Edit: My bad; straightforward concatenation of prompts and audio array works fine.
Hi,
I am interested in the possibility of performing batch inference. I noticed some comments in the code that suggest batch support might be available, but I am not entirely sure if this is currently possible.
Could you please clarify if batch inference is supported in the current version of the code? If so, could you provide some guidance or examples on how to implement it?
Edit: My bad; straightforward concatenation of prompts and audio array works fine.
Hi,
I am interested in the possibility of performing batch inference. I noticed some comments in the code that suggest batch support might be available, but I am not entirely sure if this is currently possible.
Could you please clarify if batch inference is supported in the current version of the code? If so, could you provide some guidance or examples on how to implement it?
Thank you for your time, Enis