File size: 438 Bytes
a1e619e
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
{
  "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": 3.40789476744061,
  "median_chars_per_token": 3.2962445087324546,
  "min_chars_per_token": 2.350467289719626,
  "max_chars_per_token": 5.3
}