Remove the use of pickle throughout codebase

examples/speaker_tasks/diarization/conf/inference/diar_infer_general.yaml

@@ -1,5 +1,5 @@
 # This YAML file is created for all types of offline speaker diarization inference tasks in `<NeMo git root>/example/speaker_tasks/diarization` folder.
-# The inference parameters for VAD, speaker embedding extractor, clustering module, ASR decoder are all included in this YAML file. 
+# The inference parameters for VAD, speaker embedding extractor, clustering module, ASR decoder are all included in this YAML file.
 # All the keys under `diarizer` key (`vad`, `speaker_embeddings`, `clustering`, `asr`) can be selectively used for its own purpose and also can be ignored if the module is not used.
 # The configurations in this YAML file is optimized to show balanced performances on various types of domain. VAD is optimized on multilingual ASR datasets and diarizer is optimized on DIHARD3 development set.
 # An example line in an input manifest file (`.json` format):
@@ -20,37 +20,37 @@ diarizer:
   ignore_overlap: True # Consider or ignore overlap segments while scoring
 
   vad:
-    model_path: vad_multilingual_marblenet # .nemo local model path or pretrained VAD model name 
+    model_path: vad_multilingual_marblenet # .nemo local model path or pretrained VAD model name
     external_vad_manifest: null # This option is provided to use external vad and provide its speech activity labels for speaker embeddings extraction. Only one of model_path or external_vad_manifest should be set
 
     parameters: # Tuned by detection error rate (false alarm + miss) on multilingual ASR evaluation datasets
-      window_length_in_sec: 0.63  # Window length in sec for VAD context input 
+      window_length_in_sec: 0.63  # Window length in sec for VAD context input
       shift_length_in_sec: 0.08 # Shift length in sec for generate frame level VAD prediction
       smoothing: False # False or type of smoothing method (eg: median)
       overlap: 0.5 # Overlap ratio for overlapped mean/median smoothing filter
-      onset: 0.5 # Onset threshold for detecting the beginning and end of a speech 
+      onset: 0.5 # Onset threshold for detecting the beginning and end of a speech
       offset: 0.3 # Offset threshold for detecting the end of a speech
-      pad_onset: 0.2 # Adding durations before each speech segment 
-      pad_offset: 0.2 # Adding durations after each speech segment 
+      pad_onset: 0.2 # Adding durations before each speech segment
+      pad_offset: 0.2 # Adding durations after each speech segment
       min_duration_on: 0.5 # Threshold for short speech segment deletion
       min_duration_off: 0.5 # Threshold for small non_speech deletion
-      filter_speech_first: True 
+      filter_speech_first: True
 
   speaker_embeddings:
     model_path: titanet_large # .nemo local model path or pretrained model name (titanet_large, ecapa_tdnn or speakerverification_speakernet)
     parameters:
       window_length_in_sec: [1.9,1.2,0.5] # Window length(s) in sec (floating-point number). either a number or a list. ex) 1.5 or [1.5,1.0,0.5]
       shift_length_in_sec: [0.95,0.6,0.25] # Shift length(s) in sec (floating-point number). either a number or a list. ex) 0.75 or [0.75,0.5,0.25]
       multiscale_weights: [1,1,1] # Weight for each scale. should be null (for single scale) or a list matched with window/shift scale count. ex) [0.33,0.33,0.33]
-      save_embeddings: True # If True, save speaker embeddings in pickle format.
-  
+      save_embeddings: True # If True, save speaker embedding tensor.
+
   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: 10 # The higher the number, the more values will be examined with more time. 
+      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)
@@ -62,13 +62,13 @@ diarizer:
       asr_based_vad_threshold: 1.0 # Threshold (in sec) that caps the gap between two words when generating VAD timestamps using ASR based VAD.
       asr_batch_size: null # Batch size can be dependent on each ASR model. Default batch sizes are applied if set to null.
       decoder_delay_in_sec: null # Native decoder delay. null is recommended to use the default values for each ASR model.
-      word_ts_anchor_offset: null # Offset to set a reference point from the start of the word. Recommended range of values is [-0.05  0.2]. 
+      word_ts_anchor_offset: null # Offset to set a reference point from the start of the word. Recommended range of values is [-0.05  0.2].
       word_ts_anchor_pos: "start" # Select which part of the word timestamp we want to use. The options are: 'start', 'end', 'mid'.
       fix_word_ts_with_VAD: False # Fix the word timestamp using VAD output. You must provide a VAD model to use this feature.
       colored_text: False # If True, use colored text to distinguish speakers in the output transcript.
       print_time: True # If True, the start and end time of each speaker turn is printed in the output transcript.
       break_lines: False # If True, the output transcript breaks the line to fix the line width (default is 90 chars)
-    
+
     ctc_decoder_parameters: # Optional beam search decoder (pyctcdecode)
       pretrained_language_model: null # KenLM model file: .arpa model file or .bin binary file.
       beam_width: 32

