kkoutini / PaSST

Efficient Training of Audio Transformers with Patchout
Apache License 2.0
305 stars 50 forks source link

kaggle #13

Open woozi1122 opened 2 years ago

woozi1122 commented 2 years ago

excuse me,I wonder to know how should I setup PaSST on kaggle?I have tried some times,but I failed

kkoutini commented 2 years ago

Hi, you can use the inference repo to get the models without the training framework dependencies:

from hear21passt.base import load_model model = load_model(mode="logits").cuda() logits = model(wave_signal)

woozi1122 commented 2 years ago

Hi, you can use the inference repo to get the models without the training framework dependencies:

  • install the package:
!pip install git+https://github.com/kkoutini/passt_hear21.git
import torch

from hear21passt.base import load_model
model = load_model(mode="logits").cuda()
logits = model(wave_signal)

thank you very much,I will have a try