How to use dangkhoadl/AudioResNet with Transformers:
# Load model directly from transformers import AutoImageProcessor, ResNetForAudioClassification processor = AutoImageProcessor.from_pretrained("dangkhoadl/AudioResNet") model = ResNetForAudioClassification.from_pretrained("dangkhoadl/AudioResNet")
12ebfc9
1
2
# Input tensor shape [batch_size, Cin, num_feats, num_frames]
