What to do about misattribution?

[ErfolgreichCharismatisch]

Is there a threshold that can be set to improve correct attribution?

[MahmoudAshraf97]

These are the settings you can play with to change the diarization output:

whisper-diarization/nemo_msdd_configs/diar_infer_telephonic.yaml

Lines 47 to 67 in 6c9047d

	clustering:
	parameters:
	oracle_num_speakers: False # If True, use num of speakers value provided in manifest file.
	max_num_speakers: 8 # Max number of speakers for each recording. If an oracle number of speakers is passed, this value is ignored.
	enhanced_count_thres: 80 # If the number of segments is lower than this number, enhanced speaker counting is activated.
	max_rp_threshold: 0.25 # Determines the range of p-value search: 0 < p <= max_rp_threshold.
	sparse_search_volume: 30 # The higher the number, the more values will be examined with more time.
	maj_vote_spk_count: False # If True, take a majority vote on multiple p-values to estimate the number of speakers.
	chunk_cluster_count: 50 # Number of forced clusters (overclustering) per unit chunk in long-form audio clustering.
	embeddings_per_chunk: 10000 # Number of embeddings in each chunk for long-form audio clustering. Adjust based on GPU memory capacity. (default: 10000, approximately 40 mins of audio)
	msdd_model:
	model_path: diar_msdd_telephonic # .nemo local model path or pretrained model name for multiscale diarization decoder (MSDD)
	parameters:
	use_speaker_model_from_ckpt: True # If True, use speaker embedding model in checkpoint. If False, the provided speaker embedding model in config will be used.
	infer_batch_size: 25 # Batch size for MSDD inference.
	sigmoid_threshold: [0.7] # Sigmoid threshold for generating binarized speaker labels. The smaller the more generous on detecting overlaps.
	seq_eval_mode: False # If True, use oracle number of speaker and evaluate F1 score for the given speaker sequences. Default is False.
	split_infer: True # If True, break the input audio clip to short sequences and calculate cluster average embeddings for inference.
	diar_window_length: 50 # The length of split short sequence when split_infer is True.
	overlap_infer_spk_limit: 5 # If the estimated number of speakers are larger than this number, overlap speech is not estimated.