| [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 | |