Workflows

• Alignment
  • Alignment classes
    • CorpusAligner
      • CorpusAligner
        • CorpusAligner.align
        • CorpusAligner.alignment_extraction_arguments
        • CorpusAligner.collect_alignments
        • CorpusAligner.compute_pronunciation_probabilities
        • CorpusAligner.decode_options
        • CorpusAligner.evaluate_alignments
        • CorpusAligner.export_files
        • CorpusAligner.export_textgrid_arguments
        • CorpusAligner.export_textgrids
        • CorpusAligner.fine_tune_alignments
        • CorpusAligner.fine_tune_arguments
        • CorpusAligner.generate_pronunciations_arguments
        • CorpusAligner.hclg_options
        • CorpusAligner.score_options
    • AdaptingAligner
      • AdaptingAligner
        • AdaptingAligner.acc_stats
        • AdaptingAligner.adapt
        • AdaptingAligner.align_directory
        • AdaptingAligner.alignment_model_path
        • AdaptingAligner.export_model
        • AdaptingAligner.map_acc_stats_arguments
        • AdaptingAligner.meta
        • AdaptingAligner.model_path
        • AdaptingAligner.next_model_path
        • AdaptingAligner.train_map
        • AdaptingAligner.working_log_directory
    • PretrainedAligner
      • PretrainedAligner
        • PretrainedAligner.align
        • PretrainedAligner.align_one_utterance
        • PretrainedAligner.configuration
        • PretrainedAligner.parse_parameters
        • PretrainedAligner.setup
        • PretrainedAligner.setup_acoustic_model
  • Helper functionality
    • Mixins
      • AlignMixin
        • AlignMixin
          • AlignMixin.align_arguments
          • AlignMixin.align_options
          • AlignMixin.align_utterances
          • AlignMixin.alignment_configuration
          • AlignMixin.alignment_model_path
          • AlignMixin.compile_train_graphs
          • AlignMixin.compile_train_graphs_arguments
          • AlignMixin.data_directory
          • AlignMixin.model_path
          • AlignMixin.num_current_utterances
          • AlignMixin.phone_confidence_arguments
          • AlignMixin.phone_pdf_counts_path
          • AlignMixin.tree_path
          • AlignMixin.working_directory
          • AlignMixin.working_log_directory
    • Multiprocessing workers and functions
      • AlignFunction
        • AlignFunction
      • FineTuneFunction
        • FineTuneFunction
      • CompileTrainGraphsFunction
        • CompileTrainGraphsFunction
      • AccStatsFunction
        • AccStatsFunction
      • AlignmentExtractionFunction
        • AlignmentExtractionFunction
      • ExportTextGridProcessWorker
        • ExportTextGridProcessWorker
          • ExportTextGridProcessWorker.run
      • PhoneConfidenceFunction
        • PhoneConfidenceFunction
    • Multiprocessing argument classes
      • AlignArguments
        • AlignArguments
      • AccStatsArguments
        • AccStatsArguments
      • CompileTrainGraphsArguments
        • CompileTrainGraphsArguments
      • AlignmentExtractionArguments
        • AlignmentExtractionArguments
      • ExportTextGridArguments
        • ExportTextGridArguments
      • FineTuneArguments
        • FineTuneArguments
      • PhoneConfidenceArguments
        • PhoneConfidenceArguments
• Validation
  • Validators
    • TrainingValidator
      • TrainingValidator
        • TrainingValidator.parse_parameters
        • TrainingValidator.setup
        • TrainingValidator.validate
        • TrainingValidator.working_directory
    • PretrainedValidator
      • PretrainedValidator
        • PretrainedValidator.analyze_missing_phones
        • PretrainedValidator.setup
        • PretrainedValidator.validate
    • DictionaryValidator
      • DictionaryValidator
        • DictionaryValidator.setup
        • DictionaryValidator.validate
  • Helper functions
    • Mixins
      • ValidationMixin
        • ValidationMixin
          • ValidationMixin.analyze_files_with_no_transcription
          • ValidationMixin.analyze_missing_features
          • ValidationMixin.analyze_oovs
          • ValidationMixin.analyze_setup
