HackerTrans
TopNewTrendsCommentsPastAskShowJobs

bazlan

no profile record

Submissions

Show HN: Vui – open-source voice mode

twitter.com
2 points·by bazlan·mese scorso·0 comments

[untitled]

1 points·by bazlan·mese scorso·0 comments

Open Source Voice Mode

twitter.com
2 points·by bazlan·mese scorso·0 comments

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

twitter.com
11 points·by bazlan·2 mesi fa·9 comments

Open Source NotebookLM – 100M

twitter.com
18 points·by bazlan·anno scorso·5 comments

comments

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

A 100M podcast model

https://huggingface.co/spaces/fluxions/vui-space
bazlan
·anno scorso·discuss
[dead]
bazlan
·anno scorso·discuss
[dead]
bazlan
·anno scorso·discuss
fluxions.ai has a similar model
bazlan
·2 anni fa·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?