Upload evaluation/language_fertility.json with huggingface_hub
Browse files- evaluation/language_fertility.json +1698 -0
evaluation/language_fertility.json
ADDED
|
@@ -0,0 +1,1698 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[
|
| 2 |
+
{
|
| 3 |
+
"code": "amu",
|
| 4 |
+
"autonym": "Ñomndaa, Ñomndaa Suljaaꞌ",
|
| 5 |
+
"spanish_name": "Amuzgo de Guerrero",
|
| 6 |
+
"inali_name": "amuzgo del norte",
|
| 7 |
+
"english_name": "Guerrero Amuzgo",
|
| 8 |
+
"samples": 4,
|
| 9 |
+
"chars": 2015,
|
| 10 |
+
"utf8_bytes": 2521,
|
| 11 |
+
"tokens": 468,
|
| 12 |
+
"chars_per_token": 4.305555555555555,
|
| 13 |
+
"tokens_per_char": 0.23225806451612904,
|
| 14 |
+
"bytes_per_token": 5.386752136752137,
|
| 15 |
+
"tokens_per_byte": 0.18564061880206267,
|
| 16 |
+
"round_trip": true
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"code": "azg",
|
| 20 |
+
"autonym": "Jnꞌoon",
|
| 21 |
+
"spanish_name": "Amuzgo de San Pedro Amuzgos",
|
| 22 |
+
"inali_name": "amuzgo alto del este",
|
| 23 |
+
"english_name": "San Pedro Amuzgos Amuzgo",
|
| 24 |
+
"samples": 1,
|
| 25 |
+
"chars": 503,
|
| 26 |
+
"utf8_bytes": 608,
|
| 27 |
+
"tokens": 190,
|
| 28 |
+
"chars_per_token": 2.6473684210526316,
|
| 29 |
+
"tokens_per_char": 0.37773359840954274,
|
| 30 |
+
"bytes_per_token": 3.2,
|
| 31 |
+
"tokens_per_byte": 0.3125,
|
| 32 |
+
"round_trip": true
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"code": "ctp",
|
| 36 |
+
"autonym": "Chaꞌtñan",
|
| 37 |
+
"spanish_name": "Chatino de la Zona Alta Occidental",
|
| 38 |
+
"inali_name": "chatino occidental alto",
|
| 39 |
+
"english_name": "Western Highland Chatino",
|
| 40 |
+
"samples": 2,
|
| 41 |
+
"chars": 1007,
|
| 42 |
+
"utf8_bytes": 1167,
|
| 43 |
+
"tokens": 332,
|
| 44 |
+
"chars_per_token": 3.033132530120482,
|
| 45 |
+
"tokens_per_char": 0.32969215491559084,
|
| 46 |
+
"bytes_per_token": 3.5150602409638556,
|
| 47 |
+
"tokens_per_byte": 0.28449014567266495,
|
| 48 |
+
"round_trip": true
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"code": "cya",
|
| 52 |
+
"autonym": "Chaꞌtñan",
|
| 53 |
+
"spanish_name": "Chatino de Nopala",
|
| 54 |
+
"inali_name": "chatino oriental bajo",
|
| 55 |
+
"english_name": "Nopala Chatino",
|
| 56 |
+
"samples": 2,
|
| 57 |
+
"chars": 1007,
|
| 58 |
+
"utf8_bytes": 1019,
|
| 59 |
+
"tokens": 190,
|
| 60 |
+
"chars_per_token": 5.3,
|
| 61 |
+
"tokens_per_char": 0.18867924528301888,
|
| 62 |
+
"bytes_per_token": 5.363157894736842,
|
| 63 |
+
"tokens_per_byte": 0.18645731108930325,
|
| 64 |
+
"round_trip": true
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"code": "pei",
|
| 68 |
+
"autonym": "",
|
| 69 |
+
"spanish_name": "Chichimeco Jonaz",
|
| 70 |
+
"inali_name": "chichimeco jonaz",
|
| 71 |
+
"english_name": "Chichimeco-Jonaz",
|
| 72 |
+
"samples": 3,
|
| 73 |
+
"chars": 1511,
|
| 74 |
+
"utf8_bytes": 1725,
|
| 75 |
+
"tokens": 423,
|
| 76 |
+
"chars_per_token": 3.5721040189125297,
|
| 77 |
+
"tokens_per_char": 0.2799470549305096,
|
| 78 |
+
"bytes_per_token": 4.078014184397163,
|
| 79 |
+
"tokens_per_byte": 0.24521739130434783,
|
| 80 |
+
"round_trip": true
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"code": "chj",
|
| 84 |
+
"autonym": "Jmiih kia’ dzä ‘vï ï, Jujmi",
|
| 85 |
+
"spanish_name": "Chinanteco de Ojitlán",
|
| 86 |
+
"inali_name": "chinanteco del norte",
|
| 87 |
+
"english_name": "Ojitlán Chinantec",
|
| 88 |
+
"samples": 3,
|
| 89 |
+
"chars": 1511,
|
| 90 |
+
"utf8_bytes": 1740,
|
| 91 |
+
"tokens": 591,
|
| 92 |
+
"chars_per_token": 2.55668358714044,
|
| 93 |
+
"tokens_per_char": 0.39113170086035737,
|
| 94 |
+
"bytes_per_token": 2.9441624365482233,
|
| 95 |
+
"tokens_per_byte": 0.3396551724137931,
|
| 96 |
+
"round_trip": true
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"code": "cuc",
|
| 100 |
+
"autonym": "Jau² jm⁴³",
|
| 101 |
+
"spanish_name": "Chinanteco de Usila",
|
| 102 |
+
"inali_name": "chinanteco del oeste central alto",
|
| 103 |
+
"english_name": "Usila Chinantec",
|
| 104 |
+
"samples": 4,
|
| 105 |
+
"chars": 2015,
|
| 106 |
+
"utf8_bytes": 2521,
|
| 107 |
+
"tokens": 830,
|
| 108 |
+
"chars_per_token": 2.427710843373494,
|
| 109 |
+
"tokens_per_char": 0.4119106699751861,
|
| 110 |
+
"bytes_per_token": 3.0373493975903614,
|
| 111 |
+
"tokens_per_byte": 0.32923443078143594,
|
| 112 |
+
"round_trip": true
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"code": "cco",
|
| 116 |
+
"autonym": "Jmíiˊ",
|
| 117 |
+
"spanish_name": "Chinanteco de Comaltepec",
|
| 118 |
+
"inali_name": "chinanteco de la Sierra",
|
| 119 |
+
"english_name": "Comaltepec Chinantec",
|
| 120 |
+
"samples": 1,
|
| 121 |
+
"chars": 503,
|
| 122 |
+
"utf8_bytes": 599,
|
| 123 |
+
"tokens": 182,
|
| 124 |
+
"chars_per_token": 2.7637362637362637,
|
| 125 |
+
"tokens_per_char": 0.36182902584493043,
|
| 126 |
+
"bytes_per_token": 3.291208791208791,
|
| 127 |
+
"tokens_per_byte": 0.3038397328881469,
|
| 128 |
+
"round_trip": true
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"code": "coz",
|
| 132 |
+
"autonym": "",
|
| 133 |
+
"spanish_name": "Chocholteco",
|
| 134 |
+
"inali_name": "chocholteco del oeste",
|
| 135 |
+
"english_name": "Chocholtec",
|
| 136 |
+
"samples": 3,
|
| 137 |
+
"chars": 1511,
|
| 138 |
+
"utf8_bytes": 1591,
|
| 139 |
+
"tokens": 467,
|
| 140 |
+
"chars_per_token": 3.235546038543897,
|
| 141 |
+
"tokens_per_char": 0.30906684315023164,
|
| 142 |
+
"bytes_per_token": 3.4068522483940042,
|
| 143 |
+
"tokens_per_byte": 0.29352608422375864,
|
| 144 |
+
"round_trip": true
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"code": "ctu",
|
| 148 |
+
"autonym": "Ch'ol, Lakty’añ",
|
| 149 |
+
"spanish_name": "Ch'ol",
|
| 150 |
+
"inali_name": "ch’ol del noroeste",
|
| 151 |
+
"english_name": "Chol",
|
| 152 |
+
"samples": 3,
|
| 153 |
+
"chars": 1511,
|
| 154 |
+
"utf8_bytes": 1753,
|
| 155 |
+
"tokens": 365,
|
| 156 |
+
"chars_per_token": 4.13972602739726,
|
| 157 |
+
"tokens_per_char": 0.2415618795499669,
|
| 158 |
+
"bytes_per_token": 4.802739726027397,
|
| 159 |
+
"tokens_per_byte": 0.20821448944666288,
|
| 160 |
+
"round_trip": true
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"code": "chf",
|
| 164 |
+
"autonym": "Yocot'an",
|
| 165 |
+
"spanish_name": "Chontal de Tabasco",
|
| 166 |
+
"inali_name": "chontal de Tabasco central",
|
| 167 |
+
"english_name": "Tabasco Chontal",
|
| 168 |
+
"samples": 4,
|
| 169 |
+
"chars": 2015,
|
| 170 |
+
"utf8_bytes": 2165,
|
| 171 |
+
"tokens": 658,
|
| 172 |
+
"chars_per_token": 3.0623100303951367,
|
| 173 |
+
"tokens_per_char": 0.32655086848635234,
|
| 174 |
+
"bytes_per_token": 3.290273556231003,
|
| 175 |
+
"tokens_per_byte": 0.3039260969976905,
|
| 176 |
+
"round_trip": true
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"code": "cac",
|
| 180 |
+
"autonym": "Koti'",
|
| 181 |
+
"spanish_name": "Chuj",
|
| 182 |
+
"inali_name": "Chuj",
|
| 183 |
+
"english_name": "Chuj",
|
| 184 |
+
"samples": 3,
|
| 185 |
+
"chars": 1445,
|
| 186 |
+
"utf8_bytes": 1614,
|
| 187 |
+
"tokens": 456,
|
| 188 |
+
"chars_per_token": 3.168859649122807,
|
| 189 |
+
"tokens_per_char": 0.31557093425605537,
|
| 190 |
+
"bytes_per_token": 3.539473684210526,
|
| 191 |
+
"tokens_per_byte": 0.2825278810408922,
|
| 192 |
+
"round_trip": true
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"code": "crn",
|
| 196 |
+
"autonym": "Naáyeri Nyuuca",
|
| 197 |
+
"spanish_name": "Cora de El Nayar",
|
| 198 |
+
"inali_name": "cora meseño",
|
| 199 |
+
"english_name": "El Nayar Cora",
|
| 200 |
+
"samples": 3,
|
| 201 |
+
"chars": 1511,
|
| 202 |
+
"utf8_bytes": 1664,
|
| 203 |
+
"tokens": 565,
|
| 204 |
+
"chars_per_token": 2.674336283185841,
|
| 205 |
+
"tokens_per_char": 0.3739245532759762,
|
| 206 |
+
"bytes_per_token": 2.945132743362832,
|
| 207 |
+
"tokens_per_byte": 0.3395432692307692,
|
| 208 |
+
"round_trip": true
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"code": "cok",
|
| 212 |
+
"autonym": "Cuéimarusaꞌna",
|
| 213 |
+
"spanish_name": "Cora de Santa Teresa",
|