          • ValidationMixin.analyze_textgrid_read_errors
          • ValidationMixin.analyze_transcriptions_with_no_wavs
          • ValidationMixin.analyze_unreadable_text_files
          • ValidationMixin.analyze_wav_errors
          • ValidationMixin.test_utterance_transcriptions
          • ValidationMixin.working_log_directory
• Generating dictionaries
  • Dictionary generation
    • PyniniCorpusGenerator
      • PyniniCorpusGenerator
        • PyniniCorpusGenerator.export_file_pronunciations
        • PyniniCorpusGenerator.export_pronunciations
        • PyniniCorpusGenerator.setup
        • PyniniCorpusGenerator.words_to_g2p
        • PyniniCorpusGenerator.working_directory
    • PyniniWordListGenerator
      • PyniniWordListGenerator
        • PyniniWordListGenerator.data_directory
        • PyniniWordListGenerator.data_source_identifier
        • PyniniWordListGenerator.setup
  • Helper functionality
    • Mixins
      • PyniniGenerator
        • PyniniGenerator
          • PyniniGenerator.data_directory
          • PyniniGenerator.data_source_identifier
          • PyniniGenerator.generate_pronunciations
          • PyniniGenerator.words_to_g2p
          • PyniniGenerator.working_directory
    • Helper
      • Rewriter
        • Rewriter
      • RewriterWorker
        • RewriterWorker
          • RewriterWorker.run
• Transcription
  • Transcriber
    • Transcriber
      • Transcriber
        • Transcriber.create_decoding_graph
        • Transcriber.create_hclgs
        • Transcriber.create_hclgs_arguments
        • Transcriber.export_files
        • Transcriber.export_transcriptions
        • Transcriber.parse_parameters
        • Transcriber.setup
  • Helper functions
    • Mixins
      • TranscriberMixin
        • TranscriberMixin
          • TranscriberMixin.calc_final_fmllr
          • TranscriberMixin.calc_initial_fmllr
          • TranscriberMixin.carpa_lm_rescore
          • TranscriberMixin.carpa_lm_rescore_arguments
          • TranscriberMixin.compute_wer
          • TranscriberMixin.decode
          • TranscriberMixin.decode_arguments
          • TranscriberMixin.evaluate_transcriptions
          • TranscriberMixin.final_fmllr_arguments
          • TranscriberMixin.fmllr_rescore
          • TranscriberMixin.fmllr_rescore_arguments
          • TranscriberMixin.initial_fmllr_arguments
          • TranscriberMixin.lm_rescore
          • TranscriberMixin.lm_rescore_arguments
          • TranscriberMixin.lm_rescore_options
          • TranscriberMixin.model_directory
          • TranscriberMixin.model_log_directory
          • TranscriberMixin.save_transcription_evaluation
          • TranscriberMixin.setup_phone_lm
          • TranscriberMixin.train_phone_lm
          • TranscriberMixin.train_speaker_lm_arguments
          • TranscriberMixin.train_speaker_lms
          • TranscriberMixin.transcribe_fmllr
          • TranscriberMixin.transcribe_fmllr_options
          • TranscriberMixin.transcribe_utterances
    • Decoding graph
      • CreateHclgFunction
        • CreateHclgFunction
      • CreateHclgArguments
        • CreateHclgArguments
    • Speaker-independent transcription
      • DecodeFunction
        • DecodeFunction
      • DecodeArguments
        • DecodeArguments
      • LmRescoreFunction
        • LmRescoreFunction
      • LmRescoreArguments
        • LmRescoreArguments
      • CarpaLmRescoreFunction
        • CarpaLmRescoreFunction
      • CarpaLmRescoreArguments
        • CarpaLmRescoreArguments
    • Speaker-adapted transcription
      • InitialFmllrFunction
        • InitialFmllrFunction
      • InitialFmllrArguments
        • InitialFmllrArguments
      • FmllrRescoreFunction
        • FmllrRescoreFunction
      • FmllrRescoreArguments
        • FmllrRescoreArguments
      • FinalFmllrFunction
        • FinalFmllrFunction
      • FinalFmllrArguments
        • FinalFmllrArguments
• Segmentation
  • Segmenter
    • VadSegmenter
      • VadSegmenter
        • VadSegmenter.export_files
        • VadSegmenter.parse_parameters
        • VadSegmenter.segment
