Upload folder using huggingface_hub

adapted_tokenizers/added-opt-amh/opt_100-add_full-amh-opt/added_tokens.json

@@ -0,0 +1,102 @@
+{
+  " ለ": 50313,
+  " ላይ": 50358,
+  " መ": 50287,
+  " ማ": 50343,
+  " ም": 50344,
+  " ሰ": 50349,
+  " ሲ": 50354,
+  " ስ": 50340,
+  " በ": 50271,
+  " ባ": 50359,
+  " ብ": 50351,
+  " ተ": 50301,
+  " ነ": 50308,
+  " ነው": 50346,
+  " አ": 50274,
+  " እ": 50280,
+  " እና": 50361,
+  " እን": 50304,
+  " እንደ": 50350,
+  " ከ": 50299,
+  " ወ": 50324,
+  " ው": 50353,
+  " የ": 50267,
+  " የሚ": 50332,
+  " የተ": 50342,
+  " ያ": 50327,
+  " ይ": 50319,
+  " ግ": 50355,
+  "ሁ": 50363,
+  "ህ": 50318,
+  "ሆ": 50328,
+  "ለ": 50275,
+  "ሉ": 50315,
+  "ላ": 50290,
+  "ል": 50270,
+  "መ": 50282,
+  "ሚ": 50298,
+  "ማ": 50296,
+  "ም": 50272,
+  "ሞ": 50360,
+  "ረ": 50285,
+  "ሩ": 50337,
+  "ሪ": 50302,
+  "ራ": 50288,
+  "ር": 50269,
+  "ሮ": 50335,
+  "ሰ": 50300,
+  "ሳ": 50321,
+  "ስ": 50273,
+  "ቀ": 50309,
+  "ቃ": 50347,
+  "ቅ": 50325,
+  "በ": 50292,
+  "ባ": 50297,
+  "ብ": 50295,
+  "ተ": 50277,
+  "ቱ": 50330,
+  "ታ": 50293,
+  "ት": 50266,
+  "ቶ": 50336,
+  "ቸ": 50306,
+  "ቸው": 50310,
+  "ች": 50276,
+  "ነ": 50294,
+  "ነት": 50364,
+  "ኑ": 50356,
+  "ና": 50278,
+  "ን": 50265,
+  "ኛ": 50338,
+  "አ": 50305,
+  "ከ": 50317,
+  "ካ": 50316,
+  "ክ": 50303,
+  "ወ": 50323,
+  "ዊ": 50345,
+  "ዋ": 50314,
+  "ዋል": 50348,
+  "ው": 50268,
+  "ዎች": 50333,
+  "ዚ": 50362,
+  "ዝ": 50357,
+  "የ": 50329,
+  "ያ": 50279,
+  "ይ": 50281,
+  "ዮ": 50352,
+  "ደ": 50284,
+  "ዲ": 50341,
+  "ዳ": 50307,
+  "ድ": 50289,
+  "ገ": 50286,
+  "ጋ": 50331,
+  "ግ": 50291,
+  "ጠ": 50320,
+  "ጣ": 50334,
+  "ጥ": 50311,
+  "ፈ": 50326,
+  "ፍ": 50312,
+  "፡": 50322,
+  "።": 50283,
+  "፣": 50339
+}

adapted_tokenizers/added-opt-amh/opt_100-add_full-amh-opt/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

adapted_tokenizers/added-opt-amh/opt_100-add_full-amh-opt/tokenizer_config.json

@@ -0,0 +1,830 @@
+{
+  "add_bos_token": true,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50265": {
+      "content": "ን",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50266": {
+      "content": "ት",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50267": {
+      "content": " የ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50268": {
+      "content": "ው",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50269": {
+      "content": "ር",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50270": {
+      "content": "ል",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50271": {
+      "content": " በ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50272": {
+      "content": "ም",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50273": {
+      "content": "ስ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50274": {
+      "content": " አ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50275": {
+      "content": "ለ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50276": {
+      "content": "ች",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50277": {
+      "content": "ተ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50278": {
+      "content": "ና",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50279": {
+      "content": "ያ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50280": {
+      "content": " እ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50281": {
+      "content": "ይ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50282": {
+      "content": "መ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50283": {
+      "content": "።",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50284": {
+      "content": "ደ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50285": {
+      "content": "ረ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50286": {
+      "content": "ገ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50287": {
+      "content": " መ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50288": {
+      "content": "ራ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50289": {
+      "content": "ድ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50290": {
+      "content": "ላ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50291": {
+      "content": "ግ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50292": {
+      "content": "በ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50293": {
+      "content": "ታ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50294": {
+      "content": "ነ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50295": {
+      "content": "ብ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50296": {
+      "content": "ማ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50297": {
+      "content": "ባ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50298": {
+      "content": "ሚ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50299": {
+      "content": " ከ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50300": {
+      "content": "ሰ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50301": {
+      "content": " ተ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50302": {
+      "content": "ሪ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50303": {
+      "content": "ክ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50304": {
+      "content": " እን",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50305": {
+      "content": "አ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50306": {
+      "content": "ቸ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50307": {
+      "content": "ዳ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50308": {
+      "content": " ነ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50309": {
+      "content": "ቀ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50310": {
+      "content": "ቸው",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50311": {
+      "content": "ጥ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50312": {
+      "content": "ፍ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50313": {
+      "content": " ለ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50314": {
+      "content": "ዋ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50315": {
+      "content": "ሉ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50316": {
+      "content": "ካ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50317": {
+      "content": "ከ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50318": {
+      "content": "ህ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50319": {
+      "content": " ይ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50320": {
+      "content": "ጠ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50321": {
+      "content": "ሳ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50322": {
+      "content": "፡",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50323": {
+      "content": "ወ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50324": {
+      "content": " ወ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50325": {
+      "content": "ቅ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50326": {
+      "content": "ፈ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50327": {
+      "content": " ያ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50328": {
+      "content": "ሆ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50329": {
+      "content": "የ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50330": {
+      "content": "ቱ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50331": {
+      "content": "ጋ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50332": {
+      "content": " የሚ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50333": {
+      "content": "ዎች",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50334": {
+      "content": "ጣ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50335": {
+      "content": "ሮ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50336": {
+      "content": "ቶ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50337": {
+      "content": "ሩ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50338": {
+      "content": "ኛ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50339": {
+      "content": "፣",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50340": {
+      "content": " ስ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50341": {
+      "content": "ዲ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50342": {
+      "content": " የተ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50343": {
+      "content": " ማ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50344": {
+      "content": " ም",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50345": {
+      "content": "ዊ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50346": {
+      "content": " ነው",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50347": {
+      "content": "ቃ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50348": {
+      "content": "ዋል",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50349": {
+      "content": " ሰ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50350": {
+      "content": " እንደ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50351": {
+      "content": " ብ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50352": {
+      "content": "ዮ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50353": {
+      "content": " ው",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50354": {
+      "content": " ሲ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50355": {
+      "content": " ግ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50356": {
+      "content": "ኑ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50357": {
+      "content": "ዝ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50358": {
+      "content": " ላይ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50359": {
+      "content": " ባ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50360": {
+      "content": "ሞ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50361": {
+      "content": " እና",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50362": {
+      "content": "ዚ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50363": {
+      "content": "ሁ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50364": {
+      "content": "ነት",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "</s>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "errors": "replace",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "</s>"
+}

adapted_tokenizers/added-opt-amh/opt_1000-add_full-amh-opt/added_tokens.json

@@ -0,0 +1,1002 @@
+{
+  " \n": 50900,
+  "  ": 51256,
+  " avai": 50808,
+  " ሀ": 50712,
+  " ሁ": 50428,
+  " ሁለት": 50920,
+  " ሁሉ": 50864,
+  " ሁኔ": 50662,
+  " ሁኔታ": 50689,
+  " ሂ": 51164,
+  " ሃ": 50567,
+  " ህ": 50528,
+  " ሆ": 50478,
+  " ሆነ": 50959,
+  " ሆኖ": 50940,
+  " ለ": 50313,
+  " ለመ": 50452,
+  " ለማ": 50490,
+  " ለተ": 50987,
+  " ለአ": 50829,
+  " ሊ": 50463,
+  " ላ": 50882,
+  " ላይ": 50358,
+  " ሌ": 50593,
+  " ሌላ": 51103,
+  " ሌሎች": 50916,
+  " ል": 50426,
+  " ልዩ": 51204,
+  " ልጅ": 51140,
+  " ልጆች": 50826,
+  " ሐ": 50866,
+  " ሕ": 50493,
+  " መ": 50287,
+  " መሆኑ": 50616,
+  " መሆኑን": 50749,
+  " መል": 50747,
+  " መረጃ": 50957,
+  " መር": 51229,
+  " መሰ": 50972,
+  " መስ": 50690,
+  " መቀ": 51161,
+  " መብ": 50867,
+  " መን": 50630,
+  " መንገድ": 51046,
+  " መንግሥ": 50491,
+  " መንግሥታት": 51263,
+  " መንግሥት": 50565,
+  " መካ": 50670,
+  " መካከል": 50724,
+  " መግለጫ": 50878,
+  " መጠ": 50795,
+  " ሙ": 50623,
+  " ሚ": 50439,
+  " ሚሊዮን": 51102,
+  " ሚኒ": 50599,
+  " ሚኒስት": 50701,
+  " ሚኒስትር": 50885,
+  " ማ": 50343,
+  " ማለት": 51118,
+  " ማስ": 50952,
+  " ማዕ": 51037,
+  " ሜ": 50993,
+  " ም": 50344,
+  " ምር": 50970,
+  " ምርጫ": 51008,
+  " ምሳሌ": 51010,
+  " ምን": 50857,
+  " ምንም": 51108,
+  " ምክ": 50523,
+  " ምክር": 51110,
+  " ምክንያ": 50674,
+  " ምክንያት": 50773,
+  " ሞ": 50718,
+  " ሠ": 50859,
+  " ሥ": 50498,
+  " ሥራ": 50819,
+  " ሥር": 51030,
+  " ረ": 50911,
+  " ሩ": 50980,
+  " ሪ": 50903,
+  " ራ": 50856,
+  " ር": 51159,
+  " ሰ": 50349,
+  " ሰው": 50763,
+  " ሰዎች": 50499,
+  " ሱ": 51160,
+  " ሲ": 50354,
+  " ሲሆን": 50534,
+  " ሲሉ": 50717,
+  " ሲል": 50998,
+  " ሲያ": 51064,
+  " ሳ": 50469,
+  " ሳይ": 50777,
+  " ሴ": 50722,
+  " ስ": 50340,
+  " ስለ": 50544,
+  " ስም": 50818,
+  " ስር": 51183,
+  " ስቴ": 50779,
+  " ስቴትስ": 50850,
+  " ሶ": 51074,
+  " ሺ": 50884,
+  " ሺህ": 51089,
+  " ሽ": 50973,
+  " ቀ": 50407,
+  " ቀን": 50825,
+  " ቁ": 50588,
+  " ቁጥር": 50950,
+  " ቃ": 50744,
+  " ቃል": 51000,
+  " ቅ": 50589,
+  " ቆ": 50797,
+  " ቆይ": 51242,
+  " በ": 50271,
+  " በላይ": 50727,
+  " በሌ": 51109,
+  " በመ": 50394,
+  " በሚ": 50512,
+  " በሚል": 51258,
+  " በማ": 50500,
+  " በማለት": 51149,
+  " በም": 50834,
+  " በር": 50738,
+  " በርካታ": 50995,
+  " በሰ": 50803,
+  " በስ": 51011,
+  " በቀ": 50891,
+  " በበ": 51063,
+  " በተ": 50402,
+  " በተለ": 51131,
+  " በተጨማሪ": 51119,
+  " በት": 50948,
+  " በኋላ": 50545,
+  " በአ": 50405,
+  " በኢትዮጵያ": 50967,
+  " በእ": 50704,
+  " በኩ": 51111,
+  " በኩል": 51184,
+  " በወ": 51101,
+  " በዚህ": 50682,
+  " በግ": 51221,
+  " በጣም": 51214,
+  " በፊት": 50789,
+  " ቡ": 50659,
+  " ቡድን": 51054,
+  " ቢ": 50479,
+  " ቢሆን": 51156,
+  " ባ": 50359,
+  " ባለ": 50460,
+  " ባለሥልጣ": 51157,
+  " ባለፈው": 50985,
+  " ባይ": 51071,
+  " ቤ": 50420,
+  " ቤተ": 50843,
+  " ቤት": 50552,
+  " ብ": 50351,
+  " ብለዋል": 50625,
+  " ብለው": 51252,
+  " ብሎ": 51153,
+  " ብሏል": 51122,
+  " ብቻ": 50823,
+  " ብዙ": 50725,
+  " ቦ": 50783,
+  " ቦታ": 51097,
+  " ተ": 50301,
+  " ተመ": 50810,
+  " ተሰ": 51195,
+  " ተቀ": 50988,
+  " ተቃ": 51082,
+  " ተቋ": 50994,
+  " ተብ": 50784,
+  " ተና": 50626,
+  " ተናግ": 50715,
+  " ተናግረዋል": 50824,
+  " ተከ": 50610,
+  " ተከት": 50936,
+  " ተከትሎ": 50960,
+  " ተወ": 50913,
+  " ተገ": 50696,
+  " ተጠ": 50992,
+  " ተፈ": 51113,
+  " ታ": 50453,
+  " ቴ": 51174,
+  " ት": 50385,
+  " ትምህርት": 51259,
+  " ቻ": 51099,
+  " ች": 50745,
+  " ኃ": 50543,
+  " ኃላፊ": 51065,
+  " ኃይ": 50675,
+  " ኃይሎች": 51155,
+  " ነ": 50308,
+  " ነበር": 50456,
+  " ነዋ": 51135,
+  " ነው": 50346,
+  " ነገ": 51100,
+  " ነገር": 50575,
+  " ና": 50532,
+  " ናቸው": 50641,
+  " ን": 50562,
+  " ንግ": 51093,
+  " አ": 50274,
+  " አሁን": 51014,
+  " አለ": 50598,
+  " አል": 50526,
+  " አመ": 50766,
+  " አማ": 50947,
+  " አሜሪካ": 50928,
+  " አም": 50709,
+  " አር": 51223,
+  " አሳ": 51005,
+  " አስ": 50383,
+  " አስተ": 50635,
+  " አስተዳ": 51126,
+  " አስታው": 50929,
+  " አቀ": 50692,
+  " አቀፍ": 51194,
+  " አበ": 50886,
+  " አበባ": 51022,
+  " አባ": 50628,
+  " አባላት": 51179,
+  " አብ": 50748,
+  " አቶ": 50770,
+  " አን": 50503,
+  " አንዱ": 51200,
+  " አንድ": 50592,
+  " አካ": 50570,
+  " አካባቢ": 50781,
+  " አክ": 51251,
+  " አው": 51035,
+  " አይ": 50509,
+  " አይደ": 51045,
+  " አይደለም": 51226,
+  " አዲስ": 50977,
+  " አድ": 50871,
+  " አድ���": 51220,
+  " አገ": 50530,
+  " አገልግ": 51085,
+  " አገራት": 50974,
+  " አገር": 51125,
+  " አፍሪካ": 51004,
+  " ኢ": 50579,
+  " ኢትዮጵያ": 50574,
+  " ኤ": 50636,
+  " እ": 50280,
+  " እር": 50660,
+  " እርምጃ": 51248,
+  " እስ": 50516,
+  " እስከ": 50740,
+  " እና": 50361,
+  " እን": 50304,
+  " እንደ": 50350,
+  " እንደሆነ": 50925,
+  " እንደሚ": 50487,
+  " እንደሚያ": 51134,
+  " እንደተ": 51032,
+  " እንዲ": 50389,
+  " እንዲሁ": 50760,
+  " እንዲሁም": 50817,
+  " እንዲያ": 50965,
+  " እንዳ": 50507,
+  " እንዳይ": 51255,
+  " እየ": 50474,
+  " እየተ": 50646,
+  " እያ": 50671,
+  " እጅ": 51219,
+  " ኦ": 50791,
+  " ከ": 50299,
+  " ከመ": 50708,
+  " ከሚ": 51040,
+  " ከተ": 50454,
+  " ከተማ": 50645,
+  " ከአ": 50605,
+  " ከእ": 51129,
+  " ከዚህ": 50849,
+  " ከፍ": 50606,
+  " ከፍተኛ": 50703,
+  " ኩ": 51241,
+  " ኪ": 50896,
+  " ካ": 50488,
+  " ኬ": 51254,
+  " ክ": 50381,
+  " ክል": 50624,
+  " ክልል": 50733,
+  " ክት": 51136,
+  " ክፍ": 50679,
+  " ክፍል": 51239,
+  " ኮ": 50535,
+  " ኮሚ": 51018,
+  " ወ": 50324,
+  " ወር": 50860,
+  " ወቅ": 50751,
+  " ወቅት": 50807,
+  " ወታደ": 50898,
+  " ወን": 50930,
+  " ወይም": 50772,
+  " ወደ": 50422,
+  " ዋ": 50540,
+  " ዋና": 50869,
+  " ው": 50353,
+  " ውሳኔ": 51201,
+  " ውስጥ": 50409,
+  " ውድ": 51167,
+  " ውጤ": 51257,
+  " ዓ": 50378,
+  " ዓለም": 50927,
+  " ዓመ": 50497,
+  " ዓመታት": 50870,
+  " ዓመት": 50665,
+  " ዕ": 50601,
+  " ዘ": 50435,
+  " ዘመ": 51068,
+  " ዘመን": 51112,
+  " ዘገባ": 51218,
+  " ዙ": 51148,
+  " ዛ": 50793,
+  " ዛሬ": 50907,
+  " ዜ": 50853,
+  " ዝ": 50613,
+  " የ": 50267,
+  " የህ": 51055,
+  " የሆነ": 50888,
+  " የሆኑ": 51073,
+  " የሕ": 51036,
+  " የመ": 50425,
+  " የመጀመሪያ": 51202,
+  " የሚ": 50332,
+  " የሚል": 51207,
+  " የሚያ": 50539,
+  " የሚገኙ": 51249,
+  " የማ": 50597,
+  " የም": 50538,
+  " የሰ": 50750,
+  " የሰብ": 51215,
+  " የስ": 50956,
+  " የቀ": 50746,
+  " የበ": 51117,
+  " የተ": 50342,
+  " የተሰ": 50958,
+  " የተባ": 50729,
+  " የታ": 51003,
+  " የት": 50805,
+  " የነ": 50559,
+  " የነበረ": 50832,
+  " የአ": 50375,
+  " የአማርኛ": 51059,
+  " የአሜሪካ": 51026,
+  " የኢ": 51171,
+  " የኢትዮጵያ": 50688,
+  " የኤ": 51222,
+  " የእ": 50657,
+  " የኮ": 50949,
+  " የወ": 50622,
+  " የው": 50830,
+  " የውጭ": 51186,
+  " የዓለም": 51050,
+  " የዩ": 50883,
+  " የድም": 51017,
+  " የድምፅ": 51217,
+  " የግ": 51137,
+  " የፈ": 51244,
+  " የፖ": 51165,
+  " ዩ": 50687,
+  " ያ": 50327,
+  " ያለ": 50726,
+  " ያለው": 50653,
+  " ያሉ": 50953,
+  " ያል": 51033,
+  " ያስ": 50815,
+  " ያዳም": 51175,
+  " ያዳምጡ": 51181,
+  " ይ": 50319,
+  " ይህ": 50465,
+  " ይህን": 51150,
+  " ይላሉ": 51176,
+  " ይች": 50756,
+  " ይችላሉ": 51178,
+  " ይችላል": 51247,
+  " ደ": 50379,
+  " ደረጃ": 51066,
+  " ደግሞ": 50580,
+  " ዲ": 50917,
+  " ዳ": 50732,
+  " ድ": 50382,
+  " ድም": 50915,
+  " ድረስ": 50962,
+  " ድርጅ": 50661,
+  " ድርጅት": 50861,
+  " ድን": 51213,
+  " ድጋ": 51210,
+  " ዶ": 50619,
+  " ጀ": 50648,
+  " ጀምሮ": 51147,
+  " ጆ": 51170,
+  " ገ": 50397,
+  " ገል": 50652,
+  " ገልጸ": 51240,
+  " ጉ": 50450,
+  " ጉዳ": 50524,
+  " ጉዳይ": 50739,
+  " ጊዜ": 50521,
+  " ጋ": 50436,
+  " ጋር": 50473,
+  " ግ": 50355,
+  " ግለ": 51185,
+  " ግን": 50442,
+  " ግጭ": 51208,
+  " ጎ": 50837,
+  " ጠ": 50477,
+  " ጠቅ": 50771,
+  " ጠቅላይ": 50964,
+  " ጣ": 51009,
+  " ጥ": 50377,
+  " ጥቃ": 50638,
+  " ጥቃት": 50802,
+  " ጥያቄ": 51120,
+  " ጦር": 50684,
+  " ጦርነት": 50963,
+  " ጨ": 50672,
+  " ጨምሮ": 51133,
+  " ጭ": 51127,
+  " ጽ": 51078,
+  " ፈ": 50571,
+  " ፊ": 51006,
+  " ፋይ": 50939,
+  " ፋይል": 51023,
+  " ፍ": 50518,
+  " ፍርድ": 51158,
+  " ፓ": 50699,
+  " ፓርቲ": 51031,
+  " ፕ": 50502,
+  " ፕሬ": 50576,
+  " ፕሬዚ": 50846,
+  " ፕሬዚዳንት": 51139,
+  " ፕሬዝ": 50946,
+  " ፕሮ": 51193,
+  " ፖ": 50649,
+  " ፖሊስ": 51166,
+  " ፣": 51013,
+  " “": 50529,
+  "lable": 50809,
+  "vai": 50806,
+  "ሀ": 50728,
+  "ሁ": 50363,
+  "ሁለት": 51192,
+  "ሁን": 50587,
+  "ሂ": 51162,
+  "ሃ": 50466,
+  "ሄ": 50501,
+  "ህ": 50318,
+  "ህል": 51027,
+  "ሆ": 50328,
+  "ሆነ": 50482,
+  "ሆኑ": 50423,
+  "ሆና": 51061,
+  "ሆን": 50411,
+  "ለ": 50275,
+  "ለሁ": 50955,
+  "ለም": 50437,
+  "ለቱ": 50969,
+  "ለቲ": 50919,
+  "ለቲካ": 51020,
+  "ለት": 50440,
+  "ለች": 50510,
+  "ለን": 50865,
+  "ለዋል": 50546,
+  "ለው": 50372,
+  "ለያ": 50683,
+  "ለያዩ": 50858,
+  "ሉ": 50315,
+  "ሉም": 51146,
+  "ሉት": 50577,
+  "ሊ": 50365,
+  "ሊስ": 50838,
+  "ሊያ": 50922,
+  "ሊዮን": 50868,
+  "ላ": 50290,
+  "ላለ": 51145,
+  "ላሉ": 50644,
+  "ላል": 50537,
+  "ላማ": 50836,
+  "ላም": 50895,
+  "ላት": 50611,
+  "ላቸው": 50566,
+  "ላቸውን": 51191,
+  "ላን": 51188,
+  "ላንድ": 51238,
+  "ላይ": 50481,
+  "ላፊ": 50876,
+  "ሌ": 50392,
+  "ል": 50270,
+  "ልም": 50877,
+  "ልቅ": 51130,
+  "ልክ": 50663,
+  "ልግ": 50978,
+  "ልጣ": 50594,
+  "ሎ": 50384,
+  "ሎት": 51038,
+  "ሎች": 50480,
+  "ሏ": 50564,
+  "ሏል": 50643,
+  "ሐ": 50640,
+  "ሓ": 51209,
+  "ሔ": 50782,
+  "ሕ": 50504,
+  "መ": 50282,
+  "መለ": 50585,
+  "መረ": 51052,
+  "መራ": 50633,
+  "መር": 50984,
+  "መስ": 51075,
+  "መን": 50615,
+  "መው": 50906,
+  "መድ": 50944,
+  "መጣ": 51261,
+  "ሙ": 50416,
+  "ሙያ": 51212,
+  "ሚ": 50298,
+  "ሚያ": 50775,
+  "ማ": 50296,
+  "ማሪ": 50553,
+  "ማር": 50694,
+  "ማርኛ": 50937,
+  "ማት": 50873,
+  "ማን": 51123,
+  "ማይ": 51182,
+  "ሜ": 50406,
+  "ሜሪካ": 50536,
+  "ሜን": 51002,
+  "ም": 50272,
+  "ምህ": 50734,
+  "ምህርት": 50942,
+  "ምር": 51154,
+  "ምሮ": 50651,
+  "ምነት": 51039,
+  "ምና": 50759,
+  "ምን": 50910,
+  "ምንት": 51095,
+  "ምጃ": 51151,
+  "ምፕ": 50893,
+  "ሞ": 50360,
+  "ሞች": 50816,
+  "ሞክ": 51047,
+  "ሞክራ": 51250,
+  "ሟ": 50839,
+  "ሠ": 50578,
+  "ሣ": 50761,
+  "ሥ": 50368,
+  "ሥልጣ": 50945,
+  "ሥራ": 50941,
+  "ረ": 50285,
+  "ረር": 51088,
+  "ረስ": 50549,
+  "ረብ": 51235,
+  "ረት": 50494,
+  "ረን": 50897,
+  "ረዋል": 50668,
+  "ረው": 50600,
+  "ረዳ": 50788,
+  "ረጃ": 50603,
+  "ረጋ": 50844,
+  "ሩ": 50337,
+  "ሩሲያ": 51096,
+  "ሩት": 50800,
+  "ሩን": 50828,
+  "ሪ": 50302,
+  "ሪካ": 50434,
+  "ሪክ": 50840,
+  "ሪዎች": 50714,
+  "ሪያ": 50424,
+  "ራ": 50288,
+  "ራሉ": 50753,
+  "ራል": 50681,
+  "ራምፕ": 51180,
+  "ራት": 50468,
+  "ራቸው": 50794,
+  "ራን": 50986,
+  "ራዊ": 50522,
+  "ራው": 51245,
+  "ሬ": 50367,
+  "ር": 50269,
+  "ርስ": 50612,
+  "ርስቲ": 51072,
+  "ርቲ": 50845,
+  "ርት": 50511,
+  "ርትራ": 51053,
+  "ርክ": 51048,
+  "ርዝ": 51012,
+  "ርያ": 50933,
+  "ርድ": 50711,
+  "ርጅ": 50607,
+  "ርጫ": 50752,
+  "ሮ": 50335,
+  "ሮች": 50542,
+  "ሮና": 50968,
+  "ሮናቫይረስ": 51106,
+  "ሯ": 50678,
+  "ሯል": 50982,
+  "ሰ": 50300,
+  "ሰራ": 51098,
+  "ሰቡ": 51234,
+  "ሰብ": 50555,
+  "ሰው": 50669,
+  "ሱ": 50401,
+  "ሱን": 51057,
+  "ሲ": 50404,
+  "ሲያ": 50695,
+  "ሳ": 50321,
+  "ሳሌ": 50799,
+  "ሳል": 51114,
+  "ሳት": 50966,
+  "ሳኔ": 51116,
+  "ሳይ": 50720,
+  "ሴ": 50527,
+  "ስ": 50273,
+  "ስራ": 51262,
+  "ስር": 51230,
+  "ስተ": 50551,
+  "ስታ": 51083,
+  "ስት": 50410,
+  "ስጥ": 50399,
+  "ስፋ": 51173,
+  "ሶ": 50513,
+  "ሷ": 50971,
+  "ሸ": 50515,
+  "ሸን": 51211,
+  "ሺ": 50976,
+  "ሻ": 50461,
+  "ሽ": 50374,
+  "ሽን": 50943,
+  "ሾ": 51198,
+  "ቀ": 50309,
+  "ቀረ": 51190,
+  "ቀር": 50938,
+  "ቀዋል": 51199,
+  "ቀው": 50863,
+  "ቁ": 50433,
+  "ቂ": 50505,
+  "ቃ": 50347,
+  "ቃል": 51216,
+  "ቄ": 50813,
+  "ቅ": 50325,
+  "ቅም": 50848,
+  "ቅር": 50654,
+  "ቆ": 50418,
+  "ቆጣ": 50961,
+  "ቋ": 50455,
+  "ቋል": 50894,
+  "በ": 50292,
+  "በረ": 50467,
+  "በሩ": 50558,
+  "በሩት": 50890,
+  "በር": 50376,
+  "በት": 50412,
+  "በው": 51087,
+  "ቡ": 50386,
+  "ቡብ": 50852,
+  "ቢ": 50371,
+  "ቢሲ": 51025,
+  "ቢያ": 50735,
+  "ባ": 50297,
+  "ባለ": 51196,
+  "ባል": 50909,
+  "ባቢ": 50583,
+  "ባት": 50572,
+  "ባቸው": 50608,
+  "ባይ": 50924,
+  "ቤ": 50484,
+  "ቤት": 50999,
+  "ብ": 50295,
+  "ብረ": 50921,
+  "ብረት": 50932,
+  "ብር": 50719,
+  "ቦ": 50462,
+  "ቦች": 50814,
+  "ቧ": 50975,
+  "ቧል": 51228,
+  "ቨ": 50983,
+  "ቪ": 50604,
+  "ቪድ": 51197,
+  "ቫ": 50658,
+  "ቫይ": 50821,
+  "ቫይረስ": 51060,
+  "ቭ": 51224,
+  "ተ": 50277,
+  "ተር": 50673,
+  "ተን": 51124,
+  "ተኛ": 50443,
+  "ተኞች": 50908,
+  "ተዋል": 50642,
+  "ተው": 50614,
+  "ቱ": 50330,
+  "ቱን": 50531,
+  "ቲ": 50391,
+  "ታ": 50293,
+  "ታል": 50563,
+  "ታት": 50506,
+  "ታቸው": 50596,
+  "ታቸውን": 50768,
+  "ታወ": 50560,
+  "ታዊ": 50798,
+  "ታው": 50591,
+  "ታደ": 50757,
+  "ቴ": 50457,
+  "ት": 50266,
+  "ትል": 51168,
+  "ትስ": 50758,
+  "ትና": 50847,
+  "ትን": 50517,
+  "ቶ": 50336,
+  "ቶች": 50388,
+  "ቶችን": 50872,
+  "ቷ": 50495,
+  "ቷል": 50631,
+  "ቸ": 50306,
+  "ቸዋል": 50979,
+  "ቸው": 50310,
+  "ቸውን": 50414,
+  "ቹ": 50441,
+  "ቻ": 50398,
+  "ቻቸው": 51028,
+  "ቻይና": 51233,
+  "ች": 50276,
+  "ችል": 51051,
+  "ችን": 50471,
+  "ችው": 50889,
+  "ኃ": 51132,
+  "ኅ": 50705,
+  "ነ": 50294,
+  "ነሳ": 51041,
+  "ነስ": 51203,
+  "ነበረ": 50990,
+  "ነቱ": 51058,
+  "ነት": 50364,
+  "ነው": 50737,
+  "ነዚህ": 50902,
+  "ነገ": 51225,
+  "ነጋ": 51084,
+  "ኑ": 50356,
+  "ኒ": 50387,
+  "ና": 50278,
+  "ናል": 50595,
+  "ናት": 50548,
+  "ናይት": 50706,
+  "ናይትድ": 50716,
+  "ናገ": 50676,
+  "ኔ": 50403,
+  "ን": 50265,
+  "ንም": 50485,
+  "ንስ": 50655,
+  "ንቀ": 51232,
+  "ንት": 50446,
+  "ንነት": 51090,
+  "ንን": 50707,
+  "ንዘ": 50931,
+  "ንዘብ": 51077,
+  "ንያ": 50519,
+  "ንዳ": 50912,
+  "ንድ": 50380,
+  "ንግ": 50369,
+  "ንግሥ": 50449,
+  "ንግሥት": 51152,
+  "ኖ": 50373,
+  "ኖር": 51070,
+  "ኖች": 50786,
+  "ኗ": 51121,
+  "ኘ": 50769,
+  "ኙ": 50792,
+  "ኛ": 50338,
+  "ኛው": 50637,
+  "ኝ": 50396,
+  "ኞ": 50470,
+  "ኞች": 50584,
+  "አ": 50305,
+  "ኢ": 51079,
+  "ኢትዮጵያ": 51007,
+  "ኤ": 50472,
+  "ኤል": 51069,
+  "እ": 50370,
+  "ኦ": 50935,
+  "ከ": 50317,
+  "ከላ": 50801,
+  "ከል": 50557,
+  "ከር": 51260,
+  "ከሰ": 51044,
+  "ከተ": 50686,
+  "ከት": 51092,
+  "ኩ": 50483,
+  "ኪ": 50590,
+  "ካ": 50316,
+  "ካሄ": 50710,
+  "ካባቢ": 51206,
+  "ካታ": 50851,
+  "ኬ": 50991,
+  "ክ": 50303,
+  "ክል": 50713,
+  "ክምና": 51142,
+  "ክሬ": 50862,
+  "ክሬን": 51067,
+  "ክስ": 51062,
+  "ክት": 50765,
+  "ኮ": 50476,
+  "ኳ": 50774,
+  "ወ": 50323,
+  "ወሰ": 50827,
+  "ወጣ": 50804,
+  "ዉ": 51042,
+  "ዊ": 50345,
+  "ዋ": 50314,
+  "ዋል": 50348,
+  "ዋን": 51246,
+  "ው": 50268,
+  "ውሮ": 50698,
+  "ውሮፓ": 50934,
+  "ውስ": 51253,
+  "ውን": 50395,
+  "ውያን": 50741,
+  "ዎ": 50541,
+  "ዎቹ": 50702,
+  "ዎች": 50333,
+  "ዎችን": 50650,
+  "ዓ": 50427,
+  "ዓለም": 50691,
+  "ዓት": 50926,
+  "ዓዊ": 51104,
+  "ዕ": 50444,
+  "ዕራ": 51081,
+  "ዘ": 50366,
+  "ዘጋ": 51086,
+  "ዙ": 50492,
+  "ዚ": 50362,
+  "ዚህ": 50429,
+  "ዚያ": 50787,
+  "ዛ": 50417,
+  "ዛት": 50904,
+  "ዜ": 50430,
+  "ዜጠ": 51189,
+  "ዝ": 50357,
+  "ዝብ": 50743,
+  "ዞ": 50776,
+  "ዥ": 50918,
+  "የ": 50329,
+  "የር": 50754,
+  "የት": 50811,
+  "ዩ": 50393,
+  "ያ": 50279,
+  "ያቄ": 51080,
+  "ያን": 50458,
+  "ያዘ": 50693,
+  "ያያዘ": 50833,
+  "ዬ": 50905,
+  "ይ": 50281,
+  "ይም": 50629,
+  "ይት": 50556,
+  "ይና": 50796,
+  "ይወ": 50736,
+  "ይወት": 51115,
+  "ዮ": 50352,
+  "ዮች": 50892,
+  "ዮን": 50730,
+  "ደ": 50284,
+  "ደም": 50822,
+  "ደረ": 50421,
+  "ደረሰ": 51172,
+  "ደረገ": 50667,
+  "ደረገው": 51231,
+  "ደረጉ": 50887,
+  "ደር": 50486,
+  "ደቡብ": 51107,
+  "ደት": 51243,
+  "ደን": 50820,
+  "ደው": 50881,
+  "ደጋ": 50841,
+  "ዱ": 50448,
+  "ዲ": 50341,
+  "ዲስ": 50656,
+  "ዲያ": 51091,
+  "ዳ": 50307,
+  "ዳም": 51034,
+  "ዳታ": 51029,
+  "ዳን": 50617,
+  "ዳንት": 50677,
+  "ዴ": 50569,
+  "ድ": 50289,
+  "ድም": 50697,
+  "ድሞ": 50954,
+  "ድረ": 50618,
+  "ድረግ": 50875,
+  "ድር": 50621,
+  "ድን": 50647,
+  "ዶ": 50508,
+  "ዶች": 51143,
+  "ጀ": 50419,
+  "ጀመ": 50554,
+  "ጀመሪያ": 50780,
+  "ጁ": 51076,
+  "ጂ": 50632,
+  "ጃ": 50447,
+  "ጄ": 51144,
+  "ጅ": 50451,
+  "ጆ": 50547,
+  "ጆች": 50700,
+  "ገ": 50286,
+  "ገለ": 50880,
+  "ገል": 51169,
+  "ገሪ": 50764,
+  "ገሪቱ": 50874,
+  "ገር": 50432,
+  "ገቡ": 51141,
+  "ገባ": 50581,
+  "ገና": 50923,
+  "ገኘ": 50634,
+  "ገኘው": 50981,
+  "ገኙ": 50627,
+  "ገኛ": 50951,
+  "ገኝ": 50854,
+  "ገው": 51138,
+  "ገደ": 50855,
+  "ገድ": 50755,
+  "ጉ": 50438,
+  "ጊ": 50731,
+  "ጋ": 50331,
+  "ጋት": 50996,
+  "ግ": 50291,
+  "ግለ": 50685,
+  "ግለጫ": 50831,
+  "ግሞ": 50573,
+  "ግራ": 50586,
+  "ግራይ": 50767,
+  "ግር": 50639,
+  "ግባ": 50812,
+  "ግብ": 50785,
+  "ግኘ": 51236,
+  "ጎ": 50514,
+  "ጎች": 51237,
+  "ጓ": 50899,
+  "ጠ": 50320,
+  "ጠረ": 51264,
+  "ጠሩ": 51094,
+  "ጠር": 50778,
+  "ጠቀ": 50914,
+  "ጠበ": 51043,
+  "ጠና": 50879,
+  "ጠው": 51019,
+  "ጡ": 50445,
+  "ጡት": 50989,
+  "ጣ": 50334,
+  "ጣም": 51056,
+  "ጣት": 50901,
+  "ጤ": 50680,
+  "ጤና": 51187,
+  "ጥ": 50311,
+  "ጥር": 50620,
+  "ጥታ": 51021,
+  "ጦ": 51177,
+  "ጦር": 50997,
+  "ጨ": 50464,
+  "ጨማሪ": 50723,
+  "ጨረ": 51128,
+  "ጨረሻ": 51227,
+  "ጪ": 51001,
+  "ጫ": 50475,
+  "ጭ": 50459,
+  "ጵ": 50413,
+  "ጵያ": 50415,
+  "ጸ": 50533,
+  "ጹ": 51163,
+  "ጻ": 50561,
+  "ጽ": 50489,
+  "ጿ": 51015,
+  "ጿል": 51049,
+  "ፀ": 50602,
+  "ፃ": 50721,
+  "ፅ": 50568,
+  "ፈ": 50326,
+  "ፈል": 50762,
+  "ፈው": 50666,
+  "ፈጸ": 51016,
+  "ፉ": 50525,
+  "ፉት": 51105,
+  "ፊ": 50408,
+  "ፊት": 50664,
+  "ፋ": 50390,
+  "ፋት": 51205,
+  "ፌ": 50790,
+  "ፍ": 50312,
+  "ፍሪካ": 50609,
+  "ፍት": 50842,
+  "ፎ": 50835,
+  "ፒ": 50742,
+  "ፓ": 50582,
+  "ፕ": 50496,
+  "ፖ": 50550,
+  "፡": 50322,
+  "፡፡": 50400,
+  "።": 50283,
+  "፣": 50339,
+  "፤": 50431,
+  "፥": 51024,
+  "”": 50520
+}

adapted_tokenizers/added-opt-amh/opt_1000-add_full-amh-opt/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

adapted_tokenizers/added-opt-amh/opt_10000-add_full-amh-opt/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

adapted_tokenizers/added-opt-amh/opt_15000-add_full-amh-opt/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

adapted_tokenizers/added-opt-amh/opt_2000-add_full-amh-opt/added_tokens.json

@@ -0,0 +1,2002 @@
+{
+  " \n": 50900,
+  "  ": 51256,
+  " avai": 50808,
+  " ሀ": 50712,
+  " ሀገ": 51820,
+  " ሁ": 50428,
+  " ሁለተኛ": 51861,
+  " ሁለቱ": 51583,
+  " ሁለት": 50920,
+  " ሁሉ": 50864,
+  " ሁሉም": 51976,
+  " ሁኔ": 50662,
+  " ሁኔታ": 50689,
+  " ሂ": 51164,
+  " ሂደት": 52089,
+  " ሃ": 50567,
+  " ሃገ": 51866,
+  " ሄ": 51532,
+  " ህ": 50528,
+  " ህዝብ": 52193,
+  " ሆ": 50478,
+  " ሆስፒ": 51730,
+  " ሆስፒታል": 52078,
+  " ሆነ": 50959,
+  " ሆነው": 51628,
+  " ሆኖ": 50940,
+  " ሆኖም": 51847,
+  " ለ": 50313,
+  " ለመ": 50452,
+  " ለሚ": 51392,
+  " ለማ": 50490,
+  " ለማስ": 51467,
+  " ለማድረግ": 51836,
+  " ለም": 51705,
+  " ለሰ": 51325,
+  " ለሰይጣንም": 51648,
+  " ለቢቢሲ": 51562,
+  " ለተ": 50987,
+  " ለተጨማሪ": 52007,
+  " ለአ": 50829,
+  " ለእ": 51759,
+  " ለው": 51412,
+  " ለውጥ": 51947,
+  " ለዚህ": 51986,
+  " ሉ": 51852,
+  " ሊ": 50463,
+  " ሊሆኑ": 51505,
+  " ሊሆን": 52173,
+  " ሊቀ": 52008,
+  " ሊያ": 51313,
+  " ላ": 50882,
+  " ላይ": 50358,
+  " ሌ": 50593,
+  " ሌላ": 51103,
+  " ሌሎች": 50916,
+  " ል": 50426,
+  " ልዩ": 51204,
+  " ልጅ": 51140,
+  " ልጆ": 52199,
+  " ልጆች": 50826,
+  " ሐ": 50866,
+  " ሕ": 50493,
+  " ሕዝ": 51864,
+  " ሕዝብ": 51501,
+  " ሕይወ": 52213,
+  " ሕይወት": 52135,
+  " ሕግ": 51374,
+  " መ": 50287,
+  " መሆኑ": 50616,
+  " መሆኑን": 50749,
+  " መሆና": 51356,
+  " መሆናቸውን": 51743,
+  " መለ": 51831,
+  " መል": 50747,
+  " መልኩ": 52242,
+  " መልዕ": 51706,
+  " መመ": 52068,
+  " መም": 52126,
+  " መሠ": 51328,
+  " መሠረት": 51744,
+  " መሣ": 52086,
+  " መሥ": 52156,
+  " መረጃ": 50957,
+  " መሪ": 51302,
+  " መሪዎች": 51723,
+  " መር": 51229,
+  " መሰ": 50972,
+  " መሰረት": 51731,
+  " መሳ": 51624,
+  " መሳሪያ": 51901,
+  " መስ": 50690,
+  " መቀ": 51161,
+  " መብ": 50867,
+  " መብት": 51346,
+  " መብቶች": 52134,
+  " መተ": 52204,
+  " መታ": 51977,
+  " መቶ": 52205,
+  " መን": 50630,
+  " መንገ": 52054,
+  " መንገድ": 51046,
+  " መንግ": 51272,
+  " መንግሥ": 50491,
+  " መንግሥታት": 51263,
+  " መንግሥት": 50565,
+  " መንግስት": 51742,
+  " መኖ": 51882,
+  " መከላከያ": 52100,
+  " መካ": 50670,
+  " መካከል": 50724,
+  " መዋ": 52150,
+  " መው": 51567,
+  " መዝ": 52225,
+  " መድ": 51361,
+  " መድረ": 51780,
+  " መጀመሪያ": 52230,
+  " መገደ": 52171,
+  " መግ": 52096,
+  " መግለጫ": 50878,
+  " መጠ": 50795,
+  " መጠን": 51887,
+  " መጥ": 51860,
+  " መጽ": 52029,
+  " መፈ": 51735,
+  " ሙ": 50623,
+  " ሙሉ": 51441,
+  " ሚ": 50439,
+  " ሚሊ": 52202,
+  " ሚሊዮን": 51102,
+  " ሚኒ": 50599,
+  " ሚኒስቴ": 51529,
+  " ሚኒስቴር": 51656,
+  " ሚኒስት": 50701,
+  " ሚኒስትሩ": 51869,
+  " ሚኒስትር": 50885,
+  " ሚዲያ": 52109,
+  " ማ": 50343,
+  " ማህ": 51868,
+  " ማለ": 51899,
+  " ማለት": 51118,
+  " ማረ": 52219,
+  " ማሳ": 51958,
+  " ማስ": 50952,
+  " ማኅ": 51335,
+  " ማን": 51308,
+  " ማክ": 51823,
+  " ማዕ": 51037,
+  " ማድረግ": 51760,
+  " ሜ": 50993,
+  " ሜትር": 52240,
+  " ም": 50344,
+  " ምላሽ": 51597,
+  " ምልክ": 52185,
+  " ምር": 50970,
+  " ምርመራ": 51410,
+  " ምርጫ": 51008,
+  " ምሳሌ": 51010,
+  " ምስ": 51627,
+  " ምን": 50857,
+  " ምንም": 51108,
+  " ምክ": 50523,
+  " ምክር": 51110,
+  " ምክትል": 51960,
+  " ምክንያ": 50674,
+  " ምክንያት": 50773,
+  " ምግብ": 51870,
+  " ሞ": 50718,
+  " ሠ": 50859,
+  " ሠራ": 51659,
+  " ሠራዊት": 52250,
+  " ሥ": 50498,
+  " ሥራ": 50819,
+  " ሥር": 51030,
+  " ሥርዓት": 52129,
+  " ሥነ": 52163,
+  " ሦስት": 51677,
+  " ረ": 50911,
+  " ሩ": 50980,
+  " ሩሲያ": 51444,
+  " ሪ": 50903,
+  " ሪፖርት": 52062,
+  " ራ": 50856,
+  " ር": 51159,
+  " ሮ": 51383,
+  " ሰ": 50349,
+  " ሰላም": 52079,
+  " ሰብ": 51498,
+  " ሰው": 50763,
+  " ሰዎች": 50499,
+  " ሰዎችን": 51620,
+  " ሰዓት": 51686,
+  " ሰጥ": 51795,
+  " ሱ": 51160,
+  " ሱዳን": 51862,
+  " ሲ": 50354,
+  " ሲሆን": 50534,
+  " ሲሉ": 50717,
+  " ሲል": 50998,
+  " ሲያ": 51064,
+  " ሳ": 50469,
+  " ሳምንት": 51331,
+  " ሳይ": 50777,
+  " ሳይሆን": 51658,
+  " ሴ": 50722,
+  " ሴት": 51652,
+  " ሴቶች": 51456,
+  " ስ": 50340,
+  " ስለ": 50544,
+  " ስለሚ": 52070,
+  " ስለዚህ": 52021,
+  " ስም": 50818,
+  " ስምምነት": 51637,
+  " ስራ": 51777,
+  " ስር": 51183,
+  " ስብ": 51573,
+  " ስብሰባ": 52069,
+  " ስታ": 52223,
+  " ስቴ": 50779,
+  " ስቴትስ": 50850,
+  " ስት": 51555,
+  " ስደ": 51506,
+  " ስደተኞች": 52178,
+  " ስጋት": 51898,
+  " ስፍራ": 52254,
+  " ሶ": 51074,
+  " ሸ": 51445,
+  " ሺ": 50884,
+  " ሺህ": 51089,
+  " ሻ": 51950,
+  " ሽ": 50973,
+  " ቀ": 50407,
+  " ቀር": 51920,
+  " ቀናት": 51319,
+  " ቀን": 50825,
+  " ቀደም": 51324,
+  " ቀጥ": 51877,
+  " ቁ": 50588,
+  " ቁጥር": 50950,
+  " ቃ": 50744,
+  " ቃል": 51000,
+  " ቅ": 50589,
+  " ቆ": 50797,
+  " ቆይ": 51242,
+  " ቋ": 51398,
+  " ቋንቋ": 51626,
+  " በ": 50271,
+  " በሁ": 51803,
+  " በህ": 51754,
+  " በሆነ": 52002,
+  " በላይ": 50727,
+  " በሌ": 51109,
+  " በሌላ": 51695,
+  " በሕ": 51462,
+  " በመ": 50394,
+  " በመሆኑ": 51935,
+  " በመቶ": 51304,
+  " በሙሉ": 51804,
+  " በሚ": 50512,
+  " በሚል": 51258,
+  " በማ": 50500,
+  " በማለት": 51149,
+  " በም": 50834,
+  " በር": 50738,
+  " በርካታ": 50995,
+  " በሰ": 50803,
+  " በሰሜን": 52221,
+  " በሰጡት": 52144,
+  " በስ": 51011,
+  " በሽ": 51311,
+  " በሽታ": 51923,
+  " በቀ": 50891,
+  " በቁ": 51542,
+  " በቁጥጥር": 51896,
+  " በቅር": 51362,
+  " በቅርቡ": 51791,
+  " በበ": 51063,
+  " በበኩ": 51475,
+  " በተ": 50402,
+  " በተለ": 51131,
+  " በተለያዩ": 51663,
+  " በተለይ": 51728,
+  " በተመለከተ": 51738,
+  " በተያያዘ": 52211,
+  " በተጨማሪ": 51119,
+  " በተጨማሪም": 51892,
+  " በታ": 51337,
+  " በት": 50948,
+  " በትግራይ": 51805,
+  " በኋላ": 50545,
+  " በነ": 51544,
+  " በአ": 50405,
+  " በአሁኑ": 51710,
+  " በአሜሪካ": 51828,
+  " በአንድ": 51508,
+  " በአዲስ": 52168,
+  " በአፍሪካ": 52103,
+  " በኢ": 51997,
+  " በኢትዮጵያ": 50967,
+  " በእ": 50704,
+  " በኦ": 52056,
+  " በከፍተኛ": 52121,
+  " በኩ": 51111,
+  " በኩል": 51184,
+  " በኮ": 51411,
+  " በወ": 51101,
+  " በወቅ": 52188,
+  " በዋ": 51801,
+  " በው": 51853,
+  " በዓ": 51809,
+  " በዓለም": 51565,
+  " በዚህ": 50682,
+  " በዚህም": 51848,
+  " በየ": 51296,
+  " በዩ": 51461,
+  " በደቡብ": 51984,
+  " በድ": 51932,
+  " በጉ": 52245,
+  " በግ": 51221,
+  " በጎ": 51951,
+  " በጣም": 51214,
+  " በጥ": 51277,
+  " በፊት": 50789,
+  " በፍ": 51733,
+  " ቡ": 50659,
+  " ቡድ": 51460,
+  " ቡድን": 51054,
+  " ቢ": 50479,
+  " ቢሆን": 51156,
+  " ቢሆንም": 51541,
+  " ቢሮ": 52036,
+  " ባ": 50359,
+  " ባህ": 51810,
+  " ባለ": 50460,
+  " ባለሙያ": 51363,
+  " ባለሙያዎች": 52114,
+  " ባለሥልጣ": 51157,
+  " ባለሥልጣናት": 51593,
+  " ባለስ": 51978,
+  " ባለስልጣ": 52235,
+  " ባለው": 51830,
+  " ባለፈው": 50985,
+  " ባል": 51604,
+  " ባወጣው": 51998,
+  " ባይ": 51071,
+  " ባይደን": 51684,
+  " ቤ": 50420,
+  " ቤተ": 50843,
+  " ቤቱ": 51293,
+  " ቤት": 50552,
+  " ቤቶች": 51666,
+  " ብ": 50351,
+  " ብለዋል": 50625,
+  " ብለው": 51252,
+  " ብሎ": 51153,
+  " ብሏል": 51122,
+  " ብሔ": 51271,
+  " ብሔራዊ": 51779,
+  " ብር": 51314,
+  " ብቻ": 50823,
+  " ብዙ": 50725,
+  " ቦ": 50783,
+  " ቦታ": 51097,
+  " ቪ": 51750,
+  " ቫ": 51454,
+  " ቫይ": 51704,
+  " ተ": 50301,
+  " ተመ": 50810,
+  " ተማሪ": 51396,
+  " ተማሪዎች": 52091,
+  " ተሰ": 51195,
+  " ተስፋ": 51587,
+  " ተቀ": 50988,
+  " ተቃ": 51082,
+  " ተቃዋሚ": 52162,
+  " ተቃውሞ": 51992,
+  " ተቋ": 50994,
+  " ተቋማት": 51989,
+  " ተቋም": 52258,
+  " ተብ": 50784,
+  " ተብሎ": 51291,
+  " ተብሏል": 51493,
+  " ተና": 50626,
+  " ተናግ": 50715,
+  " ተናግረዋል": 50824,
+  " ተከ": 50610,
+  " ተከት": 50936,
+  " ተከትሎ": 50960,
+  " ተወ": 50913,
+  " ተዋ": 51893,
+  " ተገ": 50696,
+  " ተገል": 51556,
+  " ተገልጿል": 51713,
+  " ተግባ": 51473,
+  " ተጠ": 50992,
+  " ተጨማሪ": 51794,
+  " ተጫ": 51990,
+  " ተጫዋ": 52237,
+  " ተፈ": 51113,
+  " ቱ": 51769,
+  " ታ": 50453,
+  " ታሪክ": 51418,
+  " ታይ": 52140,
+  " ታጣቂ": 51837,
+  " ቴ": 51174,
+  " ት": 50385,
+  " ትልቅ": 51918,
+  " ትምህርት": 51259,
+  " ትራምፕ": 51389,
+  " ትና": 51491,
+  " ትናንት": 51539,
+  " ትን": 51815,
+  " ትኩ": 52152,
+  " ትግራይ": 51987,
+  " ቶ": 51993,
+  " ቻ": 51099,
+  " ቻይና": 51476,
+  " ች": 50745,
+  " ችግ": 51922,
+  " ችግር": 51323,
+  " ኃ": 50543,
+  " ኃላፊ": 51065,
+  " ኃይ": 50675,
+  " ኃይል": 51297,
+  " ኃይሎች": 51155,
+  " ኅ": 51691,
+  " ነ": 50308,
+  " ነበረ": 51572,
+  " ነበሩ": 51675,
+  " ነበር": 50456,
+  " ነዋ": 51135,
+  " ነዋሪ": 52203,
+  " ነዋሪዎች": 51590,
+  " ነው": 50346,
+  " ነገ": 51100,
+  " ነገር": 50575,
+  " ነጻ": 51746,
+  " ነፃ": 52016,
+  " ኒ": 51778,
+  " ና": 50532,
+  " ናት": 51931,
+  " ናቸው": 50641,
+  " ን": 50562,
+  " ንብረት": 52220,
+  " ንጉ": 51284,
+  " ንጉሥ": 51953,
+  " ንግ": 51093,
+  " ንግግር": 51790,
+  " ኖ": 52159,
+  " አ": 50274,
+  " አሁን": 51014,
+  " አሁንም": 51821,
+  " አህ": 52175,
+  " አለ": 50598,
+  " አለመ": 51408,
+  " አሉ": 51376,
+  " አላ": 51574,
+  " አል": 50526,
+  " አልተ": 51636,
+  " አመ": 50766,
+  " አመልክ": 51615,
+  " አመራ": 51849,
+  " አማ": 50947,
+  " አማራ": 52256,
+  " አማካ": 51797,
+  " አሜሪካ": 50928,
+  " አም": 50709,
+  " አምስት": 51933,
+  " አምባ": 51721,
+  " አምባሳ": 52200,
+  " አረ": 52124,
+  " አራት": 51824,
+  " አር": 51223,
+  " አሰ": 51614,
+  " አሳ": 51005,
+  " አስ": 50383,
+  " አስተ": 50635,
+  " አስተያ": 51900,
+  " አስተዳ": 51126,
+  " አስተዳደር": 51585,
+  " አስታወቀ": 51927,
+  " አስታው": 50929,
+  " አስታውቀዋል": 52241,
+  " አስታውቋል": 51407,
+  " አስከ": 52165,
+  " አስፈ": 51448,
+  " አስፈላጊ": 52113,
+  " አቀ": 50692,
+  " አቀባይ": 51942,
+  " አቀፍ": 51194,
+  " አቅ": 51395,
+  " አቅር": 51379,
+  " አቋ": 52128,
+  " አበ": 50886,
+  " አበባ": 51022,
+  " አባ": 50628,
+  " አባላት": 51179,
+  " አባል": 51495,
+  " አብ": 50748,
+  " አብዛ": 51907,
+  " አት": 51471,
+  " አቶ": 50770,
+  " አን": 50503,
+  " አንዱ": 51200,
+  " አንዳ": 51455,
+  " አንዳንድ": 51770,
+  " አንድ": 50592,
+  " አካ": 50570,
+  " አካል": 51787,
+  " አካባቢ": 50781,
+  " አካባቢዎች": 51595,
+  " አክ": 51251,
+  " አዋ": 51904,
+  " አው": 51035,
+  " አውሮፕ": 51729,
+  " አየር": 51598,
+  " አያ": 51270,
+  " አይ": 50509,
+  " አይነት": 51623,
+  " አይደ": 51045,
+  " አይደለም": 51226,
+  " አደ": 51919,
+  " አደጋ": 51288,
+  " አዲስ": 50977,
+  " አዳ": 51954,
+  " አድ": 50871,
+  " አድር": 51220,
+  " አድርጎ": 52158,
+  " አገ": 50530,
+  " አገልግ": 51085,
+  " አገልግሎት": 51421,
+  " አገራት": 50974,
+  " አገር": 51125,
+  " አገሮች": 52247,
+  " አጋ": 51278,
+  " አግ": 51855,
+  " አጥ": 51452,
+  " አፈ": 52111,
+  " አፍ": 51764,
+  " አፍሪካ": 51004,
+  " ኡ": 52105,
+  " ኢ": 50579,
+  " ኢትዮጵያ": 50574,
+  " ኢትዮጵያን": 51340,
+  " ኢን": 51446,
+  " ኣ": 51514,
+  " ኤ": 50636,
+  " ኤርትራ": 52215,
+  " እ": 50280,
+  " እር": 50660,
+  " እርምጃ": 51248,
+  " እርዳታ": 51345,
+  " እስ": 50516,
+  " እስከ": 50740,
+  " እስካ": 51386,
+  " እስካሁን": 51538,
+  " እነዚህ": 51401,
+  " እና": 50361,
+  " እኔ": 52022,
+  " እን": 50304,
+  " እንቅስቃሴ": 51592,
+  " እንኳ": 51492,
+  " እንኳን": 52085,
+  " እንደ": 50350,
+  " እንደሆነ": 50925,
+  " እንደሚ": 50487,
+  " እንደሚችል": 52130,
+  " እንደሚያ": 51134,
+  " እንደማይ": 52028,
+  " እንደተ": 51032,
+  " እንደነበር": 51596,
+  " እንዲ": 50389,
+  " እንዲሁ": 50760,
+  " እንዲሁም": 50817,
+  " እንዲህ": 51842,
+  " እንዲያ": 50965,
+  " እንዳ": 50507,
+  " እንዳለ": 51516,
+  " እንዳል": 51799,
+  " እንዳይ": 51255,
+  " እንዴት": 51983,
+  " እንድ": 51668,
+  " እንጂ": 51306,
+  " እንግ": 51761,
+  " እው": 51833,
+  " እየ": 50474,
+  " እየተ": 50646,
+  " እያ": 50671,
+  " እድ": 51665,
+  " እጅ": 51219,
+  " እጅግ": 51632,
+  " እግር": 52172,
+  " ኦ": 50791,
+  " ከ": 50299,
+  " ከሆነ": 51524,
+  " ከሌ": 52074,
+  " ከመ": 50708,
+  " ከሚ": 51040,
+  " ከማ": 51660,
+  " ከሰ": 51413,
+  " ከስ": 51964,
+  " ከባድ": 51674,
+  " ከተ": 50454,
+  " ከተማ": 50645,
+  " ከተሞች": 52234,
+  " ከተያያዘው": 51616,
+  " ከነ": 52222,
+  " ከአ": 50605,
+  " ከአንድ": 52082,
+  " ከእ": 51129,
+  " ከወ": 52151,
+  " ከዚህ": 50849,
+  " ከዚያ": 51450,
+  " ከፍ": 50606,
+  " ከፍተኛ": 50703,
+  " ኩ": 51241,
+  " ኩባ": 51912,
+  " ኩባንያ": 52115,
+  " ኪ": 50896,
+  " ካ": 50488,
+  " ካል": 52132,
+  " ኬ": 51254,
+  " ኬንያ": 52095,
+  " ክ": 50381,
+  " ክል": 50624,
+  " ክልል": 50733,
+  " ክስ": 51688,
+  " ክት": 51136,
+  " ክትባ": 52081,
+  " ክትባት": 51940,
+  " ክፍ": 50679,
+  " ክፍለ": 51879,
+  " ክፍል": 51239,
+  " ኮ": 50535,
+  " ኮሚ": 51018,
+  " ኮሚሽን": 52176,
