kkoutini / passt_hear21

Inference code for PaSST, using the HEAR API.

kkoutini/passt_hear21 Issues

Missing normalization in audio preprocessing
Closed 9 months ago2
Torch size 3 vs 64
Closed a year ago3
Errors with some of the models defined
Closed 2 years ago5
Load model
Closed 2 years ago5
Does the model support the variable audio length?
Updated 2 years ago8
Inference
Updated 2 years ago5
UserWarning: Input image size (128*1000) doesn't match model (128*998)
Closed 3 years ago2