{ "catalogue_url": "https://huggingface.co/datasets/tachiwin/language_utils/resolve/main/catalogue.json", "languages_in_catalogue": 363, "languages_with_samples": 106, "samples_evaluated": 327, "failed_sample_round_trips": 0, "failed_language_round_trips": 0, "mean_chars_per_token": 2.8783262361616155, "median_chars_per_token": 2.8708188627252476, "min_chars_per_token": 2.0762886597938146, "max_chars_per_token": 4.01195219123506 }