src/speech_decoding/models/v14_converged_v3/objective.py

Selected training excerpt · lines 338–342 · source SHA-256 5718458b537d

338            self.enc_to_pred = nn.Sequential(339                nn.Linear(N_LEVELS * self.d_model, self.d_model),340                nn.GELU(),341                nn.Linear(self.d_model, self.d_pred),342            )