| 214 |
+
"inali_name": "cora tereseño",
|
| 215 |
+
"english_name": "Santa Teresa Cora",
|
| 216 |
+
"samples": 1,
|
| 217 |
+
"chars": 503,
|
| 218 |
+
"utf8_bytes": 503,
|
| 219 |
+
"tokens": 172,
|
| 220 |
+
"chars_per_token": 2.9244186046511627,
|
| 221 |
+
"tokens_per_char": 0.341948310139165,
|
| 222 |
+
"bytes_per_token": 2.9244186046511627,
|
| 223 |
+
"tokens_per_byte": 0.341948310139165,
|
| 224 |
+
"round_trip": true
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"code": "cux",
|
| 228 |
+
"autonym": "Cuicateco yeⁿꞌe Tepeuxila",
|
| 229 |
+
"spanish_name": "Cuicateco de Tepeuxila",
|
| 230 |
+
"inali_name": "cuicateco del centro",
|
| 231 |
+
"english_name": "Tepeuxila Cuicatec",
|
| 232 |
+
"samples": 3,
|
| 233 |
+
"chars": 1511,
|
| 234 |
+
"utf8_bytes": 1828,
|
| 235 |
+
"tokens": 407,
|
| 236 |
+
"chars_per_token": 3.7125307125307123,
|
| 237 |
+
"tokens_per_char": 0.26935804103242883,
|
| 238 |
+
"bytes_per_token": 4.4914004914004915,
|
| 239 |
+
"tokens_per_byte": 0.22264770240700218,
|
| 240 |
+
"round_trip": true
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"code": "var",
|
| 244 |
+
"autonym": "Warijio",
|
| 245 |
+
"spanish_name": "Guarijío",
|
| 246 |
+
"inali_name": "guarijío del norte",
|
| 247 |
+
"english_name": "Huarijío",
|
| 248 |
+
"samples": 3,
|
| 249 |
+
"chars": 1511,
|
| 250 |
+
"utf8_bytes": 1648,
|
| 251 |
+
"tokens": 498,
|
| 252 |
+
"chars_per_token": 3.034136546184739,
|
| 253 |
+
"tokens_per_char": 0.32958305757776307,
|
| 254 |
+
"bytes_per_token": 3.3092369477911645,
|
| 255 |
+
"tokens_per_byte": 0.30218446601941745,
|
| 256 |
+
"round_trip": true
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"code": "hus",
|
| 260 |
+
"autonym": "Teenek",
|
| 261 |
+
"spanish_name": "Huasteco",
|
| 262 |
+
"inali_name": "huasteco del occidente",
|
| 263 |
+
"english_name": "Huastec",
|
| 264 |
+
"samples": 3,
|
| 265 |
+
"chars": 1450,
|
| 266 |
+
"utf8_bytes": 1585,
|
| 267 |
+
"tokens": 378,
|
| 268 |
+
"chars_per_token": 3.835978835978836,
|
| 269 |
+
"tokens_per_char": 0.26068965517241377,
|
| 270 |
+
"bytes_per_token": 4.193121693121693,
|
| 271 |
+
"tokens_per_byte": 0.2384858044164038,
|
| 272 |
+
"round_trip": true
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"code": "huv",
|
| 276 |
+
"autonym": "Ombeayiüts",
|
| 277 |
+
"spanish_name": "Huave de San Mateo del Mar",
|
| 278 |
+
"inali_name": "huave del oeste",
|
| 279 |
+
"english_name": "San Mateo del Mar Huave",
|
| 280 |
+
"samples": 3,
|
| 281 |
+
"chars": 1511,
|
| 282 |
+
"utf8_bytes": 1600,
|
| 283 |
+
"tokens": 376,
|
| 284 |
+
"chars_per_token": 4.0186170212765955,
|
| 285 |
+
"tokens_per_char": 0.24884182660489743,
|
| 286 |
+
"bytes_per_token": 4.25531914893617,
|
| 287 |
+
"tokens_per_byte": 0.235,
|
| 288 |
+
"round_trip": true
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"code": "hch",
|
| 292 |
+
"autonym": "Wixárika, Wixárika Niukiyari",
|
| 293 |
+
"spanish_name": "Huichol",
|
| 294 |
+
"inali_name": "huichol del norte",
|
| 295 |
+
"english_name": "Huichol",
|
| 296 |
+
"samples": 5,
|
| 297 |
+
"chars": 2519,
|
| 298 |
+
"utf8_bytes": 2752,
|
| 299 |
+
"tokens": 844,
|
| 300 |
+
"chars_per_token": 2.984597156398104,
|
| 301 |
+
"tokens_per_char": 0.3350535926955141,
|
| 302 |
+
"bytes_per_token": 3.2606635071090047,
|
| 303 |
+
"tokens_per_byte": 0.3066860465116279,
|
| 304 |
+
"round_trip": true
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"code": "jac",
|
| 308 |
+
"autonym": "Abxubal, Abꞌxubꞌal Poptiꞌ",
|
| 309 |
+
"spanish_name": "Jakalteko",
|
| 310 |
+
"inali_name": "Jakalteko",
|
| 311 |
+
"english_name": "Jakalteko",
|
| 312 |
+
"samples": 3,
|
| 313 |
+
"chars": 1511,
|
| 314 |
+
"utf8_bytes": 1689,
|
| 315 |
+
"tokens": 523,
|
| 316 |
+
"chars_per_token": 2.8891013384321225,
|
| 317 |
+
"tokens_per_char": 0.34612839179351423,
|
| 318 |
+
"bytes_per_token": 3.229445506692161,
|
| 319 |
+
"tokens_per_byte": 0.30965068087625813,
|
| 320 |
+
"round_trip": true
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"code": "quc",
|
| 324 |
+
"autonym": "K'iche', Qach'abel",
|
| 325 |
+
"spanish_name": "Kiché",
|
| 326 |
+
"inali_name": "K’iche’ (oriental)",
|
| 327 |
+
"english_name": "K’iche’",
|
| 328 |
+
"samples": 3,
|
| 329 |
+
"chars": 1511,
|
| 330 |
+
"utf8_bytes": 1558,
|
| 331 |
+
"tokens": 470,
|
| 332 |
+
"chars_per_token": 3.2148936170212767,
|
| 333 |
+
"tokens_per_char": 0.3110522832561218,
|
| 334 |
+
"bytes_per_token": 3.3148936170212764,
|
| 335 |
+
"tokens_per_byte": 0.30166880616174585,
|
| 336 |
+
"round_trip": true
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"code": "klb",
|
| 340 |
+
"autonym": "Kiliwa",
|
| 341 |
+
"spanish_name": "Kiliwa",
|
| 342 |
+
"inali_name": "kiliwa",
|
| 343 |
+
"english_name": "Kiliwa",
|
| 344 |
+
"samples": 1,
|
| 345 |
+
"chars": 503,
|
| 346 |
+
"utf8_bytes": 528,
|
| 347 |
+
"tokens": 168,
|
| 348 |
+
"chars_per_token": 2.994047619047619,
|
| 349 |
+
"tokens_per_char": 0.33399602385685884,
|
| 350 |
+
"bytes_per_token": 3.142857142857143,
|
| 351 |
+
"tokens_per_byte": 0.3181818181818182,
|
| 352 |
+
"round_trip": true
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"code": "dih",
|
| 356 |
+
"autonym": "Kumiai",
|
| 357 |
+
"spanish_name": "Kumiai",
|
| 358 |
+
"inali_name": "kumiai",
|
| 359 |
+
"english_name": "Kumiai",
|
| 360 |
+
"samples": 2,
|
| 361 |
+
"chars": 1007,
|
| 362 |
+
"utf8_bytes": 1048,
|
| 363 |
+
"tokens": 305,
|
| 364 |
+
"chars_per_token": 3.301639344262295,
|
| 365 |
+
"tokens_per_char": 0.3028798411122145,
|
| 366 |
+
"bytes_per_token": 3.4360655737704917,
|
| 367 |
+
"tokens_per_byte": 0.29103053435114506,
|
| 368 |
+
"round_trip": true
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"code": "lac",
|
| 372 |
+
"autonym": "Jach-t'aan",
|
| 373 |
+
"spanish_name": "Lacandón",
|
| 374 |
+
"inali_name": "lacandón",
|
| 375 |
+
"english_name": "Lacandon",
|
| 376 |
+
"samples": 5,
|
| 377 |
+
"chars": 2519,
|
| 378 |
+
"utf8_bytes": 2820,
|
| 379 |
+
"tokens": 673,
|
| 380 |
+
"chars_per_token": 3.7429420505200595,
|
| 381 |
+
"tokens_per_char": 0.26716951171099645,
|
| 382 |
+
"bytes_per_token": 4.190193164933135,
|
| 383 |
+
"tokens_per_byte": 0.23865248226950356,
|
| 384 |
+
"round_trip": true
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"code": "mam",
|
| 388 |
+
"autonym": "Qyol Mam, Yol Mam",
|
| 389 |
+
"spanish_name": "Mam",
|
| 390 |
+
"inali_name": "Mam de la frontera",
|
| 391 |
+
"english_name": "Mam",
|
| 392 |
+
"samples": 4,
|
| 393 |
+
"chars": 2015,
|
| 394 |
+
"utf8_bytes": 2083,
|
| 395 |
+
"tokens": 602,
|
| 396 |
+
"chars_per_token": 3.3471760797342194,
|
| 397 |
+
"tokens_per_char": 0.2987593052109181,
|
| 398 |
+
"bytes_per_token": 3.4601328903654487,
|
| 399 |
+
"tokens_per_byte": 0.28900624099855976,
|
| 400 |
+
"round_trip": true
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"code": "mat",
|
| 404 |
+
"autonym": "bot’una",
|
| 405 |
+
"spanish_name": "Matlatzinca de San Francisco",
|
| 406 |
+
"inali_name": "matlatzinca",
|
| 407 |
+
"english_name": "Matlatzinca, San Francisco",
|
| 408 |
+
"samples": 3,
|
| 409 |
+
"chars": 1511,
|
| 410 |
+
"utf8_bytes": 1619,
|
| 411 |
+
"tokens": 373,
|
| 412 |
+
"chars_per_token": 4.050938337801608,
|
| 413 |
+
"tokens_per_char": 0.2468563864990073,
|
| 414 |
+
"bytes_per_token": 4.340482573726542,
|
| 415 |
+
"tokens_per_byte": 0.23038912909203213,
|
| 416 |
+
"round_trip": true
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"code": "yua",
|
| 420 |
+
"autonym": "Maaya t'aan",
|
| 421 |
+
"spanish_name": "Maya de Yucatán",
|
| 422 |
+
"inali_name": "maya",
|
| 423 |
+
"english_name": "Yucatec Maya",
|
| 424 |
+
"samples": 5,
|
| 425 |
+
"chars": 2519,
|
| 426 |
+
"utf8_bytes": 2945,
|
| 427 |
+
"tokens": 565,
|
| 428 |
+
"chars_per_token": 4.458407079646018,
|
| 429 |
+
"tokens_per_char": 0.2242953552997221,
|
| 430 |
+
"bytes_per_token": 5.212389380530974,
|
| 431 |
+
"tokens_per_byte": 0.19185059422750425,
|
| 432 |
