hezar.data.datasets package

Submodules

• hezar.data.datasets.dataset module
  • Dataset
    • Dataset.required_backends
    • Dataset.config_filename
    • Dataset.cache_dir
    • Dataset.cache_dir
    • Dataset.config_filename
    • Dataset.load()
    • Dataset.required_backends
• hezar.data.datasets.image_captioning_dataset module
  • ImageCaptioningDataset
    • ImageCaptioningDataset.required_backends
  • ImageCaptioningDatasetConfig
    • ImageCaptioningDatasetConfig.image_processor_config
    • ImageCaptioningDatasetConfig.images_paths_column
    • ImageCaptioningDatasetConfig.max_length
    • ImageCaptioningDatasetConfig.name
    • ImageCaptioningDatasetConfig.path
    • ImageCaptioningDatasetConfig.task
    • ImageCaptioningDatasetConfig.test_split_size
    • ImageCaptioningDatasetConfig.text_column
    • ImageCaptioningDatasetConfig.tokenizer_path
• hezar.data.datasets.ocr_dataset module
  • OCRDataset
    • OCRDataset.required_backends
  • OCRDatasetConfig
    • OCRDatasetConfig.id2label
    • OCRDatasetConfig.image_processor_config
    • OCRDatasetConfig.images_paths_column
    • OCRDatasetConfig.invalid_characters
    • OCRDatasetConfig.max_length
    • OCRDatasetConfig.name
    • OCRDatasetConfig.path
    • OCRDatasetConfig.reverse_digits
    • OCRDatasetConfig.reverse_text
    • OCRDatasetConfig.task
    • OCRDatasetConfig.text_column
    • OCRDatasetConfig.text_split_type
    • OCRDatasetConfig.tokenizer_path
  • TextSplitType
    • TextSplitType.CHAR_SPLIT
    • TextSplitType.TOKENIZE
• hezar.data.datasets.sequence_labeling_dataset module
  • SequenceLabelingDataset
  • SequenceLabelingDatasetConfig
    • SequenceLabelingDatasetConfig.ignore_index
    • SequenceLabelingDatasetConfig.is_iob_schema
    • SequenceLabelingDatasetConfig.label_all_tokens
    • SequenceLabelingDatasetConfig.max_length
    • SequenceLabelingDatasetConfig.name
    • SequenceLabelingDatasetConfig.path
    • SequenceLabelingDatasetConfig.tags_field
    • SequenceLabelingDatasetConfig.task
    • SequenceLabelingDatasetConfig.tokenizer_path
    • SequenceLabelingDatasetConfig.tokens_field
• hezar.data.datasets.speech_recognition_dataset module
  • SpeechRecognitionDataset
    • SpeechRecognitionDataset.required_backends
  • SpeechRecognitionDatasetConfig
    • SpeechRecognitionDatasetConfig.audio_array_column
    • SpeechRecognitionDatasetConfig.audio_array_padding_type
    • SpeechRecognitionDatasetConfig.audio_column
    • SpeechRecognitionDatasetConfig.audio_file_path_column
    • SpeechRecognitionDatasetConfig.feature_extractor_path
    • SpeechRecognitionDatasetConfig.labels_max_length
    • SpeechRecognitionDatasetConfig.labels_padding_type
    • SpeechRecognitionDatasetConfig.max_audio_array_length
    • SpeechRecognitionDatasetConfig.name
    • SpeechRecognitionDatasetConfig.path
    • SpeechRecognitionDatasetConfig.sampling_rate
    • SpeechRecognitionDatasetConfig.task
    • SpeechRecognitionDatasetConfig.tokenizer_path
    • SpeechRecognitionDatasetConfig.transcript_column
• hezar.data.datasets.text_classification_dataset module
  • TextClassificationDataset
  • TextClassificationDatasetConfig
    • TextClassificationDatasetConfig.label_field
    • TextClassificationDatasetConfig.max_length
    • TextClassificationDatasetConfig.name
    • TextClassificationDatasetConfig.path
    • TextClassificationDatasetConfig.task
    • TextClassificationDatasetConfig.text_field
    • TextClassificationDatasetConfig.tokenizer_path
• hezar.data.datasets.text_summarization_dataset module
  • TextSummarizationDataset
  • TextSummarizationDatasetConfig
    • TextSummarizationDatasetConfig.max_length
    • TextSummarizationDatasetConfig.max_target_length
    • TextSummarizationDatasetConfig.name
    • TextSummarizationDatasetConfig.path
    • TextSummarizationDatasetConfig.prefix
    • TextSummarizationDatasetConfig.summary_field
    • TextSummarizationDatasetConfig.task
    • TextSummarizationDatasetConfig.text_field
    • TextSummarizationDatasetConfig.title_field
    • TextSummarizationDatasetConfig.tokenizer_path

Module contents