Top New Trends Comments Past Ask Show Jobs

bazlan

no profile record

Submissions

Show HN: Vui – open-source voice mode

2 points·by bazlan·last month·0 comments

[untitled]

1 points·by bazlan·last month·0 comments

Open Source Voice Mode

2 points·by bazlan·last month·0 comments

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

11 points·by bazlan·2 months ago·9 comments

Open Source NotebookLM – 100M

18 points·by bazlan·last year·5 comments

comments

·2 months ago·discuss

What's the buisness?

·2 months ago·discuss

thanks!

·2 months ago·discuss

Haha yeah this is the idea

·2 months ago·discuss

Definitely possible but tricky with stacks > 1B in params

·2 months ago·discuss

[dead]

·10 months ago·discuss

Sad to not see vui on the comparisons!

A 100M podcast model

https://huggingface.co/spaces/fluxions/vui-space

·last year·discuss

[dead]

·last year·discuss

[dead]

·last year·discuss

fluxions.ai has a similar model

·2 years ago·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?

·2 years ago·discuss

Let it die