thao-uyen1508/vietnamese-ocr-dataset

--- dataset_info: features: - name: image_path dtype: image - name: text dtype: string splits: - name: train num_bytes: 652954174.41 num_examples: 5621 - name: validation num_bytes: 161893912.268 num_examples: 1406 - name: test num_bytes: 35095791.0 num_examples: 201 download_size: 870457152 dataset_size: 849943877.678 configs: - config_name: default data_files: - split: train path: data/train-* - split: validation path: data/validation-* - split: test path: data/test-* ---