label_evaluation.evaluate_text

Functions

calculate_cer(reference, hypothesis)	Calculate the Character Error Rate (CER) between reference and hypothesis.
calculate_scores(gold_text, predicted_text)	Calculate Word Error Rate (WER) and Character Error Rate (CER) between ground truth and prediction.
create_plot(data, score_name, file_name)	Create and save a violin plot for the given error scores.
evaluate_text_predictions(ground_truth_file, ...)	Evaluate OCR predictions against a ground truth dataset.
get_gold_transcriptions(filename[, sep])	Load ground truth transcriptions from a CSV file into a dictionary.
load_json_predictions(filename)	Load predictions from a JSON file.

Exceptions

EmptyReferenceError([message])

Custom exception for handling cases where the reference string is empty.