in whisper/model.py [0:0]
def forward(self, x: Tensor):
"""
x : torch.Tensor, shape = (batch_size, n_mels, n_ctx)
the mel spectrogram of the audio
"""
x = F.gelu(self.conv1(x))
x = F.gelu(self.conv2(x))
x = x.permute(0, 2, 1)
assert x.shape[1:] == self.positional_embedding.shape, "incorrect audio shape"
x = (x + self.positional_embedding).to(x.dtype)
for block in self.blocks:
x = block(x)
x = self.ln_post(x)
return x