+
"round_trip": true
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"code": "mfy",
|
| 436 |
+
"autonym": "Yorem Nokpo",
|
| 437 |
+
"spanish_name": "Mayo",
|
| 438 |
+
"inali_name": "mayo",
|
| 439 |
+
"english_name": "Mayo",
|
| 440 |
+
"samples": 3,
|
| 441 |
+
"chars": 1511,
|
| 442 |
+
"utf8_bytes": 1555,
|
| 443 |
+
"tokens": 470,
|
| 444 |
+
"chars_per_token": 3.2148936170212767,
|
| 445 |
+
"tokens_per_char": 0.3110522832561218,
|
| 446 |
+
"bytes_per_token": 3.3085106382978724,
|
| 447 |
+
"tokens_per_byte": 0.3022508038585209,
|
| 448 |
+
"round_trip": true
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"code": "maz",
|
| 452 |
+
"autonym": "Jñatjo",
|
| 453 |
+
"spanish_name": "Mazahua Central",
|
| 454 |
+
"inali_name": "mazahua de oriente",
|
| 455 |
+
"english_name": "Central Mazahua",
|
| 456 |
+
"samples": 3,
|
| 457 |
+
"chars": 1511,
|
| 458 |
+
"utf8_bytes": 1702,
|
| 459 |
+
"tokens": 380,
|
| 460 |
+
"chars_per_token": 3.9763157894736842,
|
| 461 |
+
"tokens_per_char": 0.2514890800794176,
|
| 462 |
+
"bytes_per_token": 4.478947368421053,
|
| 463 |
+
"tokens_per_byte": 0.22326674500587543,
|
| 464 |
+
"round_trip": true
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"code": "mmc",
|
| 468 |
+
"autonym": "Jñatjo",
|
| 469 |
+
"spanish_name": "Mazahua de Michoacán",
|
| 470 |
+
"inali_name": "mazahua de occidente",
|
| 471 |
+
"english_name": "Michoacán Mazahua",
|
| 472 |
+
"samples": 2,
|
| 473 |
+
"chars": 1007,
|
| 474 |
+
"utf8_bytes": 1069,
|
| 475 |
+
"tokens": 338,
|
| 476 |
+
"chars_per_token": 2.9792899408284024,
|
| 477 |
+
"tokens_per_char": 0.3356504468718967,
|
| 478 |
+
"bytes_per_token": 3.162721893491124,
|
| 479 |
+
"tokens_per_byte": 0.3161833489242282,
|
| 480 |
+
"round_trip": true
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"code": "vmp",
|
| 484 |
+
"autonym": "En naxijen",
|
| 485 |
+
"spanish_name": "Mazateco de Soyaltepec",
|
| 486 |
+
"inali_name": "mazateco del noreste",
|
| 487 |
+
"english_name": "Soyaltepec Mazatec",
|
| 488 |
+
"samples": 3,
|
| 489 |
+
"chars": 1511,
|
| 490 |
+
"utf8_bytes": 1661,
|
| 491 |
+
"tokens": 484,
|
| 492 |
+
"chars_per_token": 3.121900826446281,
|
| 493 |
+
"tokens_per_char": 0.3203176704169424,
|
| 494 |
+
"bytes_per_token": 3.4318181818181817,
|
| 495 |
+
"tokens_per_byte": 0.2913907284768212,
|
| 496 |
+
"round_trip": true
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"code": "mzi",
|
| 500 |
+
"autonym": "En ningotsie",
|
| 501 |
+
"spanish_name": "Mazateco de Ixcatlán",
|
| 502 |
+
"inali_name": "mazateco de la presa bajo",
|
| 503 |
+
"english_name": "Ixcatlán Mazatec",
|
| 504 |
+
"samples": 3,
|
| 505 |
+
"chars": 1511,
|
| 506 |
+
"utf8_bytes": 1686,
|
| 507 |
+
"tokens": 461,
|
| 508 |
+
"chars_per_token": 3.27765726681128,
|
| 509 |
+
"tokens_per_char": 0.30509596293845137,
|
| 510 |
+
"bytes_per_token": 3.6572668112798263,
|
| 511 |
+
"tokens_per_byte": 0.2734282325029656,
|
| 512 |
+
"round_trip": true
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"code": "maj",
|
| 516 |
+
"autonym": "Kinꞌekꞌatiya, Ntaxjo̱",
|
| 517 |
+
"spanish_name": "Mazateco de Jalapa de Díaz",
|
| 518 |
+
"inali_name": "mazateco del este bajo",
|
| 519 |
+
"english_name": "Jalapa de Díaz Mazatec",
|
| 520 |
+
"samples": 1,
|
| 521 |
+
"chars": 503,
|
| 522 |
+
"utf8_bytes": 507,
|
| 523 |
+
"tokens": 134,
|
| 524 |
+
"chars_per_token": 3.753731343283582,
|
| 525 |
+
"tokens_per_char": 0.2664015904572565,
|
| 526 |
+
"bytes_per_token": 3.783582089552239,
|
| 527 |
+
"tokens_per_byte": 0.26429980276134124,
|
| 528 |
+
"round_trip": true
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"code": "maq",
|
| 532 |
+
"autonym": "Hne naja, Nne nangui ngaxni",
|
| 533 |
+
"spanish_name": "Mazateco de Chiquihuitlán",
|
| 534 |
+
"inali_name": "mazateco del sur",
|
| 535 |
+
"english_name": "Chiquihuitlán Mazatec",
|
| 536 |
+
"samples": 2,
|
| 537 |
+
"chars": 1007,
|
| 538 |
+
"utf8_bytes": 1099,
|
| 539 |
+
"tokens": 330,
|
| 540 |
+
"chars_per_token": 3.0515151515151517,
|
| 541 |
+
"tokens_per_char": 0.32770605759682225,
|
| 542 |
+
"bytes_per_token": 3.33030303030303,
|
| 543 |
+
"tokens_per_byte": 0.3002729754322111,
|
| 544 |
+
"round_trip": true
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"code": "vmy",
|
| 548 |
+
"autonym": "Enre naxinanda nguifi",
|
| 549 |
+
"spanish_name": "Mazateco de Ayautla",
|
| 550 |
+
"inali_name": "mazateco del sureste",
|
| 551 |
+
"english_name": "Ayautla Mazatec",
|
| 552 |
+
"samples": 1,
|
| 553 |
+
"chars": 503,
|
| 554 |
+
"utf8_bytes": 556,
|
| 555 |
+
"tokens": 173,
|
| 556 |
+
"chars_per_token": 2.907514450867052,
|
| 557 |
+
"tokens_per_char": 0.34393638170974156,
|
| 558 |
+
"bytes_per_token": 3.213872832369942,
|
| 559 |
+
"tokens_per_byte": 0.31115107913669066,
|
| 560 |
+
"round_trip": true
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"code": "mau",
|
| 564 |
+
"autonym": "Én‑ná",
|
| 565 |
+
"spanish_name": "Mazateco de Huautla",
|
| 566 |
+
"inali_name": "mazateco del centro",
|
| 567 |
+
"english_name": "Huautla Mazatec",
|
| 568 |
+
"samples": 5,
|
| 569 |
+
"chars": 2519,
|
| 570 |
+
"utf8_bytes": 2838,
|
| 571 |
+
"tokens": 761,
|
| 572 |
+
"chars_per_token": 3.3101182654402104,
|
| 573 |
+
"tokens_per_char": 0.3021040095275903,
|
| 574 |
+
"bytes_per_token": 3.729303547963206,
|
| 575 |
+
"tokens_per_byte": 0.2681465821000705,
|
| 576 |
+
"round_trip": true
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"code": "mto",
|
| 580 |
+
"autonym": "Ayöök",
|
| 581 |
+
"spanish_name": "Mixe de Totontepec",
|
| 582 |
+
"inali_name": "mixe alto del norte",
|
| 583 |
+
"english_name": "Totontepec Mixe",
|
| 584 |
+
"samples": 4,
|
| 585 |
+
"chars": 2015,
|
| 586 |
+
"utf8_bytes": 2331,
|
| 587 |
+
"tokens": 718,
|
| 588 |
+
"chars_per_token": 2.8064066852367686,
|
| 589 |
+
"tokens_per_char": 0.3563275434243176,
|
| 590 |
+
"bytes_per_token": 3.246518105849582,
|
| 591 |
+
"tokens_per_byte": 0.308022308022308,
|
| 592 |
+
"round_trip": true
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"code": "mxp",
|
| 596 |
+
"autonym": "Ayuujk",
|
| 597 |
+
"spanish_name": "Mixe de Tlahuitoltepec",
|
| 598 |
+
"inali_name": "mixe alto del centro",
|
| 599 |
+
"english_name": "Tlahuitoltepec Mixe",
|
| 600 |
+
"samples": 2,
|
| 601 |
+
"chars": 1007,
|
| 602 |
+
"utf8_bytes": 1141,
|
| 603 |
+
"tokens": 400,
|
| 604 |
+
"chars_per_token": 2.5175,
|
| 605 |
+
"tokens_per_char": 0.3972194637537239,
|
| 606 |
+
"bytes_per_token": 2.8525,
|
| 607 |
+
"tokens_per_byte": 0.35056967572305,
|
| 608 |
+
"round_trip": true
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"code": "mxq",
|
| 612 |
+
"autonym": "Ayuk",
|
| 613 |
+
"spanish_name": "Mixe de Juquila",
|
| 614 |
+
"inali_name": "mixe medio del este",
|
| 615 |
+
"english_name": "Juquila Mixe",
|
| 616 |
+
"samples": 4,
|
| 617 |
+
"chars": 2015,
|
| 618 |
+
"utf8_bytes": 2509,
|
| 619 |
+
"tokens": 675,
|
| 620 |
+
"chars_per_token": 2.9851851851851854,
|
| 621 |
+
"tokens_per_char": 0.3349875930521092,
|
| 622 |
+
"bytes_per_token": 3.717037037037037,
|
| 623 |
+
"tokens_per_byte": 0.269031486648067,
|
| 624 |
+
"round_trip": true
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"code": "xta",
|
| 628 |
+
"autonym": "Tu̱'un sâvi",
|
| 629 |
+
"spanish_name": "Mixteco de Alcozauca",
|
| 630 |
+
"inali_name": "mixteco de Guerrero del noreste central",
|
| 631 |
+
"english_name": "Alcozauca Mixtec",
|
| 632 |
+
"samples": 2,
|
| 633 |
+
"chars": 1007,
|
| 634 |
+
"utf8_bytes": 1075,
|
| 635 |
+
"tokens": 306,
|
| 636 |
+
"chars_per_token": 3.2908496732026142,
|
| 637 |
+
"tokens_per_char": 0.3038728897715988,
|
| 638 |
+
"bytes_per_token": 3.5130718954248366,
|
| 639 |
+
"tokens_per_byte": 0.2846511627906977,
|
| 640 |
+
"round_trip": true
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"code": "mxv",
|
| 644 |
+
"autonym": "Tuꞌun Savi de Metlatónoc y Cochoapa el Grande, Tuꞌun savi",
|
| 645 |
+
"spanish_name": "Mixteco de Metlatónoc",
