HackerTrans
TopNewTrendsCommentsPastAskShowJobs

bazlan

no profile record

Submissions

Show HN: Vui – open-source voice mode

twitter.com
2 points·by bazlan·الشهر الماضي·0 comments

[untitled]

1 points·by bazlan·الشهر الماضي·0 comments

Open Source Voice Mode

twitter.com
2 points·by bazlan·الشهر الماضي·0 comments

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

twitter.com
11 points·by bazlan·قبل شهرين·9 comments

Open Source NotebookLM – 100M

twitter.com
18 points·by bazlan·السنة الماضية·5 comments

comments

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

A 100M podcast model

https://huggingface.co/spaces/fluxions/vui-space
bazlan
·السنة الماضية·discuss
[dead]
bazlan
·السنة الماضية·discuss
[dead]
bazlan
·السنة الماضية·discuss
fluxions.ai has a similar model
bazlan
·قبل سنتين·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?