src/speech_decoding/models/v14_converged_v3/towers.py

Selected training excerpt · lines 302–304 · source SHA-256 5610fc7e8fc4

302        B, M, d = x_flat.shape303        device = x_flat.device304        x_flat = x_flat + self.parcel_embed(parcel_bm).to(x_flat.dtype)  # (B, M, d)