|
| 646 |
+
"inali_name": "mixteco de Guerrero del este medio",
|
| 647 |
+
"english_name": "Metlatónoc Mixtec",
|
| 648 |
+
"samples": 1,
|
| 649 |
+
"chars": 503,
|
| 650 |
+
"utf8_bytes": 568,
|
| 651 |
+
"tokens": 214,
|
| 652 |
+
"chars_per_token": 2.350467289719626,
|
| 653 |
+
"tokens_per_char": 0.4254473161033797,
|
| 654 |
+
"bytes_per_token": 2.6542056074766354,
|
| 655 |
+
"tokens_per_byte": 0.3767605633802817,
|
| 656 |
+
"round_trip": true
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"code": "miy",
|
| 660 |
+
"autonym": "Tu̱n savi̱ꞌ Tu̱tyoo̱ꞌ",
|
| 661 |
+
"spanish_name": "Mixteco de Ayutla",
|
| 662 |
+
"inali_name": "mixteco de Ayutla",
|
| 663 |
+
"english_name": "Ayutla Mixtec",
|
| 664 |
+
"samples": 4,
|
| 665 |
+
"chars": 2015,
|
| 666 |
+
"utf8_bytes": 2417,
|
| 667 |
+
"tokens": 613,
|
| 668 |
+
"chars_per_token": 3.2871125611745513,
|
| 669 |
+
"tokens_per_char": 0.3042183622828784,
|
| 670 |
+
"bytes_per_token": 3.9429037520391517,
|
| 671 |
+
"tokens_per_byte": 0.25362019031857674,
|
| 672 |
+
"round_trip": true
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"code": "mxt",
|
| 676 |
+
"autonym": "Sa'an Xiñi Savi",
|
| 677 |
+
"spanish_name": "Mixteco de Jamiltepec",
|
| 678 |
+
"inali_name": "mixteco de Oaxaca de costa central baja",
|
| 679 |
+
"english_name": "Jamiltepec Mixtec",
|
| 680 |
+
"samples": 3,
|
| 681 |
+
"chars": 1511,
|
| 682 |
+
"utf8_bytes": 1672,
|
| 683 |
+
"tokens": 446,
|
| 684 |
+
"chars_per_token": 3.3878923766816142,
|
| 685 |
+
"tokens_per_char": 0.29516876240900064,
|
| 686 |
+
"bytes_per_token": 3.7488789237668163,
|
| 687 |
+
"tokens_per_byte": 0.26674641148325356,
|
| 688 |
+
"round_trip": true
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"code": "mza",
|
| 692 |
+
"autonym": "Tu'un va'a",
|
| 693 |
+
"spanish_name": "Mixteco de Santa María Zacatepec",
|
| 694 |
+
"inali_name": "mixteco de Sierra sur oeste",
|
| 695 |
+
"english_name": "Santa María Zacatepec Mixtec",
|
| 696 |
+
"samples": 3,
|
| 697 |
+
"chars": 1511,
|
| 698 |
+
"utf8_bytes": 1780,
|
| 699 |
+
"tokens": 441,
|
| 700 |
+
"chars_per_token": 3.4263038548752833,
|
| 701 |
+
"tokens_per_char": 0.29185969556585045,
|
| 702 |
+
"bytes_per_token": 4.036281179138322,
|
| 703 |
+
"tokens_per_byte": 0.24775280898876403,
|
| 704 |
+
"round_trip": true
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"code": "meh",
|
| 708 |
+
"autonym": "Tu̱ꞌun káꞌánꞌ kájí",
|
| 709 |
+
"spanish_name": "Mixteco del Suroeste de Tlaxiaco",
|
| 710 |
+
"inali_name": "mixteco del suroeste",
|
| 711 |
+
"english_name": "Southwestern Tlaxiaco Mixtec",
|
| 712 |
+
"samples": 3,
|
| 713 |
+
"chars": 1511,
|
| 714 |
+
"utf8_bytes": 1552,
|
| 715 |
+
"tokens": 400,
|
| 716 |
+
"chars_per_token": 3.7775,
|
| 717 |
+
"tokens_per_char": 0.26472534745201853,
|
| 718 |
+
"bytes_per_token": 3.88,
|
| 719 |
+
"tokens_per_byte": 0.25773195876288657,
|
| 720 |
+
"round_trip": true
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"code": "mix",
|
| 724 |
+
"autonym": "Sa'an Savi Snuviko, Sa'an savi",
|
| 725 |
+
"spanish_name": "Mixteco de Mixtepec",
|
| 726 |
+
"inali_name": "mixteco de Ñumi",
|
| 727 |
+
"english_name": "Mixtepec Mixtec",
|
| 728 |
+
"samples": 3,
|
| 729 |
+
"chars": 1511,
|
| 730 |
+
"utf8_bytes": 1669,
|
| 731 |
+
"tokens": 444,
|
| 732 |
+
"chars_per_token": 3.4031531531531534,
|
| 733 |
+
"tokens_per_char": 0.2938451356717406,
|
| 734 |
+
"bytes_per_token": 3.759009009009009,
|
| 735 |
+
"tokens_per_byte": 0.2660275614140204,
|
| 736 |
+
"round_trip": true
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"code": "xtn",
|
| 740 |
+
"autonym": "Saꞌan savi",
|
| 741 |
+
"spanish_name": "Mixteco de Tlaxiaco del Norte",
|
| 742 |
+
"inali_name": "mixteco del norte bajo",
|
| 743 |
+
"english_name": "Northern Tlaxiaco Mixtec",
|
| 744 |
+
"samples": 4,
|
| 745 |
+
"chars": 2015,
|
| 746 |
+
"utf8_bytes": 2174,
|
| 747 |
+
"tokens": 619,
|
| 748 |
+
"chars_per_token": 3.255250403877221,
|
| 749 |
+
"tokens_per_char": 0.30719602977667493,
|
| 750 |
+
"bytes_per_token": 3.5121163166397413,
|
| 751 |
+
"tokens_per_byte": 0.2847286108555658,
|
| 752 |
+
"round_trip": true
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"code": "mks",
|
| 756 |
+
"autonym": "Tu̱hun ndáhví",
|
| 757 |
+
"spanish_name": "Mixteco de Silacayoapan",
|
| 758 |
+
"inali_name": "mixteco del oeste alto",
|
| 759 |
+
"english_name": "Silacayoapan Mixtec",
|
| 760 |
+
"samples": 1,
|
| 761 |
+
"chars": 503,
|
| 762 |
+
"utf8_bytes": 549,
|
| 763 |
+
"tokens": 167,
|
| 764 |
+
"chars_per_token": 3.0119760479041915,
|
| 765 |
+
"tokens_per_char": 0.3320079522862823,
|
| 766 |
+
"bytes_per_token": 3.287425149700599,
|
| 767 |
+
"tokens_per_byte": 0.30418943533697634,
|
| 768 |
+
"round_trip": true
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"code": "mie",
|
| 772 |
+
"autonym": "Tūhun sāsávī",
|
| 773 |
+
"spanish_name": "Mixteco de Ocotepec",
|
| 774 |
+
"inali_name": "mixteco de Sierra sur noroeste",
|
| 775 |
+
"english_name": "Ocotepec Mixtec",
|
| 776 |
+
"samples": 4,
|
| 777 |
+
"chars": 2015,
|
| 778 |
+
"utf8_bytes": 2238,
|
| 779 |
+
"tokens": 540,
|
| 780 |
+
"chars_per_token": 3.7314814814814814,
|
| 781 |
+
"tokens_per_char": 0.2679900744416873,
|
| 782 |
+
"bytes_per_token": 4.144444444444445,
|
| 783 |
+
"tokens_per_byte": 0.24128686327077747,
|
| 784 |
+
"round_trip": true
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"code": "mio",
|
| 788 |
+
"autonym": "Tuhun Ñuun Ñucaan",
|
| 789 |
+
"spanish_name": "Mixteco de Pinotepa Nacional",
|
| 790 |
+
"inali_name": "mixteco del oeste de la costa",
|
| 791 |
+
"english_name": "Pinotepa Nacional Mixtec",
|
| 792 |
+
"samples": 4,
|
| 793 |
+
"chars": 2015,
|
| 794 |
+
"utf8_bytes": 2186,
|
| 795 |
+
"tokens": 462,
|
| 796 |
+
"chars_per_token": 4.361471861471862,
|
| 797 |
+
"tokens_per_char": 0.2292803970223325,
|
| 798 |
+
"bytes_per_token": 4.731601731601732,
|
| 799 |
+
"tokens_per_byte": 0.21134492223238793,
|
| 800 |
+
"round_trip": true
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"code": "nhx",
|
| 804 |
+
"autonym": "Melaꞌtájto̱l",
|
| 805 |
+
"spanish_name": "Náhuatl del Istmo-Mecayapan",
|
| 806 |
+
"inali_name": "náhuatl del Istmo",
|
| 807 |
+
"english_name": "Isthmus-Mecayapan Nahuatl",
|
| 808 |
+
"samples": 1,
|
| 809 |
+
"chars": 503,
|
| 810 |
+
"utf8_bytes": 503,
|
| 811 |
+
"tokens": 139,
|
| 812 |
+
"chars_per_token": 3.618705035971223,
|
| 813 |
+
"tokens_per_char": 0.27634194831013914,
|
| 814 |
+
"bytes_per_token": 3.618705035971223,
|
| 815 |
+
"tokens_per_byte": 0.27634194831013914,
|
| 816 |
+
"round_trip": true
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"code": "nhe",
|
| 820 |
+
"autonym": "Mexkatl",
|
| 821 |
+
"spanish_name": "Náhuatl Huasteco Oriental",
|
| 822 |
+
"inali_name": "náhuatl de la Huasteca veracruzana",
|
| 823 |
+
"english_name": "Eastern Huasteca Nahuatl",
|
| 824 |
+
"samples": 4,
|
| 825 |
+
"chars": 2015,
|
| 826 |
+
"utf8_bytes": 2083,
|
| 827 |
+
"tokens": 462,
|
| 828 |
+
"chars_per_token": 4.361471861471862,
|
| 829 |
+
"tokens_per_char": 0.2292803970223325,
|
| 830 |
+
"bytes_per_token": 4.508658008658009,
|
| 831 |
+
"tokens_per_byte": 0.22179548727796447,
|
| 832 |
+
"round_trip": true
|
| 833 |
+
},
|
| 834 |
+
{
|
| 835 |
+
"code": "nhw",
|
| 836 |
+
"autonym": "Nahuatl",
|
| 837 |
+
"spanish_name": "Náhuatl Huasteco Occidental",
|
| 838 |
+
"inali_name": "náhuatl de la Huasteca potosina",
|
| 839 |
+
"english_name": "Western Huasteca Nahuatl",
|
| 840 |
+
"samples": 4,
|
| 841 |
+
"chars": 2015,
|
| 842 |
+
"utf8_bytes": 2015,
|
| 843 |
+
"tokens": 460,
|
| 844 |
+
"chars_per_token": 4.380434782608695,
|
| 845 |
+
"tokens_per_char": 0.228287841191067,
|
| 846 |
+
"bytes_per_token": 4.380434782608695,
|
| 847 |
+
"tokens_per_byte": 0.228287841191067,
|
| 848 |
+
"round_trip": true
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"code": "nhy",
|
| 852 |
+
"autonym": "Nāhuatlahtōlli",
|
| 853 |