examples/speaker_tasks/diarization/conf/inference/diar_infer_meeting.yaml

@@ -1,5 +1,5 @@
 # This YAML file is created for all types of offline speaker diarization inference tasks in `<NeMo git root>/example/speaker_tasks/diarization` folder.
-# The inference parameters for VAD, speaker embedding extractor, clustering module, ASR decoder are all included in this YAML file. 
+# The inference parameters for VAD, speaker embedding extractor, clustering module, ASR decoder are all included in this YAML file.
 # All the keys under `diarizer` key (`vad`, `speaker_embeddings`, `clustering`, `asr`) can be selectively used for its own purpose and also can be ignored if the module is not used.
 # The configurations in this YAML file is suitable for 3~5 speakers participating in a meeting and may not show the best performance on other types of dialogues.
 # An example line in an input manifest file (`.json` format):
@@ -20,55 +20,55 @@ diarizer:
   ignore_overlap: True # Consider or ignore overlap segments while scoring
 
   vad:
-    model_path:  vad_multilingual_marblenet # .nemo local model path or pretrained VAD model name 
+    model_path:  vad_multilingual_marblenet # .nemo local model path or pretrained VAD model name
     external_vad_manifest: null # This option is provided to use external vad and provide its speech activity labels for speaker embeddings extraction. Only one of model_path or external_vad_manifest should be set
 
-    parameters: # Tuned parameters for CH109 (using the 11 multi-speaker sessions as dev set) 
-      window_length_in_sec: 0.63  # Window length in sec for VAD context input 
+    parameters: # Tuned parameters for CH109 (using the 11 multi-speaker sessions as dev set)
+      window_length_in_sec: 0.63  # Window length in sec for VAD context input
       shift_length_in_sec: 0.01 # Shift length in sec for generate frame level VAD prediction
       smoothing: False # False or type of smoothing method (eg: median)
       overlap: 0.5 # Overlap ratio for overlapped mean/median smoothing filter
-      onset: 0.9 # Onset threshold for detecting the beginning and end of a speech 
+      onset: 0.9 # Onset threshold for detecting the beginning and end of a speech
       offset: 0.5 # Offset threshold for detecting the end of a speech
-      pad_onset: 0 # Adding durations before each speech segment 
-      pad_offset: 0 # Adding durations after each speech segment 
+      pad_onset: 0 # Adding durations before each speech segment
+      pad_offset: 0 # Adding durations after each speech segment
       min_duration_on: 0 # Threshold for short speech segment deletion
       min_duration_off: 0.6 # Threshold for small non_speech deletion
-      filter_speech_first: True 
+      filter_speech_first: True
 
   speaker_embeddings:
     model_path: titanet_large # .nemo local model path or pretrained model name (titanet_large, ecapa_tdnn or speakerverification_speakernet)
     parameters:
       window_length_in_sec: [3.0,2.5,2.0,1.5,1.0,0.5] # Window length(s) in sec (floating-point number). either a number or a list. ex) 1.5 or [1.5,1.0,0.5]
       shift_length_in_sec: [1.5,1.25,1.0,0.75,0.5,0.25] # Shift length(s) in sec (floating-point number). either a number or a list. ex) 0.75 or [0.75,0.5,0.25]
       multiscale_weights: [1,1,1,1,1,1] # Weight for each scale. should be null (for single scale) or a list matched with window/shift scale count. ex) [0.33,0.33,0.33]
-      save_embeddings: True # If True, save speaker embeddings in pickle format.
-  
+      save_embeddings: True # If True, save speaker embedding tensor.
+
   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. 
+      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) 
-  
+      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)
+
   asr:
     model_path: stt_en_conformer_ctc_large # Provide NGC cloud ASR model name. stt_en_conformer_ctc_* models are recommended for diarization purposes.
     parameters:
       asr_based_vad: False # if True, speech segmentation for diarization is based on word-timestamps from ASR inference.
       asr_based_vad_threshold: 1.0 # Threshold (in sec) that caps the gap between two words when generating VAD timestamps using ASR based VAD.
       asr_batch_size: null # Batch size can be dependent on each ASR model. Default batch sizes are applied if set to null.
       decoder_delay_in_sec: null # Native decoder delay. null is recommended to use the default values for each ASR model.
-      word_ts_anchor_offset: null # Offset to set a reference point from the start of the word. Recommended range of values is [-0.05  0.2]. 
+      word_ts_anchor_offset: null # Offset to set a reference point from the start of the word. Recommended range of values is [-0.05  0.2].
       word_ts_anchor_pos: "start" # Select which part of the word timestamp we want to use. The options are: 'start', 'end', 'mid'.
       fix_word_ts_with_VAD: False # Fix the word timestamp using VAD output. You must provide a VAD model to use this feature.
       colored_text: False # If True, use colored text to distinguish speakers in the output transcript.
       print_time: True # If True, the start and end time of each speaker turn is printed in the output transcript.
       break_lines: False # If True, the output transcript breaks the line to fix the line width (default is 90 chars)
-    
+
     ctc_decoder_parameters: # Optional beam search decoder (pyctcdecode)
       pretrained_language_model: null # KenLM model file: .arpa model file or .bin binary file.
       beam_width: 32

