
[dead]
bazlan
·letztes Jahr·discuss
[dead]
bazlan
·letztes Jahr·discuss
fluxions.ai has a similar model
bazlan
·vor 2 Jahren·discuss
As someone who has worked in TTS for over 4 years now. I can tell you that evaluation is the most difficult aspect of generative audio ML.

How will this really check that the models are performing well vs just listening?