+
"spanish_name": "Náhuatl del Norte de Oaxaca",
|
| 854 |
+
"inali_name": "náhuatl de Oaxaca",
|
| 855 |
+
"english_name": "Northern Oaxaca Nahuatl",
|
| 856 |
+
"samples": 5,
|
| 857 |
+
"chars": 2519,
|
| 858 |
+
"utf8_bytes": 2587,
|
| 859 |
+
"tokens": 683,
|
| 860 |
+
"chars_per_token": 3.6881405563689604,
|
| 861 |
+
"tokens_per_char": 0.27113934100833664,
|
| 862 |
+
"bytes_per_token": 3.787701317715959,
|
| 863 |
+
"tokens_per_byte": 0.26401236954000773,
|
| 864 |
+
"round_trip": true
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"code": "nsu",
|
| 868 |
+
"autonym": "Nahuatl, Nahuatlajtoli",
|
| 869 |
+
"spanish_name": "Náhuatl de la Sierra Negra",
|
| 870 |
+
"inali_name": "náhuatl de la Sierra negra, sur",
|
| 871 |
+
"english_name": "Sierra Negra Nahuatl",
|
| 872 |
+
"samples": 3,
|
| 873 |
+
"chars": 1511,
|
| 874 |
+
"utf8_bytes": 1548,
|
| 875 |
+
"tokens": 444,
|
| 876 |
+
"chars_per_token": 3.4031531531531534,
|
| 877 |
+
"tokens_per_char": 0.2938451356717406,
|
| 878 |
+
"bytes_per_token": 3.4864864864864864,
|
| 879 |
+
"tokens_per_byte": 0.2868217054263566,
|
| 880 |
+
"round_trip": true
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"code": "ncj",
|
| 884 |
+
"autonym": "Mexicatl",
|
| 885 |
+
"spanish_name": "Náhuatl del Norte de Puebla",
|
| 886 |
+
"inali_name": "náhuatl alto del norte de Puebla",
|
| 887 |
+
"english_name": "Northern Puebla Nahuatl",
|
| 888 |
+
"samples": 4,
|
| 889 |
+
"chars": 2015,
|
| 890 |
+
"utf8_bytes": 2035,
|
| 891 |
+
"tokens": 551,
|
| 892 |
+
"chars_per_token": 3.6569872958257714,
|
| 893 |
+
"tokens_per_char": 0.27344913151364764,
|
| 894 |
+
"bytes_per_token": 3.6932849364791287,
|
| 895 |
+
"tokens_per_byte": 0.27076167076167074,
|
| 896 |
+
"round_trip": true
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"code": "ncx",
|
| 900 |
+
"autonym": "",
|
| 901 |
+
"spanish_name": "Náhuatl de Puebla Central",
|
| 902 |
+
"inali_name": "náhuatl del centro de Puebla",
|
| 903 |
+
"english_name": "Nahuatl, Central Puebla",
|
| 904 |
+
"samples": 5,
|
| 905 |
+
"chars": 2519,
|
| 906 |
+
"utf8_bytes": 2554,
|
| 907 |
+
"tokens": 615,
|
| 908 |
+
"chars_per_token": 4.095934959349593,
|
| 909 |
+
"tokens_per_char": 0.2441445017864232,
|
| 910 |
+
"bytes_per_token": 4.152845528455285,
|
| 911 |
+
"tokens_per_byte": 0.2407987470634299,
|
| 912 |
+
"round_trip": true
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"code": "azn",
|
| 916 |
+
"autonym": "Meshikan de San Agustin Buenaventura y de Santa Cruz",
|
| 917 |
+
"spanish_name": "Náhuatl de Durango Occidental",
|
| 918 |
+
"inali_name": "mexicano del noroeste",
|
| 919 |
+
"english_name": "Western Durango Nahuatl",
|
| 920 |
+
"samples": 4,
|
| 921 |
+
"chars": 2007,
|
| 922 |
+
"utf8_bytes": 2026,
|
| 923 |
+
"tokens": 576,
|
| 924 |
+
"chars_per_token": 3.484375,
|
| 925 |
+
"tokens_per_char": 0.28699551569506726,
|
| 926 |
+
"bytes_per_token": 3.517361111111111,
|
| 927 |
+
"tokens_per_byte": 0.2843040473840079,
|
| 928 |
+
"round_trip": true
|
| 929 |
+
},
|
| 930 |
+
{
|
| 931 |
+
"code": "ngu",
|
| 932 |
+
"autonym": "Nauatlajtojli",
|
| 933 |
+
"spanish_name": "Náhuatl de Guerrero",
|
| 934 |
+
"inali_name": "mexicano de Guerrero",
|
| 935 |
+
"english_name": "Guerrero Nahuatl",
|
| 936 |
+
"samples": 4,
|
| 937 |
+
"chars": 2015,
|
| 938 |
+
"utf8_bytes": 2020,
|
| 939 |
+
"tokens": 590,
|
| 940 |
+
"chars_per_token": 3.4152542372881354,
|
| 941 |
+
"tokens_per_char": 0.29280397022332505,
|
| 942 |
+
"bytes_per_token": 3.4237288135593222,
|
| 943 |
+
"tokens_per_byte": 0.29207920792079206,
|
| 944 |
+
"round_trip": true
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"code": "nhm",
|
| 948 |
+
"autonym": "Ika mejikano, Ika nauatl",
|
| 949 |
+
"spanish_name": "Náhuatl de Morelos",
|
| 950 |
+
"inali_name": "mexicano central bajo",
|
| 951 |
+
"english_name": "Morelos Nahuatl",
|
| 952 |
+
"samples": 3,
|
| 953 |
+
"chars": 1511,
|
| 954 |
+
"utf8_bytes": 1511,
|
| 955 |
+
"tokens": 360,
|
| 956 |
+
"chars_per_token": 4.197222222222222,
|
| 957 |
+
"tokens_per_char": 0.23825281270681667,
|
| 958 |
+
"bytes_per_token": 4.197222222222222,
|
| 959 |
+
"tokens_per_byte": 0.23825281270681667,
|
| 960 |
+
"round_trip": true
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"code": "nch",
|
| 964 |
+
"autonym": "Nāhuatlahtōlli",
|
| 965 |
+
"spanish_name": "Náhuatl Huasteco Central",
|
| 966 |
+
"inali_name": "mexicano de la Huasteca Hidalguense",
|
| 967 |
+
"english_name": "Central Huasteca Nahuatl",
|
| 968 |
+
"samples": 3,
|
| 969 |
+
"chars": 1511,
|
| 970 |
+
"utf8_bytes": 1511,
|
| 971 |
+
"tokens": 451,
|
| 972 |
+
"chars_per_token": 3.350332594235033,
|
| 973 |
+
"tokens_per_char": 0.2984778292521509,
|
| 974 |
+
"bytes_per_token": 3.350332594235033,
|
| 975 |
+
"tokens_per_byte": 0.2984778292521509,
|
| 976 |
+
"round_trip": true
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"code": "plo",
|
| 980 |
+
"autonym": "",
|
| 981 |
+
"spanish_name": "Popoluca de Oluta",
|
| 982 |
+
"inali_name": "oluteco",
|
| 983 |
+
"english_name": "Popoluca, Oluta",
|
| 984 |
+
"samples": 1,
|
| 985 |
+
"chars": 499,
|
| 986 |
+
"utf8_bytes": 540,
|
| 987 |
+
"tokens": 177,
|
| 988 |
+
"chars_per_token": 2.8192090395480225,
|
| 989 |
+
"tokens_per_char": 0.35470941883767537,
|
| 990 |
+
"bytes_per_token": 3.0508474576271185,
|
| 991 |
+
"tokens_per_byte": 0.3277777777777778,
|
| 992 |
+
"round_trip": true
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"code": "otm",
|
| 996 |
+
"autonym": "Nyuhu",
|
| 997 |
+
"spanish_name": "Otomí de la Sierra Oriental",
|
| 998 |
+
"inali_name": "otomí de la Sierra",
|
| 999 |
+
"english_name": "Eastern Highland Otomi",
|
| 1000 |
+
"samples": 3,
|
| 1001 |
+
"chars": 1511,
|
| 1002 |
+
"utf8_bytes": 1745,
|
| 1003 |
+
"tokens": 523,
|
| 1004 |
+
"chars_per_token": 2.8891013384321225,
|
| 1005 |
+
"tokens_per_char": 0.34612839179351423,
|
| 1006 |
+
"bytes_per_token": 3.3365200764818357,
|
| 1007 |
+
"tokens_per_byte": 0.2997134670487106,
|
| 1008 |
+
"round_trip": true
|
| 1009 |
+
},
|
| 1010 |
+
{
|
| 1011 |
+
"code": "otq",
|
| 1012 |
+
"autonym": "Ñhöñhö",
|
| 1013 |
+
"spanish_name": "Otomí de Querétaro",
|
| 1014 |
+
"inali_name": "otomí del noroeste",
|
| 1015 |
+
"english_name": "Querétaro Otomi",
|
| 1016 |
+
"samples": 3,
|
| 1017 |
+
"chars": 1511,
|
| 1018 |
+
"utf8_bytes": 1834,
|
| 1019 |
+
"tokens": 523,
|
| 1020 |
+
"chars_per_token": 2.8891013384321225,
|
| 1021 |
+
"tokens_per_char": 0.34612839179351423,
|
| 1022 |
+
"bytes_per_token": 3.5066921606118546,
|
| 1023 |
+
"tokens_per_byte": 0.2851690294438386,
|
| 1024 |
+
"round_trip": true
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"code": "ppi",
|
| 1028 |
+
"autonym": "Paipai",
|
| 1029 |
+
"spanish_name": "Paipai",
|
| 1030 |
+
"inali_name": "paipai",
|
| 1031 |
+
"english_name": "Paipai",
|
| 1032 |
+
"samples": 3,
|
| 1033 |
+
"chars": 1511,
|
| 1034 |
+
"utf8_bytes": 1554,
|
| 1035 |
+
"tokens": 530,
|
| 1036 |
+
"chars_per_token": 2.8509433962264152,
|
| 1037 |
+
"tokens_per_char": 0.35076108537392453,
|
| 1038 |
+
"bytes_per_token": 2.9320754716981132,
|
| 1039 |
+
"tokens_per_byte": 0.3410553410553411,
|
| 1040 |
+
"round_trip": true
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"code": "pmq",
|
| 1044 |
+
"autonym": "Xi'iuy",
|
| 1045 |
+
"spanish_name": "Pame del Norte",
|
| 1046 |
+
"inali_name": "pame del norte",
|
| 1047 |
+
"english_name": "Northern Pame",
|
| 1048 |
+
"samples": 3,
|
| 1049 |
+
"chars": 1511,
|
| 1050 |
+
"utf8_bytes": 1738,
|
| 1051 |
+
"tokens": 464,
|
| 1052 |
+
"chars_per_token": 3.2564655172413794,
|
| 1053 |
+
"tokens_per_char": 0.3070814030443415,
|
| 1054 |
+
"bytes_per_token": 3.7456896551724137,
|
| 1055 |
+
"tokens_per_byte": 0.2669735327963176,
|
| 1056 |
+
"round_trip": true
|
| 1057 |
+
},
|
| 1058 |
+
{
|
| 1059 |
+
"code": "pbs",
|
| 1060 |
+
"autonym": "Xi'oi",
|
| 1061 |
+
"spanish_name": "Pame Central",
|
| 1062 |
+
"inali_name": "pame del centro",
