Spaces:

jan-hq

/

Ichigo-llama3.1-s-v0.4

like 5

Running on Zero

I only have use for this model if it can take in an audio file and follow text instructions for that audio file to produce a text sequence. Is that currently possible? Particularly, if it is would you be willing to change the space so I can test its capabilities more simply, as would others who desire such abilities.