speakerbox

• speakerbox package
  • Submodules
  • speakerbox.examples module
    • IteratedModelEvalScores
      • IteratedModelEvalScores.dataset_size
      • IteratedModelEvalScores.equalized_data
      • IteratedModelEvalScores.mean_accuracy
      • IteratedModelEvalScores.mean_audio_per_person_test
      • IteratedModelEvalScores.mean_audio_per_person_train
      • IteratedModelEvalScores.mean_audio_per_person_valid
      • IteratedModelEvalScores.mean_duration
      • IteratedModelEvalScores.mean_precision
      • IteratedModelEvalScores.mean_recall
      • IteratedModelEvalScores.std_accuracy
      • IteratedModelEvalScores.std_audio_per_person_test
      • IteratedModelEvalScores.std_audio_per_person_train
      • IteratedModelEvalScores.std_audio_per_person_valid
      • IteratedModelEvalScores.std_duration
      • IteratedModelEvalScores.std_precision
      • IteratedModelEvalScores.std_recall
    • ModelEvalScores
      • ModelEvalScores.accuracy
      • ModelEvalScores.duration
      • ModelEvalScores.precision
      • ModelEvalScores.recall
    • download_preprocessed_example_data()
    • train_and_eval_all_example_models()
    • train_and_eval_example_model()
  • speakerbox.main module
    • apply()
    • eval_model()
    • train()
  • speakerbox.preprocess module
    • diarize_and_split_audio()
    • expand_gecko_annotations_to_dataset()
    • expand_labeled_diarized_audio_dir_to_dataset()
    • prepare_dataset()
  • speakerbox.types module
    • AnnotatedAudio
      • AnnotatedAudio.audio
      • AnnotatedAudio.conversation_id
      • AnnotatedAudio.duration
      • AnnotatedAudio.from_dict()
      • AnnotatedAudio.from_json()
      • AnnotatedAudio.label
      • AnnotatedAudio.schema()
      • AnnotatedAudio.to_dict()
      • AnnotatedAudio.to_json()
    • GeckoAnnotationAndAudio
      • GeckoAnnotationAndAudio.annotation_file
      • GeckoAnnotationAndAudio.audio_file
  • speakerbox.utils module
    • set_global_seed()
  • Module contents
    • apply()
    • eval_model()
    • train()