|
| 1063 |
+
"english_name": "Central Pame",
|
| 1064 |
+
"samples": 3,
|
| 1065 |
+
"chars": 1511,
|
| 1066 |
+
"utf8_bytes": 1671,
|
| 1067 |
+
"tokens": 488,
|
| 1068 |
+
"chars_per_token": 3.096311475409836,
|
| 1069 |
+
"tokens_per_char": 0.3229649238914626,
|
| 1070 |
+
"bytes_per_token": 3.4241803278688523,
|
| 1071 |
+
"tokens_per_byte": 0.29204069419509276,
|
| 1072 |
+
"round_trip": true
|
| 1073 |
+
},
|
| 1074 |
+
{
|
| 1075 |
+
"code": "ood",
|
| 1076 |
+
"autonym": "Oʼodham ha-ñeʼokĭ, Oʼodham ñiok",
|
| 1077 |
+
"spanish_name": "Pápago-Pima",
|
| 1078 |
+
"inali_name": "pápago",
|
| 1079 |
+
"english_name": "Tohono O’odham",
|
| 1080 |
+
"samples": 3,
|
| 1081 |
+
"chars": 1511,
|
| 1082 |
+
"utf8_bytes": 1539,
|
| 1083 |
+
"tokens": 493,
|
| 1084 |
+
"chars_per_token": 3.0649087221095335,
|
| 1085 |
+
"tokens_per_char": 0.32627399073461283,
|
| 1086 |
+
"bytes_per_token": 3.1217038539553754,
|
| 1087 |
+
"tokens_per_byte": 0.3203378817413905,
|
| 1088 |
+
"round_trip": true
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"code": "pia",
|
| 1092 |
+
"autonym": "Oob No'ok",
|
| 1093 |
+
"spanish_name": "Pima Bajo",
|
| 1094 |
+
"inali_name": "pima del sur",
|
| 1095 |
+
"english_name": "Pima Bajo",
|
| 1096 |
+
"samples": 4,
|
| 1097 |
+
"chars": 2015,
|
| 1098 |
+
"utf8_bytes": 2189,
|
| 1099 |
+
"tokens": 554,
|
| 1100 |
+
"chars_per_token": 3.637184115523466,
|
| 1101 |
+
"tokens_per_char": 0.2749379652605459,
|
| 1102 |
+
"bytes_per_token": 3.9512635379061374,
|
| 1103 |
+
"tokens_per_byte": 0.25308359981726813,
|
| 1104 |
+
"round_trip": true
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"code": "pls",
|
| 1108 |
+
"autonym": "Ngigua",
|
| 1109 |
+
"spanish_name": "Popoloca de San Marcos Tlacoyalco",
|
| 1110 |
+
"inali_name": "popoloca del norte",
|
| 1111 |
+
"english_name": "San Marcos Tlacoyalco Popoloca",
|
| 1112 |
+
"samples": 1,
|
| 1113 |
+
"chars": 503,
|
| 1114 |
+
"utf8_bytes": 513,
|
| 1115 |
+
"tokens": 156,
|
| 1116 |
+
"chars_per_token": 3.2243589743589745,
|
| 1117 |
+
"tokens_per_char": 0.3101391650099404,
|
| 1118 |
+
"bytes_per_token": 3.2884615384615383,
|
| 1119 |
+
"tokens_per_byte": 0.30409356725146197,
|
| 1120 |
+
"round_trip": true
|
| 1121 |
+
},
|
| 1122 |
+
{
|
| 1123 |
+
"code": "poi",
|
| 1124 |
+
"autonym": "Nuntajɨ̱yi",
|
| 1125 |
+
"spanish_name": "Popoluca de la Sierra",
|
| 1126 |
+
"inali_name": "popoluca de la Sierra",
|
| 1127 |
+
"english_name": "Highland Popoluca",
|
| 1128 |
+
"samples": 3,
|
| 1129 |
+
"chars": 1511,
|
| 1130 |
+
"utf8_bytes": 1764,
|
| 1131 |
+
"tokens": 435,
|
| 1132 |
+
"chars_per_token": 3.4735632183908045,
|
| 1133 |
+
"tokens_per_char": 0.2878888153540701,
|
| 1134 |
+
"bytes_per_token": 4.055172413793104,
|
| 1135 |
+
"tokens_per_byte": 0.2465986394557823,
|
| 1136 |
+
"round_trip": true
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"code": "knj",
|
| 1140 |
+
"autonym": "K'anjob'al",
|
| 1141 |
+
"spanish_name": "Kaanjobal",
|
| 1142 |
+
"inali_name": "Q’anjob’al",
|
| 1143 |
+
"english_name": "Akateko",
|
| 1144 |
+
"samples": 3,
|
| 1145 |
+
"chars": 1511,
|
| 1146 |
+
"utf8_bytes": 1635,
|
| 1147 |
+
"tokens": 476,
|
| 1148 |
+
"chars_per_token": 3.1743697478991595,
|
| 1149 |
+
"tokens_per_char": 0.31502316346790205,
|
| 1150 |
+
"bytes_per_token": 3.4348739495798317,
|
| 1151 |
+
"tokens_per_byte": 0.291131498470948,
|
| 1152 |
+
"round_trip": true
|
| 1153 |
+
},
|
| 1154 |
+
{
|
| 1155 |
+
"code": "mhc",
|
| 1156 |
+
"autonym": "Mocho'",
|
| 1157 |
+
"spanish_name": "Motozintleco",
|
| 1158 |
+
"inali_name": "mocho’",
|
| 1159 |
+
"english_name": "Mocho",
|
| 1160 |
+
"samples": 4,
|
| 1161 |
+
"chars": 2015,
|
| 1162 |
+
"utf8_bytes": 2021,
|
| 1163 |
+
"tokens": 470,
|
| 1164 |
+
"chars_per_token": 4.287234042553192,
|
| 1165 |
+
"tokens_per_char": 0.23325062034739455,
|
| 1166 |
+
"bytes_per_token": 4.3,
|
| 1167 |
+
"tokens_per_byte": 0.23255813953488372,
|
| 1168 |
+
"round_trip": true
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"code": "kek",
|
| 1172 |
+
"autonym": "Q'eqchi'",
|
| 1173 |
+
"spanish_name": "Q'eqchi'",
|
| 1174 |
+
"inali_name": "Q’eqchi’",
|
| 1175 |
+
"english_name": "Q’eqchi’",
|
| 1176 |
+
"samples": 3,
|
| 1177 |
+
"chars": 1511,
|
| 1178 |
+
"utf8_bytes": 1736,
|
| 1179 |
+
"tokens": 519,
|
| 1180 |
+
"chars_per_token": 2.9113680154142583,
|
| 1181 |
+
"tokens_per_char": 0.343481138318994,
|
| 1182 |
+
"bytes_per_token": 3.3448940269749516,
|
| 1183 |
+
"tokens_per_byte": 0.298963133640553,
|
| 1184 |
+
"round_trip": true
|
| 1185 |
+
},
|
| 1186 |
+
{
|
| 1187 |
+
"code": "sei",
|
| 1188 |
+
"autonym": "Cmiique Iitom",
|
| 1189 |
+
"spanish_name": "Seri",
|
| 1190 |
+
"inali_name": "seri",
|
| 1191 |
+
"english_name": "Seri",
|
| 1192 |
+
"samples": 3,
|
| 1193 |
+
"chars": 1511,
|
| 1194 |
+
"utf8_bytes": 1531,
|
| 1195 |
+
"tokens": 298,
|
| 1196 |
+
"chars_per_token": 5.070469798657718,
|
| 1197 |
+
"tokens_per_char": 0.1972203838517538,
|
| 1198 |
+
"bytes_per_token": 5.1375838926174495,
|
| 1199 |
+
"tokens_per_byte": 0.1946440235140431,
|
| 1200 |
+
"round_trip": true
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"code": "thh",
|
| 1204 |
+
"autonym": "ralámuli raicha",
|
| 1205 |
+
"spanish_name": "Tarahumara del Norte",
|
| 1206 |
+
"inali_name": "tarahumara del norte",
|
| 1207 |
+
"english_name": "Tarahumara, Northern",
|
| 1208 |
+
"samples": 3,
|
| 1209 |
+
"chars": 1511,
|
| 1210 |
+
"utf8_bytes": 1676,
|
| 1211 |
+
"tokens": 473,
|
| 1212 |
+
"chars_per_token": 3.1945031712473573,
|
| 1213 |
+
"tokens_per_char": 0.3130377233620119,
|
| 1214 |
+
"bytes_per_token": 3.543340380549683,
|
| 1215 |
+
"tokens_per_byte": 0.2822195704057279,
|
| 1216 |
+
"round_trip": true
|
| 1217 |
+
},
|
| 1218 |
+
{
|
| 1219 |
+
"code": "tar",
|
| 1220 |
+
"autonym": "Ralámuli raꞌíchala",
|
| 1221 |
+
"spanish_name": "Tarahumara Central",
|
| 1222 |
+
"inali_name": "tarahumara del centro",
|
| 1223 |
+
"english_name": "Central Tarahumara",
|
| 1224 |
+
"samples": 3,
|
| 1225 |
+
"chars": 1511,
|
| 1226 |
+
"utf8_bytes": 1585,
|
| 1227 |
+
"tokens": 511,
|
| 1228 |
+
"chars_per_token": 2.9569471624266144,
|
| 1229 |
+
"tokens_per_char": 0.3381866313699537,
|
| 1230 |
+
"bytes_per_token": 3.101761252446184,
|
| 1231 |
+
"tokens_per_byte": 0.322397476340694,
|
| 1232 |
+
"round_trip": true
|
| 1233 |
+
},
|
| 1234 |
+
{
|
| 1235 |
+
"code": "tsz",
|
| 1236 |
+
"autonym": "P’urhe, P’urhépecha",
|
| 1237 |
+
"spanish_name": "Purépecha",
|
| 1238 |
+
"inali_name": "purépecha",
|
| 1239 |
+
"english_name": "Purepecha",
|
| 1240 |
+
"samples": 3,
|
| 1241 |
+
"chars": 1511,
|
| 1242 |
+
"utf8_bytes": 1590,
|
| 1243 |
+
"tokens": 413,
|
| 1244 |
+
"chars_per_token": 3.6585956416464893,
|
| 1245 |
+
"tokens_per_char": 0.27332892124420916,
|
| 1246 |
+
"bytes_per_token": 3.8498789346246975,
|
| 1247 |
+
"tokens_per_byte": 0.259748427672956,
|
| 1248 |
+
"round_trip": true
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"code": "tee",
|
| 1252 |
+
"autonym": "Lhima'alh'ama'",
|
| 1253 |
+
"spanish_name": "Tepehua de Huehuetla",
|
| 1254 |
+
"inali_name": "tepehua del sur",
|
| 1255 |
+
"english_name": "Huehuetla Tepehua",
|
| 1256 |
+
"samples": 4,
|
| 1257 |
+
"chars": 2015,
|
| 1258 |
+
"utf8_bytes": 2052,
|
| 1259 |
+
"tokens": 522,
|
| 1260 |
+
"chars_per_token": 3.8601532567049808,
|
| 1261 |
+
"tokens_per_char": 0.25905707196029776,
|
| 1262 |
+
"bytes_per_token": 3.9310344827586206,
|
| 1263 |
+
"tokens_per_byte": 0.2543859649122807,
|
| 1264 |
+
"round_trip": true
|
| 1265 |
+
},
|
| 1266 |
+
{
|
| 1267 |
+
"code": "tpp",
|
| 1268 |
+
"autonym": "Lhichiwin",
|
| 1269 |
+
"spanish_name": "Tepehua de Pisaflores",
|
| 1270 |
+
"inali_name": "tepehua del norte",
|
| 1271 |
+
"english_name": "Pisaflores Tepehua",
|
| 1272 |
+
"samples": 4,
|
| 1273 |
+
"chars": 2015,
|
| 1274 |
+
"utf8_bytes": 2099,
|
| 1275 |
+
"tokens": 498,
|
| 1276 |
+
"chars_per_token": 4.046184738955823,
|
| 1277 |
+
