Preview and save multiple samples of the same prompt

by esuriddick - opened Apr 15

Apr 15

Hi,

I see in the model's page that you can generate multiple samples for the same prompt using, for example:
prompts = [
"A car engine revving",
"A dog barks and rustles with some clicking",
"Water flowing and trickling"
]
audios = tango.generate_for_batch(prompts, samples=2)

This will create two samples per prompt, so audios will comprise 2 sounds per prompt.

How do you preview the sounds and then save the one you want? I've tried using indexes, but to no success.

Regards,
esuriddick

soujanyaporia

Deep Cognition and Language Research (DeCLaRe) Lab org Apr 15

Dear Esurddick,

Thanks for reaching out to us. Would you mind creating an issue https://github.com/declare-lab/tango/issues. It is easier for us to track issues on Github and respond timely.

Thanks for understanding.

Best,
Soujanya

esuriddick

Apr 16

Hi Soujanya,

I've done it: https://github.com/declare-lab/tango/issues/45

Closing this thread now.

esuriddick changed discussion status to closed Apr 16

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment