Update README.md

README.md

@@ -33,6 +33,9 @@ from torchaudio.compliance import kaldi
 model = timm.create_model("hf_hub:gaunernst/vit_base_patch16_1024_128.audiomae_as2m_ft_as20k", pretrained=True)
 model = model.eval()
 
+MEAN = -4.2677393
+STD = 4.5689974
+
 audio = torch.randn(1, 10 * 16_000)  # make sure input is 16kHz
 melspec = kaldi.fbank(audio, htk_compat=True, window_type="hanning", num_mel_bins=128)  # shape (n_frames, 128)
 
@@ -41,6 +44,7 @@ if melspec.shape[0] < 1024:
     melspec = F.pad(melspec, (0, 0, 0, 1024 - melspec.shape[0]))
 else:
     melspec = melspec[:1024]
+melspec = (melspec - MEAN) / (STD * 2)
 
 melspec = melspec.view(1, 1, 1024, 128)  # add batch dim and channel dim
 output = model(melspec)