"tokens_per_char": 0.24714640198511167,
|
| 1278 |
+
"bytes_per_token": 4.214859437751004,
|
| 1279 |
+
"tokens_per_byte": 0.2372558361124345,
|
| 1280 |
+
"round_trip": true
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"code": "ntp",
|
| 1284 |
+
"autonym": "Oodamicʌdʌ",
|
| 1285 |
+
"spanish_name": "Tepehuano del Norte",
|
| 1286 |
+
"inali_name": "tepehuano del norte",
|
| 1287 |
+
"english_name": "Northern Tepehuan",
|
| 1288 |
+
"samples": 3,
|
| 1289 |
+
"chars": 1511,
|
| 1290 |
+
"utf8_bytes": 1638,
|
| 1291 |
+
"tokens": 417,
|
| 1292 |
+
"chars_per_token": 3.6235011990407675,
|
| 1293 |
+
"tokens_per_char": 0.2759761747187293,
|
| 1294 |
+
"bytes_per_token": 3.9280575539568345,
|
| 1295 |
+
"tokens_per_byte": 0.25457875457875456,
|
| 1296 |
+
"round_trip": true
|
| 1297 |
+
},
|
| 1298 |
+
{
|
| 1299 |
+
"code": "tla",
|
| 1300 |
+
"autonym": "",
|
| 1301 |
+
"spanish_name": "Tepehuano del Suroeste",
|
| 1302 |
+
"inali_name": "tepehuano del sur alto",
|
| 1303 |
+
"english_name": "Tepehuan, Southwestern",
|
| 1304 |
+
"samples": 2,
|
| 1305 |
+
"chars": 1007,
|
| 1306 |
+
"utf8_bytes": 1216,
|
| 1307 |
+
"tokens": 294,
|
| 1308 |
+
"chars_per_token": 3.425170068027211,
|
| 1309 |
+
"tokens_per_char": 0.2919563058589871,
|
| 1310 |
+
"bytes_per_token": 4.136054421768708,
|
| 1311 |
+
"tokens_per_byte": 0.24177631578947367,
|
| 1312 |
+
"round_trip": true
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"code": "stp",
|
| 1316 |
+
"autonym": "Oꞌdam",
|
| 1317 |
+
"spanish_name": "Tepehuano del Sureste",
|
| 1318 |
+
"inali_name": "tepehuano del sur bajo",
|
| 1319 |
+
"english_name": "Southeastern Tepehuan",
|
| 1320 |
+
"samples": 3,
|
| 1321 |
+
"chars": 1511,
|
| 1322 |
+
"utf8_bytes": 1570,
|
| 1323 |
+
"tokens": 583,
|
| 1324 |
+
"chars_per_token": 2.5917667238421958,
|
| 1325 |
+
"tokens_per_char": 0.385837193911317,
|
| 1326 |
+
"bytes_per_token": 2.692967409948542,
|
| 1327 |
+
"tokens_per_byte": 0.37133757961783437,
|
| 1328 |
+
"round_trip": true
|
| 1329 |
+
},
|
| 1330 |
+
{
|
| 1331 |
+
"code": "ocu",
|
| 1332 |
+
"autonym": "pjiekak'joo",
|
| 1333 |
+
"spanish_name": "Tlahuica",
|
| 1334 |
+
"inali_name": "tlahuica",
|
| 1335 |
+
"english_name": "Tlahuica",
|
| 1336 |
+
"samples": 3,
|
| 1337 |
+
"chars": 1511,
|
| 1338 |
+
"utf8_bytes": 1644,
|
| 1339 |
+
"tokens": 398,
|
| 1340 |
+
"chars_per_token": 3.7964824120603016,
|
| 1341 |
+
"tokens_per_char": 0.2634017207147584,
|
| 1342 |
+
"bytes_per_token": 4.130653266331659,
|
| 1343 |
+
"tokens_per_byte": 0.24209245742092458,
|
| 1344 |
+
"round_trip": true
|
| 1345 |
+
},
|
| 1346 |
+
{
|
| 1347 |
+
"code": "tcf",
|
| 1348 |
+
"autonym": "Mè'phàà Mañuwìín",
|
| 1349 |
+
"spanish_name": "Tlapaneco a de Malinaltepec",
|
| 1350 |
+
"inali_name": "tlapaneco central bajo",
|
| 1351 |
+
"english_name": "Malinaltepec Me’phaa",
|
| 1352 |
+
"samples": 2,
|
| 1353 |
+
"chars": 1007,
|
| 1354 |
+
"utf8_bytes": 1248,
|
| 1355 |
+
"tokens": 428,
|
| 1356 |
+
"chars_per_token": 2.352803738317757,
|
| 1357 |
+
"tokens_per_char": 0.42502482621648463,
|
| 1358 |
+
"bytes_per_token": 2.9158878504672896,
|
| 1359 |
+
"tokens_per_byte": 0.34294871794871795,
|
| 1360 |
+
"round_trip": true
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"code": "tpx",
|
| 1364 |
+
"autonym": "Meꞌpa̱a̱ Wíꞌi̱i̱n",
|
| 1365 |
+
"spanish_name": "Tlapaneco de Acatepec",
|
| 1366 |
+
"inali_name": "tlapaneco del suroeste",
|
| 1367 |
+
"english_name": "Acatepec Me’phaa",
|
| 1368 |
+
"samples": 3,
|
| 1369 |
+
"chars": 1511,
|
| 1370 |
+
"utf8_bytes": 1695,
|
| 1371 |
+
"tokens": 589,
|
| 1372 |
+
"chars_per_token": 2.565365025466893,
|
| 1373 |
+
"tokens_per_char": 0.38980807412309726,
|
| 1374 |
+
"bytes_per_token": 2.877758913412564,
|
| 1375 |
+
"tokens_per_byte": 0.34749262536873154,
|
| 1376 |
+
"round_trip": true
|
| 1377 |
+
},
|
| 1378 |
+
{
|
| 1379 |
+
"code": "tpl",
|
| 1380 |
+
"autonym": "Meꞌpa̱a̱ Wíꞌi̱i̱n",
|
| 1381 |
+
"spanish_name": "Tlapaneco de Tacoapa",
|
| 1382 |
+
"inali_name": "tlapaneco del centro",
|
| 1383 |
+
"english_name": "Tlacoapa Me’phaa",
|
| 1384 |
+
"samples": 3,
|
| 1385 |
+
"chars": 1511,
|
| 1386 |
+
"utf8_bytes": 1948,
|
| 1387 |
+
"tokens": 628,
|
| 1388 |
+
"chars_per_token": 2.406050955414013,
|
| 1389 |
+
"tokens_per_char": 0.41561879549966907,
|
| 1390 |
+
"bytes_per_token": 3.1019108280254777,
|
| 1391 |
+
"tokens_per_byte": 0.32238193018480493,
|
| 1392 |
+
"round_trip": true
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"code": "toj",
|
| 1396 |
+
"autonym": "Tojol-ab'al",
|
| 1397 |
+
"spanish_name": "Tojolabal",
|
| 1398 |
+
"inali_name": "tojolabal",
|
| 1399 |
+
"english_name": "Tojolabal",
|
| 1400 |
+
"samples": 4,
|
| 1401 |
+
"chars": 2015,
|
| 1402 |
+
"utf8_bytes": 2196,
|
| 1403 |
+
"tokens": 529,
|
| 1404 |
+
"chars_per_token": 3.8090737240075616,
|
| 1405 |
+
"tokens_per_char": 0.26253101736972706,
|
| 1406 |
+
"bytes_per_token": 4.151228733459357,
|
| 1407 |
+
"tokens_per_byte": 0.24089253187613843,
|
| 1408 |
+
"round_trip": true
|
| 1409 |
+
},
|
| 1410 |
+
{
|
| 1411 |
+
"code": "toc",
|
| 1412 |
+
"autonym": "Tutunakú",
|
| 1413 |
+
"spanish_name": "Totonaco de Coyutla",
|
| 1414 |
+
"inali_name": "totonaco central del norte",
|
| 1415 |
+
"english_name": "Coyutla Totonac",
|
| 1416 |
+
"samples": 1,
|
| 1417 |
+
"chars": 503,
|
| 1418 |
+
"utf8_bytes": 505,
|
| 1419 |
+
"tokens": 209,
|
| 1420 |
+
"chars_per_token": 2.4066985645933014,
|
| 1421 |
+
"tokens_per_char": 0.415506958250497,
|
| 1422 |
+
"bytes_per_token": 2.416267942583732,
|
| 1423 |
+
"tokens_per_byte": 0.41386138613861384,
|
| 1424 |
+
"round_trip": true
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"code": "tqt",
|
| 1428 |
+
"autonym": "Xinulajgsípij Totonaco",
|
| 1429 |
+
"spanish_name": "Totonaco del Cerro Xinolatépetl",
|
| 1430 |
+
"inali_name": "totonaco del cerro Xinolatépetl",
|
| 1431 |
+
"english_name": "Totonaco del cerro Xinolatépetl",
|
| 1432 |
+
"samples": 4,
|
| 1433 |
+
"chars": 2015,
|
| 1434 |
+
"utf8_bytes": 2057,
|
| 1435 |
+
"tokens": 606,
|
| 1436 |
+
"chars_per_token": 3.325082508250825,
|
| 1437 |
+
"tokens_per_char": 0.3007444168734491,
|
| 1438 |
+
"bytes_per_token": 3.3943894389438944,
|
| 1439 |
+
"tokens_per_byte": 0.29460379192999514,
|
| 1440 |
+
"round_trip": true
|
| 1441 |
+
},
|
| 1442 |
+
{
|
| 1443 |
+
"code": "top",
|
| 1444 |
+
"autonym": "Lichiwin Tutunaku, Tutunakú",
|
| 1445 |
+
"spanish_name": "Totonaco de Papantla",
|
| 1446 |
+
"inali_name": "totonaco de la costa",
|
| 1447 |
+
"english_name": "Papantla Totonac",
|
| 1448 |
+
"samples": 5,
|
| 1449 |
+
"chars": 2519,
|
| 1450 |
+
"utf8_bytes": 2582,
|
| 1451 |
+
"tokens": 574,
|
| 1452 |
+
"chars_per_token": 4.388501742160279,
|
| 1453 |
+
"tokens_per_char": 0.2278682016673283,
|
| 1454 |
+
"bytes_per_token": 4.498257839721254,
|
| 1455 |
+
"tokens_per_byte": 0.22230828814872192,
|
| 1456 |
+
"round_trip": true
|
| 1457 |
+
},
|
| 1458 |
+
{
|
| 1459 |
+
"code": "tos",
|
| 1460 |
+
"autonym": "Totonaco",
|
| 1461 |
+
"spanish_name": "Totonaco de la Sierra",
|
| 1462 |
+
"inali_name": "totonaco central del sur",
|
| 1463 |
+
"english_name": "Highland Totonac",
|
| 1464 |
+
"samples": 4,
|
| 1465 |
+
"chars": 2015,
|
| 1466 |
+
"utf8_bytes": 2088,
|
| 1467 |
+
"tokens": 588,
|
| 1468 |
+
"chars_per_token": 3.42687074829932,
|
| 1469 |
+
"tokens_per_char": 0.29181141439205954,
|
| 1470 |
+
"bytes_per_token": 3.5510204081632653,
|
| 1471 |
+
"tokens_per_byte": 0.28160919540229884,
|
| 1472 |
+
"round_trip": true
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"code": "trc",
|
| 1476 |
+
"autonym": "Xnaꞌánj nu̱ꞌ",
|
| 1477 |
+
"spanish_name": "Triqui de Copala",
|
| 1478 |
+
"inali_name": "triqui de San Juan Copala",
|
| 1479 |
+
"english_name": "Copala Triqui",
|
| 1480 |
+
"samples": 3,
|
| 1481 |
+
"chars": 1511,
|
| 1482 |
+
"utf8_bytes": 1791,
|
| 1483 |
+
"tokens": 305,
|
| 1484 |
+
"chars_per_token": 4.954098360655737,
|
| 1485 |
+
"tokens_per_char": 0.20185307743216413,
|
