Files
icassp2027-experiment/third_party/MuVAP/config/yaml/vap_role_mimi_12hz.yaml
T

64 lines
2.1 KiB
YAML

# Role-based VAP at 12.5 Hz, the rate Mimi natively codes at.
#
# `tap: latent` is Mimi's own frame rate, so this matches a full-duplex system
# built on Mimi codes frame for frame: same frontend, same 80 ms decision grid.
# Labels come from seg/vad12_5, written by 03_prep_vad_rate.py; the 25 Hz tree
# is untouched. bin_sec stays at the paper's times, so the rate is the only
# thing that changes against the 25 Hz runs - at 12.5 Hz they round to
# 0.16 / 0.4 / 0.64 / 0.8, still a 2.0 s horizon.
fisher_path: data/fisher
checkpoint_dir: runs/role_mimi_12hz
vap:
audio_encoder:
name: mimi
tap: latent # 12.5 Hz, Mimi's own frame rate
arch: mono # mono | stereo
batch_size: 64
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: 1
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: npy
swap_channels: false # stereo-only augmentation
projection_window:
# 1.4 s is 17.5 frames at 12.5 Hz, so the paper's times cannot be
# represented here. These keep the 4.0 s window exact - [18, 7, 7, 18] -
# where rounding [1.4, 0.6] gives 26 frames of history for a 25-frame window.
bin_sec: [1.44, 0.56, 0.56, 1.44]
num_hist_bins: 2
frame_hz: 12.5
threshold: 0.5
mode: role_relative
cut_center_frame: false
temporal:
d_model: 256
m_ff: 3
n_heads: 4
n_layers: 4
dropout: 0.1
activation: GELU
causal: true
pos_encoding: alibi # alibi | rope | sinusoidal | none
ffn: mlp # mlp | swiglu
norm: layer # layer | rms
# Size of the sinusoidal position table. Rotary and ALiBi extend to any
# length, so this bounds the sinusoidal encoding only.
max_frames: 4096