+  " ኮሚቴ": 52174,
+  " ኳ": 51360,
+  " ኳስ": 51550,
+  " ወ": 50324,
+  " ወረርሽ": 51566,
+  " ወረርሽኝ": 51985,
+  " ወረዳ": 51673,
+  " ወራት": 51525,
+  " ወር": 50860,
+  " ወቅ": 50751,
+  " ወቅት": 50807,
+  " ወታደ": 50898,
+  " ወታደራዊ": 51478,
+  " ወታደሮች": 51788,
+  " ወን": 50930,
+  " ወንድ": 51970,
+  " ወንጀ": 51458,
+  " ወንጀል": 52042,
+  " ወይ": 51875,
+  " ወይም": 50772,
+  " ወደ": 50422,
+  " ወዲህ": 52084,
+  " ወገ": 52239,
+  " ወጣ": 51839,
+  " ወጥ": 51908,
+  " ዋ": 50540,
+  " ዋና": 50869,
+  " ዋንጫ": 52157,
+  " ዋጋ": 51802,
+  " ው": 50353,
+  " ውሳኔ": 51201,
+  " ውስጥ": 50409,
+  " ውይ": 51814,
+  " ውይይት": 52148,
+  " ውድ": 51167,
+  " ውጤ": 51257,
+  " ውጤት": 51871,
+  " ውጪ": 52194,
+  " ውጭ": 52066,
+  " ዐ": 51370,
+  " ዓ": 50378,
+  " ዓለም": 50927,
+  " ዓመ": 50497,
+  " ዓመቱ": 52131,
+  " ዓመታት": 50870,
+  " ዓመት": 50665,
+  " ዓክልበ": 52139,
+  " ዓይነት": 52037,
+  " ዕ": 50601,
+  " ዕለት": 51287,
+  " ዕድ": 51563,
+  " ዘ": 50435,
+  " ዘመ": 51068,
+  " ዘመቻ": 52046,
+  " ዘመን": 51112,
+  " ዘር": 51708,
+  " ዘንድ": 51484,
+  " ዘገባ": 51218,
+  " ዙ": 51148,
+  " ዙሪያ": 51671,
+  " ዛ": 50793,
+  " ዛሬ": 50907,
+  " ዜ": 50853,
+  " ዜና": 52061,
+  " ዜጎች": 51601,
+  " ዝ": 50613,
+  " ዝርዝ": 51276,
+  " ዝርዝሩን": 52197,
+  " ዝርዝር": 52009,
+  " ዝግ": 51698,
+  " ዞ": 51535,
+  " ዞን": 51988,
+  " የ": 50267,
+  " የሀ": 52025,
+  " የሃ": 51903,
+  " የህ": 51055,
+  " የሆነ": 50888,
+  " የሆነው": 51758,
+  " የሆኑ": 51073,
+  " የሆኑት": 51696,
+  " የለ": 52080,
+  " የለም": 51419,
+  " የሌ": 51890,
+  " የል": 51856,
+  " የሕ": 51036,
+  " የመ": 50425,
+  " የመላ": 51557,
+  " የመላእክት": 51625,
+  " የመንግሥት": 51874,
+  " የመጀመሪያ": 51202,
+  " የሙ": 52167,
+  " የሚ": 50332,
+  " የሚሆኑ": 51766,
+  " የሚለው": 52001,
+  " የሚል": 51207,
+  " የሚሰ": 51385,
+  " የሚቆ": 51438,
+  " የሚቆጠሩ": 51762,
+  " የሚያ": 50539,
+  " የሚያስ": 51274,
+  " የሚገኙ": 51249,
+  " የሚገኝ": 51827,
+  " የሚጠ": 51531,
+  " የማ": 50597,
+  " የማይ": 51503,
+  " የም": 50538,
+  " የምት": 51377,
+  " የምግብ": 51980,
+  " የሞ": 51481,
+  " የሩሲያ": 51792,
+  " የራ": 51937,
+  " የሰ": 50750,
+  " የሰላም": 52255,
+  " የሰብ": 51215,
+  " የሰብዓዊ": 51582,
+  " የስ": 50956,
+  " የቀ": 50746,
+  " የቀድሞ": 51434,
+  " የቆ": 51522,
+  " የበ": 51117,
+  " የባ": 51521,
+  " የተ": 50342,
+  " የተለያዩ": 51417,
+  " የተሰ": 50958,
+  " የተቀ": 51741,
+  " የተቃ": 52090,
+  " የተባ": 50729,
+  " የተባለው": 52077,
+  " የተባበሩት": 51512,
+  " የተወሰ": 52019,
+  " የተያያዘ": 51520,
+  " የተያያዘውን": 51681,
+  " የተፈ": 51393,
+  " የታ": 51003,
+  " የት": 50805,
+  " የትግራይ": 51618,
+  " የቻይና": 52088,
+  " የነ": 50559,
+  " የነበረ": 50832,
+  " የነበረው": 51391,
+  " የነበሩ": 51584,
+  " የአ": 50375,
+  " የአማርኛ": 51059,
+  " የአሜሪካ": 51026,
+  " የአውሮፓ": 51859,
+  " የአየር": 51727,
+  " የአገሪቱ": 52101,
+  " የአፍሪካ": 51283,
+  " የኢ": 51171,
+  " የኢትዮጵያ": 50688,
+  " የኤ": 51222,
+  " የኤርትራ": 52120,
+  " የእ": 50657,
+  " የኦ": 51295,
+  " የኦሮ": 51844,
+  " የካ": 51578,
+  " የኮ": 50949,
+  " የኮሮናቫይረስ": 52076,
+  " የወ": 50622,
+  " የወደ": 51353,
+  " የወደቁ": 51613,
+  " የዋ": 51807,
+  " የው": 50830,
+  " የውጭ": 51186,
+  " የዓ": 52170,
+  " የዓለም": 51050,
+  " የዘ": 52116,
+  " የዩ": 50883,
+  " የዩናይትድ": 51267,
+  " የደ": 51732,
+  " የድ": 52137,
+  " የድም": 51017,
+  " የድምፅ": 51217,
+  " የገ": 51281,
+  " የግ": 51137,
+  " የጎ": 52249,
+  " የጤና": 51357,
+  " የጥ": 51715,
+  " የጦር": 51483,
+  " የፀ": 51737,
+  " የፈ": 51244,
+  " የፌ": 51654,
+  " የፍ": 51948,
+  " የፍት": 51426,
+  " የፍትወት": 51649,
+  " የፓ": 52262,
+  " የፖ": 51165,
+  " የፖለቲካ": 51629,
+  " ዩ": 50687,
+  " ዩኒቨ": 51528,
+  " ዩናይትድ": 51511,
+  " ያ": 50327,
+  " ያህል": 51406,
+  " ያለ": 50726,
+  " ያለው": 50653,
+  " ያለውን": 51402,
+  " ያሉ": 50953,
+  " ያሉት": 51424,
+  " ያላቸው": 51709,
+  " ያል": 51033,
+  " ያልተ": 51972,
+  " ያሳ": 51540,
+  " ያስ": 50815,
+  " ያሸን": 51602,
+  " ያሸንፋሉ": 51633,
+  " ያው": 51341,
+  " ያውጃሉ": 51646,
+  " ያደር": 52264,
+  " ያዳም": 51175,
+  " ያዳምጡ": 51181,
+  " ይ": 50319,
+  " ይሁን": 51699,
+  " ይሄ": 52181,
+  " ይህ": 50465,
+  " ይህም": 51368,
+  " ይህን": 51150,
+  " ይህንን": 51432,
+  " ይሆናል": 51876,
+  " ይላሉ": 51176,
+  " ይላል": 51474,
+  " ይሰ": 51880,
+  " ይታ": 52127,
+  " ይታወ": 51265,
+  " ይታወሳል": 51832,
+  " ይች": 50756,
+  " ይችላሉ": 51178,
+  " ይችላል": 51247,
+  " ይናገ": 51387,
+  " ይናገራሉ": 51796,
+  " ይዞ": 52246,
+  " ይደ": 51431,
+  " ይደፍራሉ": 51647,
+  " ይገባ": 52099,
+  " ይገኛ": 51381,
+  " ይገኛል": 52104,
+  " ይፋ": 51436,
+  " ዮ": 51664,
+  " ደ": 50379,
+  " ደረጃ": 51066,
+  " ደር": 51720,
+  " ደቡብ": 51775,
+  " ደጋ": 52106,
+  " ደግሞ": 50580,
+  " ዲ": 50917,
+  " ዳ": 50732,
+  " ዳይ": 52112,
+  " ዴ": 51369,
+  " ድ": 50382,
+  " ድም": 50915,
+  " ድምጽ": 51736,
+  " ድምፅ": 51897,
+  " ድረስ": 50962,
+  " ድር": 51530,
+  " ድርጅ": 50661,
+  " ድርጅት": 50861,
+  " ድርጅቶች": 52087,
+  " ድርጊ": 52201,
+  " ድን": 51213,
+  " ድጋ": 51210,
+  " ድጋፍ": 51352,
+  " ዶ": 50619,
+  " ዶላር": 51327,
+  " ዶናልድ": 52195,
+  " ጀ": 50648,
+  " ጀምሮ": 51147,
+  " ጃ": 51785,
+  " ጄ": 51577,
+  " ጆ": 51170,
+  " ገ": 50397,
+  " ገለ": 51641,
+  " ገል": 50652,
+  " ገልጸ": 51240,
+  " ገልጸዋል": 51489,
+  " ገልጿል": 51683,
+  " ገልፀ": 51611,
+  " ገልፀዋል": 51962,
+  " ገብ": 51515,
+  " ገንዘብ": 51517,
+  " ጉ": 50450,
+  " ጉባ": 51640,
+  " ጉዳ": 50524,
+  " ጉዳት": 51425,
+  " ጉዳይ": 50739,
+  " ጉዳዮች": 51464,
+  " ጊዜ": 50521,
+  " ጋ": 50436,
+  " ጋር": 50473,
+  " ጋዜጠ": 51606,
+  " ጌ": 51957,
+  " ግ": 50355,
+  " ግለ": 51185,
+  " ግብ": 51678,
+  " ግን": 50442,
+  " ግንኙ": 51279,
+  " ግንኙነት": 51422,
+  " ግዛ": 52052,
+  " ግዛት": 51382,
+  " ግድ": 51332,
+  " ግድያ": 52138,
+  " ግጭ": 51208,
+  " ግጭት": 51669,
+  " ጎ": 50837,
+  " ጠ": 50477,
+  " ጠቅ": 50771,
+  " ጠቅላይ": 50964,
+  " ጠይ": 51773,
+  " ጣ": 51009,
+  " ጣቢያ": 51888,
+  " ጤ": 51367,
+  " ጤና": 51553,
+  " ጥ": 50377,
+  " ጥረት": 51716,
+  " ጥሪ": 51783,
+  " ጥቃ": 50638,
+  " ጥቃት": 50802,
+  " ጥቅም": 51653,
+  " ጥበቃ": 52229,
+  " ጥናት": 52057,
+  " ጥያቄ": 51120,
+  " ጦር": 50684,
+  " ጦርነት": 50963,
+  " ጨ": 50672,
+  " ጨምሮ": 51133,
+  " ጨዋ": 51753,
+  " ጨዋታ": 51965,
+  " ጫ": 51549,
+  " ጭ": 51127,
+  " ጸ": 51617,
+  " ጽ": 51078,
+  " ፀ": 51559,
+  " ፈ": 50571,
+  " ፈቃ": 51956,
+  " ፊ": 51006,
+  " ፋ": 51496,
+  " ፋይ": 50939,
+  " ፋይል": 51023,
+  " ፌ": 51534,
+  " ፍ": 50518,
+  " ፍላ": 51971,
+  " ፍርድ": 51158,
+  " ፎ": 52051,
+  " ፑ": 52075,
+  " ፓ": 50699,
+  " ፓርቲ": 51031,
+  " ፕ": 50502,
+  " ፕሬ": 50576,
+  " ፕሬዚ": 50846,
+  " ፕሬዚዳንት": 51139,
+  " ፕሬዝ": 50946,
+  " ፕሬዝዳንት": 51329,
+  " ፕሮ": 51193,
+  " ፖ": 50649,
+  " ፖለቲካ": 52252,
+  " ፖሊ": 51863,
+  " ፖሊስ": 51166,
+  " ፡": 52180,
+  " ፡፡": 52145,
+  " ።": 51349,
+  " ፣": 51013,
+  " ‘": 52107,
+  " “": 50529,
+  "lable": 50809,
+  "vai": 50806,
+  "ሀ": 50728,
+  "ሁ": 50363,