| 1486 |
+
"bytes_per_token": 5.872131147540983,
|
| 1487 |
+
"tokens_per_byte": 0.1702959240647683,
|
| 1488 |
+
"round_trip": true
|
| 1489 |
+
},
|
| 1490 |
+
{
|
| 1491 |
+
"code": "trs",
|
| 1492 |
+
"autonym": "Nânj Nï̀nꞌïn",
|
| 1493 |
+
"spanish_name": "Triqui de Chicahuaxtla",
|
| 1494 |
+
"inali_name": "triqui de la alta",
|
| 1495 |
+
"english_name": "Chicahuaxtla Triqui",
|
| 1496 |
+
"samples": 5,
|
| 1497 |
+
"chars": 2519,
|
| 1498 |
+
"utf8_bytes": 2774,
|
| 1499 |
+
"tokens": 789,
|
| 1500 |
+
"chars_per_token": 3.1926489226869457,
|
| 1501 |
+
"tokens_per_char": 0.3132195315601429,
|
| 1502 |
+
"bytes_per_token": 3.5158428390367553,
|
| 1503 |
+
"tokens_per_byte": 0.28442682047584716,
|
| 1504 |
+
"round_trip": true
|
| 1505 |
+
},
|
| 1506 |
+
{
|
| 1507 |
+
"code": "tzh",
|
| 1508 |
+
"autonym": "Bats'il k'op",
|
| 1509 |
+
"spanish_name": "Tzeltal",
|
| 1510 |
+
"inali_name": "tseltal del occidente",
|
| 1511 |
+
"english_name": "Tzeltal",
|
| 1512 |
+
"samples": 2,
|
| 1513 |
+
"chars": 1007,
|
| 1514 |
+
"utf8_bytes": 1102,
|
| 1515 |
+
"tokens": 236,
|
| 1516 |
+
"chars_per_token": 4.266949152542373,
|
| 1517 |
+
"tokens_per_char": 0.23435948361469713,
|
| 1518 |
+
"bytes_per_token": 4.669491525423729,
|
| 1519 |
+
"tokens_per_byte": 0.21415607985480944,
|
| 1520 |
+
"round_trip": true
|
| 1521 |
+
},
|
| 1522 |
+
{
|
| 1523 |
+
"code": "tzo",
|
| 1524 |
+
"autonym": "Bats'i k'op",
|
| 1525 |
+
"spanish_name": "Tsotsil",
|
| 1526 |
+
"inali_name": "tsotsil del centro",
|
| 1527 |
+
"english_name": "Tsotsil",
|
| 1528 |
+
"samples": 4,
|
| 1529 |
+
"chars": 2015,
|
| 1530 |
+
"utf8_bytes": 2199,
|
| 1531 |
+
"tokens": 413,
|
| 1532 |
+
"chars_per_token": 4.878934624697337,
|
| 1533 |
+
"tokens_per_char": 0.20496277915632755,
|
| 1534 |
+
"bytes_per_token": 5.324455205811138,
|
| 1535 |
+
"tokens_per_byte": 0.18781264211005003,
|
| 1536 |
+
"round_trip": true
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"code": "yaq",
|
| 1540 |
+
"autonym": "Yo'em noki",
|
| 1541 |
+
"spanish_name": "Yaqui",
|
| 1542 |
+
"inali_name": "yaqui",
|
| 1543 |
+
"english_name": "Yaqui",
|
| 1544 |
+
"samples": 4,
|
| 1545 |
+
"chars": 2015,
|
| 1546 |
+
"utf8_bytes": 2110,
|
| 1547 |
+
"tokens": 535,
|
| 1548 |
+
"chars_per_token": 3.7663551401869158,
|
| 1549 |
+
"tokens_per_char": 0.2655086848635236,
|
| 1550 |
+
"bytes_per_token": 3.94392523364486,
|
| 1551 |
+
"tokens_per_byte": 0.25355450236966826,
|
| 1552 |
+
"round_trip": true
|
| 1553 |
+
},
|
| 1554 |
+
{
|
| 1555 |
+
"code": "zaq",
|
| 1556 |
+
"autonym": "Tisa",
|
| 1557 |
+
"spanish_name": "Zapoteco de Aloápam",
|
| 1558 |
+
"inali_name": "zapoteco de San Miguel Aloápam",
|
| 1559 |
+
"english_name": "Aloápam Zapotec",
|
| 1560 |
+
"samples": 3,
|
| 1561 |
+
"chars": 1511,
|
| 1562 |
+
"utf8_bytes": 1675,
|
| 1563 |
+
"tokens": 446,
|
| 1564 |
+
"chars_per_token": 3.3878923766816142,
|
| 1565 |
+
"tokens_per_char": 0.29516876240900064,
|
| 1566 |
+
"bytes_per_token": 3.7556053811659194,
|
| 1567 |
+
"tokens_per_byte": 0.2662686567164179,
|
| 1568 |
+
"round_trip": true
|
| 1569 |
+
},
|
| 1570 |
+
{
|
| 1571 |
+
"code": "zaa",
|
| 1572 |
+
"autonym": "Titsaꞌ",
|
| 1573 |
+
"spanish_name": "Zapoteco de la Sierra de Juárez",
|
| 1574 |
+
"inali_name": "zapoteco serrano, bajo",
|
| 1575 |
+
"english_name": "Sierra de Juárez Zapotec",
|
| 1576 |
+
"samples": 3,
|
| 1577 |
+
"chars": 1511,
|
| 1578 |
+
"utf8_bytes": 1620,
|
| 1579 |
+
"tokens": 462,
|
| 1580 |
+
"chars_per_token": 3.2705627705627704,
|
| 1581 |
+
"tokens_per_char": 0.3057577763070814,
|
| 1582 |
+
"bytes_per_token": 3.5064935064935066,
|
| 1583 |
+
"tokens_per_byte": 0.2851851851851852,
|
| 1584 |
+
"round_trip": true
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"code": "zpr",
|
| 1588 |
+
"autonym": "Diste’",
|
| 1589 |
+
"spanish_name": "Zapoteco de Santiago Xanica",
|
| 1590 |
+
"inali_name": "zapoteco de la Sierra sur, del sureste bajo",
|
| 1591 |
+
"english_name": "Santiago Xanica Zapotec",
|
| 1592 |
+
"samples": 3,
|
| 1593 |
+
"chars": 1511,
|
| 1594 |
+
"utf8_bytes": 1589,
|
| 1595 |
+
"tokens": 505,
|
| 1596 |
+
"chars_per_token": 2.992079207920792,
|
| 1597 |
+
"tokens_per_char": 0.33421575115817337,
|
| 1598 |
+
"bytes_per_token": 3.1465346534653467,
|
| 1599 |
+
"tokens_per_byte": 0.31780994336060414,
|
| 1600 |
+
"round_trip": true
|
| 1601 |
+
},
|
| 1602 |
+
{
|
| 1603 |
+
"code": "zai",
|
| 1604 |
+
"autonym": "Diidxazá",
|
| 1605 |
+
"spanish_name": "Zapoteco del Istmo",
|
| 1606 |
+
"inali_name": "zapoteco de la planicie costera",
|
| 1607 |
+
"english_name": "Isthmus Zapotec",
|
| 1608 |
+
"samples": 4,
|
| 1609 |
+
"chars": 2015,
|
| 1610 |
+
"utf8_bytes": 2234,
|
| 1611 |
+
"tokens": 482,
|
| 1612 |
+
"chars_per_token": 4.180497925311204,
|
| 1613 |
+
"tokens_per_char": 0.2392059553349876,
|
| 1614 |
+
"bytes_per_token": 4.634854771784233,
|
| 1615 |
+
"tokens_per_byte": 0.21575649059982094,
|
| 1616 |
+
"round_trip": true
|
| 1617 |
+
},
|
| 1618 |
+
{
|
| 1619 |
+
"code": "zoc",
|
| 1620 |
+
"autonym": "Tzunitzame",
|
| 1621 |
+
"spanish_name": "Zoque de Copainalá",
|
| 1622 |
+
"inali_name": "zoque del centro",
|
| 1623 |
+
"english_name": "Copainalá Zoque",
|
| 1624 |
+
"samples": 4,
|
| 1625 |
+
"chars": 2015,
|
| 1626 |
+
"utf8_bytes": 2235,
|
| 1627 |
+
"tokens": 666,
|
| 1628 |
+
"chars_per_token": 3.0255255255255253,
|
| 1629 |
+
"tokens_per_char": 0.33052109181141437,
|
| 1630 |
+
"bytes_per_token": 3.355855855855856,
|
| 1631 |
+
"tokens_per_byte": 0.2979865771812081,
|
| 1632 |
+
"round_trip": true
|
| 1633 |
+
},
|
| 1634 |
+
{
|
| 1635 |
+
"code": "zoq",
|
| 1636 |
+
"autonym": "",
|
| 1637 |
+
"spanish_name": "Zoque de Tabasco",
|
| 1638 |
+
"inali_name": "zoque del este",
|
| 1639 |
+
"english_name": "Zoque, Tabasco",
|
| 1640 |
+
"samples": 3,
|
| 1641 |
+
"chars": 1511,
|
| 1642 |
+
"utf8_bytes": 1605,
|
| 1643 |
+
"tokens": 423,
|
| 1644 |
+
"chars_per_token": 3.5721040189125297,
|
| 1645 |
+
"tokens_per_char": 0.2799470549305096,
|
| 1646 |
+
"bytes_per_token": 3.7943262411347516,
|
| 1647 |
+
"tokens_per_byte": 0.2635514018691589,
|
| 1648 |
+
"round_trip": true
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"code": "zor",
|
| 1652 |
+
"autonym": "Otetzame",
|
| 1653 |
+
"spanish_name": "Zoque de Rayón",
|
| 1654 |
+
"inali_name": "zoque del norte bajo",
|
| 1655 |
+
"english_name": "Rayón Zoque",
|
| 1656 |
+
"samples": 3,
|
| 1657 |
+
"chars": 1511,
|
| 1658 |
+
"utf8_bytes": 1712,
|
| 1659 |
+
"tokens": 523,
|
| 1660 |
+
"chars_per_token": 2.8891013384321225,
|
| 1661 |
+
"tokens_per_char": 0.34612839179351423,
|
| 1662 |
+
"bytes_per_token": 3.273422562141491,
|
| 1663 |
+
"tokens_per_byte": 0.3054906542056075,
|
| 1664 |
+
"round_trip": true
|
| 1665 |
+
},
|
| 1666 |
+
{
|
| 1667 |
+
"code": "zos",
|
| 1668 |
+
"autonym": "Otetzame",
|
| 1669 |
+
"spanish_name": "Zoque de Francisco León",
|
| 1670 |
+
"inali_name": "zoque del noroeste",
|
| 1671 |
+
"english_name": "Francisco León Zoque",
|
| 1672 |
+
"samples": 3,
|
| 1673 |
+
"chars": 1511,
|
| 1674 |
+
"utf8_bytes": 1590,
|
| 1675 |
+
"tokens": 495,
|
| 1676 |
+
"chars_per_token": 3.0525252525252524,
|
| 1677 |
+
"tokens_per_char": 0.32759761747187294,
|
| 1678 |
+
"bytes_per_token": 3.212121212121212,
|
| 1679 |
+
"tokens_per_byte": 0.3113207547169811,
|
| 1680 |
+
"round_trip": true
|
| 1681 |
+
},
|
| 1682 |
+
{
|
| 1683 |
+
"code": "zoh",
|
| 1684 |
+
"autonym": "Tzunitzame",
|
| 1685 |
+
"spanish_name": "Zoque de Chimalapa",
|
| 1686 |
+
"inali_name": "zoque del oeste",
|
| 1687 |
+
"english_name": "Chimalapa Zoque",
|
| 1688 |
+
"samples": 4,
|
| 1689 |
+
"chars": 2015,
|
| 1690 |
+
"utf8_bytes": 2225,
|
| 1691 |
+
"tokens": 651,
|
| 1692 |
+
"chars_per_token": 3.0952380952380953,
|
| 1693 |
+
"tokens_per_char": 0.3230769230769231,
|
| 1694 |
+
"bytes_per_token": 3.4178187403993854,
|
| 1695 |
+
"tokens_per_byte": 0.29258426966292134,
|
| 1696 |
+
"round_trip": true
|
| 1697 |
+
}
|
| 1698 |
+
]
|