Hi,
How to use your CNN14 network with batches of input audio sequences of variable lengths? Also, is there a recommended length for audio input to the pretrained Cnn14_16k_mAP=0.438.pth?
Hi, during the training of PANNs ,all audio recordings are truncated or padded to 10 seconds with zero. In inference, the audio can be variable length.
Hi, How to use your CNN14 network with batches of input audio sequences of variable lengths? Also, is there a recommended length for audio input to the pretrained Cnn14_16k_mAP=0.438.pth?