search

marianne-m / brouhaha-vad

Predicts the level of noise and reverberation on your audiofiles
MIT License
138 stars 24 forks source link

Wrong model specifications #5

Closed hbredin closed 2 years ago

hbredin commented 2 years ago 
model = Model.from_pretrained("models/best/checkpoints/best.ckpt")
model.specification
# Specifications(problem=<Problem.MULTI_LABEL_CLASSIFICATION: 2>, 
#                resolution=<Resolution.FRAME: 1>, 
#                duration=6, 
#                warm_up=(0.0, 0.0), 
#                classes=['speech'], 
#                permutation_invariant=False)

Would be nice to update classes to ['vad', 'snr', 'c50'].

MarvinLvn commented 2 years ago

I fixed it with commit https://github.com/marianne-m/brouhaha-vad/commit/192c0dd760e8018e611f6b89e70bb1b8fff51098 I changed it in the pretrained model and in the code to avoid mismatch with future trainings.

Thanks for raising this issue!

Closing :)