tests.py

test_cases = [
    {
        "predictions": ["w ɛ ɹ ;eword ɪ z ;eword ð ɪ s ;eword", "l ɪ ɾ əl ;eword aɪ z ;eword"],
        "references": ["w ɛ ɹ ;eword ɪ z ;eword ð ɪ s ;eword", "l ɪ ɾ əl ;eword aɪ z ;eword"],
        "result": {'type_fscore': 1.0, 'type_precision': 1.0, 'type_recall': 1.0, 'token_fscore': 1.0, 'token_precision': 1.0, 'token_recall': 1.0, 'boundary_all_fscore': 1.0, 'boundary_all_precision': 1.0, 'boundary_all_recall': 1.0, 'boundary_noedge_fscore': 1.0, 'boundary_noedge_precision': 1.0, 'boundary_noedge_recall': 1.0}
    },
    {
        "predictions": ["thedog is in the boat"],
        "references": ["the dog is in the boat"],
        "result": {'type_fscore': 0.8, 'type_precision': 0.8, 'type_recall': 0.8, 'token_fscore': 0.73, 'token_precision': 0.8, 'token_recall': 0.67, 'boundary_all_fscore': 1.0, 'boundary_all_precision': 1.0, 'boundary_all_recall': 0.94, 'boundary_noedge_fscore': 0.89, 'boundary_noedge_precision': 1.0, 'boundary_noedge_recall': 0.8}
    }
]