HackerTrans
TopNewTrendsCommentsPastAskShowJobs

bazlan

no profile record

Submissions

Show HN: Vui – open-source voice mode

twitter.com
2 points·by bazlan·w zeszłym miesiącu·0 comments

[untitled]

1 points·by bazlan·w zeszłym miesiącu·0 comments

Open Source Voice Mode

twitter.com
2 points·by bazlan·w zeszłym miesiącu·0 comments

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

twitter.com
11 points·by bazlan·2 miesiące temu·9 comments

Open Source NotebookLM – 100M

twitter.com
18 points·by bazlan·w zeszłym roku·5 comments

comments

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

A 100M podcast model

https://huggingface.co/spaces/fluxions/vui-space
bazlan
·w zeszłym roku·discuss
[dead]
bazlan
·w zeszłym roku·discuss
[dead]
bazlan
·w zeszłym roku·discuss
fluxions.ai has a similar model
bazlan
·2 lata temu·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?