        • VadSegmenter.segment_vad_arguments
        • VadSegmenter.segment_vad_mfa
        • VadSegmenter.segment_vad_speechbrain
        • VadSegmenter.setup
    • TranscriptionSegmenter
      • TranscriptionSegmenter
        • TranscriptionSegmenter.export_files
        • TranscriptionSegmenter.segment
        • TranscriptionSegmenter.segment_transcript_arguments
        • TranscriptionSegmenter.setup
  • Helper functions
    • SegmentVadFunction
      • SegmentVadFunction
    • SegmentVadArguments
      • SegmentVadArguments
    • SegmentVadFunction
      • SegmentVadFunction
    • SegmentVadArguments
      • SegmentVadArguments
    • get_initial_segmentation
      • get_initial_segmentation
    • merge_segments
      • merge_segments
    • segment_utterance_transcript
      • segment_utterance_transcript
    • segment_utterance_vad
      • segment_utterance_vad
    • segment_utterance_vad_speech_brain
      • segment_utterance_vad_speech_brain
• Speaker diarization
  • Speaker Diarization
    • SpeakerDiarizer
      • SpeakerDiarizer
        • SpeakerDiarizer.calculate_eer
        • SpeakerDiarizer.classify_speakers
        • SpeakerDiarizer.cluster_utterances
        • SpeakerDiarizer.cluster_utterances_mfa
        • SpeakerDiarizer.compute_speaker_embeddings
        • SpeakerDiarizer.evaluate_classification
        • SpeakerDiarizer.evaluate_clustering
        • SpeakerDiarizer.export_files
        • SpeakerDiarizer.load_embeddings
        • SpeakerDiarizer.num_utts_path
        • SpeakerDiarizer.parse_parameters
        • SpeakerDiarizer.plda_classification_arguments
        • SpeakerDiarizer.refresh_speaker_vectors
        • SpeakerDiarizer.setup
        • SpeakerDiarizer.speaker_ivector_path
  • Helper functions
    • PldaClassificationFunction
      • PldaClassificationFunction
    • PldaClassificationArguments
      • PldaClassificationArguments
    • ComputeEerFunction
      • ComputeEerFunction
    • ComputeEerArguments
      • ComputeEerArguments
    • SpeechbrainEmbeddingFunction
      • SpeechbrainEmbeddingFunction
    • SpeechbrainClassificationFunction
      • SpeechbrainClassificationFunction
    • SpeechbrainArguments
      • SpeechbrainArguments
    • cluster_matrix
      • cluster_matrix
• Tokenizers
  • TokenizerModel
    • TokenizerModel
      • TokenizerModel.add_graphemes_path
      • TokenizerModel.add_meta_file
      • TokenizerModel.add_tokenizer_model
      • TokenizerModel.export_fst_model
      • TokenizerModel.fst_path
      • TokenizerModel.input_sym_path
      • TokenizerModel.meta
      • TokenizerModel.output_sym_path
      • TokenizerModel.sym_path
      • TokenizerModel.validate
  • Training tokenizer models
    • TokenizerTrainer
      • TokenizerTrainer
        • TokenizerTrainer.data_source_identifier
        • TokenizerTrainer.export_model
        • TokenizerTrainer.finalize_training
        • TokenizerTrainer.initialize_training
        • TokenizerTrainer.meta
        • TokenizerTrainer.sym_path
        • TokenizerTrainer.train
  • Corpus tokenizer
    • CorpusTokenizer
      • CorpusTokenizer
        • CorpusTokenizer.export_files
        • CorpusTokenizer.model_class
        • CorpusTokenizer.setup
        • CorpusTokenizer.tokenize_utterances
    • TokenizerValidator
      • TokenizerValidator
        • TokenizerValidator.compute_validation_errors
        • TokenizerValidator.data_directory
        • TokenizerValidator.data_source_identifier
        • TokenizerValidator.evaluation_csv_path
        • TokenizerValidator.setup
        • TokenizerValidator.tokenize_utterances
  • Simple tokenizer
    • SimpleTokenizer
      • SimpleTokenizer
  • Helper functionality
    • Helper
      • TokenizerRewriter
        • TokenizerRewriter
      • TokenizerArguments
        • TokenizerArguments
      • TokenizerFunction
        • TokenizerFunction
    • Helper
      • SanitizeFunction
        • SanitizeFunction
      • SplitWordsFunction
        • SplitWordsFunction
          • SplitWordsFunction.split_clitics
          • SplitWordsFunction.to_str