File size: 453 Bytes
d1417c8
 
 
 
 
 
 
 
 
 
 
 
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": 3.414915883033258,
  "median_chars_per_token": 3.3048122107830826,
  "min_chars_per_token": 2.289772727272727,
  "max_chars_per_token": 5.385026737967914
}