examples/speaker_tasks/diarization/conf/inference/diar_infer_telephonic.yaml

@@ -1,5 +1,5 @@
 # This YAML file is created for all types of offline speaker diarization inference tasks in `<NeMo git root>/example/speaker_tasks/diarization` folder.
-# The inference parameters for VAD, speaker embedding extractor, clustering module, ASR decoder are all included in this YAML file. 
+# The inference parameters for VAD, speaker embedding extractor, clustering module, ASR decoder are all included in this YAML file.
 # All the keys under `diarizer` key (`vad`, `speaker_embeddings`, `clustering`, `asr`) can be selectively used for its own purpose and also can be ignored if the module is not used.
 # The configurations in this YAML file is suitable for telephone recordings involving 2~8 speakers in a session and may not show the best performance on the other types of acoustic conditions or dialogues.
 # An example line in an input manifest file (`.json` format):
@@ -20,55 +20,55 @@ diarizer:
   ignore_overlap: True # Consider or ignore overlap segments while scoring
 
   vad:
-    model_path: vad_multilingual_marblenet # .nemo local model path or pretrained VAD model name 
+    model_path: vad_multilingual_marblenet # .nemo local model path or pretrained VAD model name
     external_vad_manifest: null # This option is provided to use external vad and provide its speech activity labels for speaker embeddings extraction. Only one of model_path or external_vad_manifest should be set
 
-    parameters: # Tuned parameters for CH109 (using the 11 multi-speaker sessions as dev set) 
-      window_length_in_sec: 0.15  # Window length in sec for VAD context input 
+    parameters: # Tuned parameters for CH109 (using the 11 multi-speaker sessions as dev set)
+      window_length_in_sec: 0.15  # Window length in sec for VAD context input
       shift_length_in_sec: 0.01 # Shift length in sec for generate frame level VAD prediction
       smoothing: "median" # False or type of smoothing method (eg: median)
       overlap: 0.5 # Overlap ratio for overlapped mean/median smoothing filter
-      onset: 0.1 # Onset threshold for detecting the beginning and end of a speech 
+      onset: 0.1 # Onset threshold for detecting the beginning and end of a speech
       offset: 0.1 # Offset threshold for detecting the end of a speech
-      pad_onset: 0.1 # Adding durations before each speech segment 
-      pad_offset: 0 # Adding durations after each speech segment 
+      pad_onset: 0.1 # Adding durations before each speech segment
+      pad_offset: 0 # Adding durations after each speech segment
       min_duration_on: 0 # Threshold for short speech segment deletion
       min_duration_off: 0.2 # Threshold for small non_speech deletion
-      filter_speech_first: True 
+      filter_speech_first: True
 
   speaker_embeddings:
     model_path: titanet_large # .nemo local model path or pretrained model name (titanet_large, ecapa_tdnn or speakerverification_speakernet)
     parameters:
       window_length_in_sec: [1.5,1.25,1.0,0.75,0.5] # Window length(s) in sec (floating-point number). either a number or a list. ex) 1.5 or [1.5,1.0,0.5]
       shift_length_in_sec: [0.75,0.625,0.5,0.375,0.25] # Shift length(s) in sec (floating-point number). either a number or a list. ex) 0.75 or [0.75,0.5,0.25]
       multiscale_weights: [1,1,1,1,1] # Weight for each scale. should be null (for single scale) or a list matched with window/shift scale count. ex) [0.33,0.33,0.33]
-      save_embeddings: True # If True, save speaker embeddings in pickle format.
-  
-  clustering: 
+      save_embeddings: True # If True, save speaker embedding tensor.
+
+  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. 
+      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) 
-  
+      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)
+
   asr:
     model_path: stt_en_conformer_ctc_large # Provide NGC cloud ASR model name. stt_en_conformer_ctc_* models are recommended for diarization purposes.
     parameters:
       asr_based_vad: False # if True, speech segmentation for diarization is based on word-timestamps from ASR inference.
       asr_based_vad_threshold: 1.0 # Threshold (in sec) that caps the gap between two words when generating VAD timestamps using ASR based VAD.
       asr_batch_size: null # Batch size can be dependent on each ASR model. Default batch sizes are applied if set to null.
       decoder_delay_in_sec: null # Native decoder delay. null is recommended to use the default values for each ASR model.
-      word_ts_anchor_offset: null # Offset to set a reference point from the start of the word. Recommended range of values is [-0.05  0.2]. 
+      word_ts_anchor_offset: null # Offset to set a reference point from the start of the word. Recommended range of values is [-0.05  0.2].
       word_ts_anchor_pos: "start" # Select which part of the word timestamp we want to use. The options are: 'start', 'end', 'mid'.
       fix_word_ts_with_VAD: False # Fix the word timestamp using VAD output. You must provide a VAD model to use this feature.
       colored_text: False # If True, use colored text to distinguish speakers in the output transcript.
       print_time: True # If True, the start and end time of each speaker turn is printed in the output transcript.
       break_lines: False # If True, the output transcript breaks the line to fix the line width (default is 90 chars)
-    
+
     ctc_decoder_parameters: # Optional beam search decoder (pyctcdecode)
       pretrained_language_model: null # KenLM model file: .arpa model file or .bin binary file.
       beam_width: 32