# Speaker-based VAP (Ekstedt & Skantze, 2022): two audio channels, one speaker per
# channel, and a 256-class codebook that projects one channel per row.
fisher_path: data/fisher
checkpoint_dir: runs/vap_speaker

vap:
  arch: stereo
  batch_size: 32
  num_workers: 16
  max_epochs: 5
  lr: 0.001
  weight_decay: 0.01
  warmup_ratio: 0.1
  min_lr: 0.0001

  precision: bf16-mixed
  gradient_clip_val: 1.0
  accumulate_grad_batches: 2
  matmul_precision: high
  # Metric that selects best.ckpt. Leave empty when there is no held-out
  # split to select on: last.ckpt is written either way.
  checkpoint_monitor: val/loss
  checkpoint_mode: min
  # npy reads the segments written by preprocessing; raw seeks the same window
  # in the source recording and resamples it.
  source: raw
  swap_channels: true          # channel order is arbitrary; swap both audio and VAD

  projection_window:
    bin_sec: [0.2, 0.4, 0.6, 0.8]
    num_hist_bins: 0           # every bin is a future bin, as in the original repo
    frame_hz: 25
    threshold: 0.5
    mode: speaker_based
    cut_center_frame: false

  temporal:
    d_model: 256
    m_ff: 3
    n_heads: 4
    n_layers: 1
    dropout: 0.1
    activation: GELU
    causal: true
    pos_encoding: alibi        # alibi | rope | sinusoidal | none
    ffn: mlp
    norm: layer
    # Size of the sinusoidal position table. Rotary and ALiBi extend to any
    # length, so this bounds the sinusoidal encoding only.
    max_frames: 4096

  cross:
    d_model: 256
    m_ff: 3
    n_heads: 4
    n_layers: 3
    dropout: 0.1
    activation: GELU
    causal: true
    pos_encoding: alibi        # alibi | rope | sinusoidal | none
    ffn: mlp
    norm: layer
    # Size of the sinusoidal position table. Rotary and ALiBi extend to any
    # length, so this bounds the sinusoidal encoding only.
    max_frames: 4096