src/speech_decoding/models/v14_converged_v3/objective.py

Selected training excerpt · lines 384–387 · source SHA-256 5718458b537d

384                self.mae_heads = nn.ModuleList(385                    nn.Linear(self.d_pred, nb) for nb, _ in PER_BAND_SPECS386                )387                self.mae_heads.apply(init_transformer_weights)