# Speaker-based VAP from ONE channel, anchored by voice activity.
#
# The 256-class codebook names channels, which mono audio cannot identify. Here
# the identity comes from the VAD instead: the model hears the mixture and is
# told who held the floor strictly before the frame it is labelling, so the two
# rows stay attached to real speakers without a second channel. The anchor is
# delayed by one frame because speaker_based bins the future from `t` inclusive.
#
# Frozen Mimi frontend, so this is comparable to vap-speaker-mimi on everything
# but the number of channels.
fisher_path: data/fisher
checkpoint_dir: runs/vap_speaker_mono_mimi

vap:
  # Frozen 37.8M Mimi encoder. Its 512-dim features are bridged onto d_model by
  # the model's encoder projection.
  audio_encoder:
    name: mimi
    tap: encoder            # 25 Hz, matching the label grid

  arch: anchored             # one mixed channel, anchored by past VAD
  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