adding long-form audio speaker diarization

nemo_msdd_configs/diar_infer_general.yaml

@@ -52,6 +52,9 @@ diarizer:
       max_rp_threshold: 0.25 # Determines the range of p-value search: 0 < p <= max_rp_threshold. 
       sparse_search_volume: 10 # 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: null  # .nemo local model path or pretrained model name for multiscale diarization decoder (MSDD)

nemo_msdd_configs/diar_infer_meeting.yaml

@@ -52,6 +52,8 @@ diarizer:
       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: null # .nemo local model path or pretrained model name for multiscale diarization decoder (MSDD)

nemo_msdd_configs/diar_infer_telephonic.yaml

@@ -52,12 +52,14 @@ diarizer:
       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. 
+      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.