[model]
path = "diarizen.models.eend.model_wavlm_conformer.Model"

[model.args]
wavlm_src = "wavlm_large_s80_md"
wavlm_layer_num = 25
wavlm_feat_dim = 1024
attention_in = 256
ffn_hidden = 1024
num_head = 4
num_layer = 4
dropout = 0.1
max_speakers_per_chunk = 4
max_speakers_per_frame = 4
chunk_size = 16
use_posi = false
output_activate_function = false
selected_channel = 0

[inference.args]
seg_duration = 16
segmentation_step = 0.1
batch_size = 32
apply_median_filtering = true

[clustering.args]
method = "VBxClustering"
min_speakers = 1
max_speakers = 20
ahc_criterion = "distance"
ahc_threshold = 0.6
Fa = 0.07
Fb = 0.8
lda_dim = 128
max_iters = 20