Audio-Text-to-Text
PEFT
Safetensors
English
mistral-lmm

Information about the model

#1
by roskoN - opened

Hi,

Thank you for sharing this work with the community.

Currently, the link to Github does not seem to work. Do you plan to share more details (e.g., technical report or paper) about your approach?

Thank you,
Rosko

AMAAI Lab org

Hi, absolutely. In about 2 days we should have a report come out as out paper was accepted. I will let you know.

AMAAI Lab org

Hello! Sorry for the trouble, the github as well as demo link is updated and should be working now!

AMAAI Lab org

You can find the paper here: https://arxiv.org/abs/2506.15154
As well as dedicated instructions in the GitHub: https://github.com/AMAAI-Lab/sonicverse

dorienh changed discussion status to closed

Sign up or log in to comment