Evonne Ng

Thank you all for such active help on these issues! Hi @MustaphaU , it seems that results from the auto-generated mask size not matching that of the audio conditioning tensor....

Closing this for now due to inactivity. But please feel to reopen if there's more issues related. Thanks!

Hmm it seems that you are attempting to load the model onto a non-gpu supported device (just the cpu). And i see that when loading the model, the map_location is...

Closing for now due to inactivity, but please feel free to reopen as needed!

Hi! The diffusion package here shouldn't be a pip package. Instead, it is a module that is included in the repo (https://github.com/facebookresearch/audio2photoreal/blob/main/diffusion/respace.py) Could you please try pip uninstalling your diffusion...

Going to close this for now due to inactivity, but please feel free to reopen if the problem persists!

Hi! An easy way to do it is use pytorch3d to plot the mesh of the geometry that is outputted by the renderer https://github.com/facebookresearch/audio2photoreal/blob/548aeeb2057465045ca1568d65ea059cea633d80/visualize/render_codes.py#L107 I haven't gotten around to writing...

Ah i see, here I think you only saved the 3d vertices from the output geom. But in order to plot the mesh, you will also need to save the...

Closing this for now due to inactivity. But please feel to reopen accordingly.

Hi! hmm it's likely the audio file is corrupted in some way. Could you check to see if you can open and play the audio saved at that location please?...