+  "ሁለት": 51192,
+  "ሁኑ": 51300,
+  "ሁን": 50587,
+  "ሁንም": 51693,
+  "ሁድ": 52257,
+  "ሂ": 51162,
+  "ሃ": 50466,
+  "ሃን": 51545,
+  "ሄ": 50501,
+  "ሄድ": 51751,
+  "ህ": 50318,
+  "ህል": 51027,
+  "ሆ": 50328,
+  "ሆነ": 50482,
+  "ሆኑ": 50423,
+  "ሆና": 51061,
+  "ሆናል": 51867,
+  "ሆን": 50411,
+  "ለ": 50275,
+  "ለሁ": 50955,
+  "ለመ": 51854,
+  "ለማ": 51682,
+  "ለም": 50437,
+  "ለቀ": 51579,
+  "ለተኛ": 51316,
+  "ለቱ": 50969,
+  "ለቲ": 50919,
+  "ለቲካ": 51020,
+  "ለት": 50440,
+  "ለች": 50510,
+  "ለን": 50865,
+  "ለዋል": 50546,
+  "ለው": 50372,
+  "ለውም": 51851,
+  "ለውን": 51404,
+  "ለያ": 50683,
+  "ለያዩ": 50858,
+  "ለጠ": 51865,
+  "ሉ": 50315,
+  "ሉም": 51146,
+  "ሉት": 50577,
+  "ሉን": 51326,
+  "ሊ": 50365,
+  "ሊሞች": 51477,
+  "ሊስ": 50838,
+  "ሊን": 51819,
+  "ሊዝ": 51268,
+  "ሊያ": 50922,
+  "ሊዮን": 50868,
+  "ላ": 50290,
+  "ላለ": 51145,
+  "ላለች": 51347,
+  "ላሉ": 50644,
+  "ላል": 50537,
+  "ላማ": 50836,
+  "ላማዊ": 51482,
+  "ላም": 50895,
+  "ላር": 51273,
+  "ላሽ": 51468,
+  "ላቅ": 52217,
+  "ላት": 50611,
+  "ላቸው": 50566,
+  "ላቸውን": 51191,
+  "ላን": 51188,
+  "ላንድ": 51238,
+  "ላክ": 51944,
+  "ላዊ": 51320,
+  "ላው": 51289,
+  "ላይ": 50481,
+  "ላጊ": 51692,
+  "ላፊ": 50876,
+  "ሌ": 50392,
+  "ል": 50270,
+  "ልም": 50877,
+  "ልስ": 51679,
+  "ልቅ": 51130,
+  "ልን": 52209,
+  "ልክ": 50663,
+  "ልድ": 52259,
+  "ልግ": 50978,
+  "ልጣ": 50594,
+  "ልጣን": 51399,
+  "ልፍ": 51472,
+  "ሎ": 50384,
+  "ሎት": 51038,
+  "ሎች": 50480,
+  "ሎጂ": 52031,
+  "ሏ": 50564,
+  "ሏል": 50643,
+  "ሐ": 50640,
+  "ሑ": 52030,
+  "ሓ": 51209,
+  "ሔ": 50782,
+  "ሕ": 50504,
+  "ሕር": 52236,
+  "መ": 50282,
+  "መለ": 50585,
+  "መለስ": 51724,
+  "መለከ": 51878,
+  "መለከተ": 51502,
+  "መል": 51333,
+  "መም": 52133,
+  "መረ": 51052,
+  "መሩ": 52055,
+  "መራ": 50633,
+  "መር": 50984,
+  "መሰ": 51825,
+  "መስ": 51075,
+  "መት": 51437,
+  "መን": 50615,
+  "መዋል": 51928,
+  "መው": 50906,
+  "መድ": 50944,
+  "መጡ": 51966,
+  "መጣ": 51261,
+  "ሙ": 50416,
+  "ሙሉ": 51440,
+  "ሙት": 51612,
+  "ሙን": 52012,
+  "ሙያ": 51212,
+  "ሚ": 50298,
+  "ሚያ": 50775,
+  "ማ": 50296,
+  "ማል": 52117,
+  "ማ���": 50553,
+  "ማራ": 51298,
+  "ማር": 50694,
+  "ማርኛ": 50937,
+  "ማሽ": 52146,
+  "ማት": 50873,
+  "ማቸው": 51621,
+  "ማን": 51123,
+  "ማኖ": 51846,
+  "ማይ": 51182,
+  "ሜ": 50406,
+  "ሜሪካ": 50536,
+  "ሜን": 51002,
+  "ም": 50272,
+  "ምህ": 50734,
+  "ምህር": 52033,
+  "ምህርት": 50942,
+  "ምር": 51154,
+  "ምሮ": 50651,
+  "ምባ": 51747,
+  "ምብ": 52214,
+  "ምት": 51354,
+  "ምነት": 51039,
+  "ምና": 50759,
+  "ምን": 50910,
+  "ምንት": 51095,
+  "ምጃ": 51151,
+  "ምፒ": 51952,
+  "ምፕ": 50893,
+  "ሞ": 50360,
+  "ሞት": 51995,
+  "ሞች": 50816,
+  "ሞክ": 51047,
+  "ሞክራ": 51250,
+  "ሟ": 50839,
+  "ሟል": 51999,
+  "ሠ": 50578,
+  "ሠራ": 51588,
+  "ሣ": 50761,
+  "ሥ": 50368,
+  "ሥልጣ": 50945,
+  "ሥራ": 50941,
+  "ሥራቅ": 52248,
+  "ሦስት": 52122,
+  "ረ": 50285,
+  "ረራ": 51793,
+  "ረር": 51088,
+  "ረርሽ": 51310,
+  "ረሱ": 51299,
+  "ረስ": 50549,
+  "ረበ": 52155,
+  "ረብ": 51235,
+  "ረተ": 51886,
+  "ረት": 50494,
+  "ረን": 50897,
+  "ረንሳይ": 51547,
+  "ረዋል": 50668,
+  "ረው": 50600,
+  "ረዳ": 50788,
+  "ረድ": 51765,
+  "ረጃ": 50603,
+  "ረጋ": 50844,
+  "ረጋገ": 51526,
+  "ረጋግ": 52136,
+  "ረጥ": 51925,
+  "ሩ": 50337,
+  "ሩሲያ": 51096,
+  "ሩት": 50800,
+  "ሩን": 50828,
+  "ሪ": 50302,
+  "ሪስ": 51858,
+  "ሪካ": 50434,
+  "ሪክ": 50840,
+  "ሪዎች": 50714,
+  "ሪያ": 50424,
+  "ራ": 50288,
+  "ራሉ": 50753,
+  "ራል": 50681,
+  "ራምፕ": 51180,
+  "ራት": 50468,
+  "ራቸው": 50794,
+  "ራቸውን": 51941,
+  "ራን": 50986,
+  "ራዊ": 50522,
+  "ራዊት": 51690,
+  "ራው": 51245,
+  "ሬ": 50367,
+  "ሬት": 51631,
+  "ር": 50269,
+  "ርሲ": 51800,
+  "ርሲቲ": 52064,
+  "ርስ": 50612,
+  "ርስቲ": 51072,
+  "ርስቲያን": 51961,
+  "ርቲ": 50845,
+  "ርት": 50511,
+  "ርትራ": 51053,
+  "ርክ": 51048,
+  "ርዝ": 51012,
+  "ርያ": 50933,
+  "ርድ": 50711,
+  "ርጅ": 50607,
+  "ርጉ": 52207,
+  "ርጊ": 51680,
+  "ርጫ": 50752,
+  "ሮ": 50335,
+  "ሮች": 50542,
+  "ሮችን": 51561,
+  "ሮና": 50968,
+  "ሮናቫይረስ": 51106,
+  "ሮን": 52010,
+  "ሯ": 50678,
+  "ሯል": 50982,
+  "ሰ": 50300,
+  "ሰማ": 51527,
+  "ሰሩ": 52024,
+  "ሰራ": 51098,
+  "ሰር": 51433,
+  "ሰቡ": 51234,
+  "ሰባ": 51303,
+  "ሰብ": 50555,
+  "ሰቦ": 51756,
+  "ሰቦች": 51409,
+  "ሰን": 51290,
+  "ሰዋል": 52047,
+  "ሰው": 50669,
+  "ሰጡ": 52210,
+  "ሰጥ": 51981,
+  "ሱ": 50401,
+  "ሱም": 51943,
+  "ሱት": 52048,
+  "ሱን": 51057,
+  "ሱዳን": 52018,
+  "ሲ": 50404,
+  "ሲያ": 50695,
+  "ሳ": 50321,
+  "ሳሌ": 50799,
+  "ሳል": 51114,
+  "ሳሳይ": 51619,
+  "ሳብ": 51435,
+  "ሳተ": 51348,
+  "ሳት": 50966,
+  "ሳቸው": 51307,
+  "ሳቸውን": 51894,
+  "ሳኔ": 51116,
+  "ሳይ": 50720,
+  "ሴ": 50527,
+  "ሴቶች": 52067,
+  "ስ": 50273,
+  "ስማ": 52044,
+  "ስራ": 51262,
+  "ስር": 51230,
+  "ስተ": 50551,
+  "ስተር": 52149,
+  "ስተኛ": 51486,
+  "ስተዳ": 52041,
+  "ስቱ": 52043,
+  "ስታ": 51083,
+  "ስታን": 51963,
+  "ስቴ": 51350,
+  "ስት": 50410,
+  "ስና": 51784,
+  "ስን": 52023,
+  "ስጠት": 52125,
+  "ስጥ": 50399,
+  "ስፋ": 51173,
+  "ስፒ": 51427,
+  "ሶ": 50513,
+  "ሶማ": 51420,
+  "ሶማሊያ": 52212,
+  "ሶች": 51372,
+  "ሷ": 50971,
+  "ሷል": 51667,
+  "ሸ": 50515,
+  "ሸነ": 51768,
+  "ሸን": 51211,
+  "ሹ": 51355,
+  "ሺ": 50976,
+  "ሻ": 50461,
+  "ሻሻ": 51885,
+  "ሽ": 50374,
+  "ሽን": 50943,
+  "ሾ": 51198,
+  "ቀ": 50309,
+  "ቀል": 51811,
+  "ቀም": 51949,
+  "ቀረ": 51190,
+  "ቀር": 50938,
+  "ቀስ": 51889,
+  "ቀበ": 52093,
+  "ቀት": 51371,
+  "ቀዋል": 51199,
+  "ቀው": 50863,
+  "ቀጥ": 51365,
+  "ቁ": 50433,
+  "ቁም": 52186,
+  "ቁት": 52179,
+  "ቂ": 50505,
+  "ቂት": 51748,
+  "ቂያ": 51676,
+  "ቃ": 50347,
+  "ቃል": 51216,
+  "ቃሴ": 51405,
+  "ቃት": 52098,
+  "ቃወ": 52243,
+  "ቄ": 50813,
+  "ቅ": 50325,
+  "ቅም": 50848,
+  "ቅር": 50654,
+  "ቅስ": 51292,
+  "ቅስቃሴ": 51416,
+  "ቅና": 51568,
+  "ቅድ": 51813,
+  "ቆ": 50418,
+  "ቆም": 51543,
+  "ቆጣ": 50961,
+  "ቆጣጠር": 51480,
+  "ቋ": 50455,
+  "ቋል": 50894,
+  "ቋቋ": 51834,
+  "በ": 50292,
+  "በል": 51330,
+  "በረ": 50467,
+  "በረሰብ": 51946,
+  "በሩ": 50558,
+  "በሩት": 50890,
+  "በራዊ": 51504,
+  "በር": 50376,
+  "በቃ": 51269,
+  "በብ": 52092,
+  "በታል": 51570,
+  "በት": 50412,
+  "በትን": 51463,
+  "በአ": 51910,
+  "በዋል": 51687,
+  "በው": 51087,
+  "በያ": 51806,
+  "ቡ": 50386,
+  "ቡብ": 50852,
+  "ቡን": 52164,
+  "ቢ": 50371,
+  "ቢሲ": 51025,
+  "ቢቢሲ": 51318,
+  "ቢያ": 50735,
+  "ባ": 50297,
+  "ባለ": 51196,
+  "ባለው": 51745,
+  "ባሉ": 51891,
+  "ባል": 50909,
+  "ባር": 51902,
+  "ባቢ": 50583,
+  "ባባ": 51817,
+  "ባብ": 51312,
+  "ባት": 50572,
+  "ባቸዋል": 52233,
+  "ባቸው": 50608,
+  "ባቸውን": 52206,
+  "ባዊ": 51603,
+  "ባይ": 50924,
+  "ባድ": 51384,
+  "ቤ": 50484,
+  "ቤተ": 51447,
+  "ቤት": 50999,
+  "ብ": 50295,
+  "ብሊ": 51717,
+  "ብሔ": 51569,
+  "ብሔር": 52261,
+  "ብረ": 50921,
+  "ብረት": 50932,
+  "ብራ": 51334,
+  "ብር": 50719,
+  "ብት": 51403,
+  "ብን": 52038,
+  "ብኝ": 51703,
+  "ብዙ": 51635,
+  "ቦ": 50462,
+  "ቦት": 51576,
+  "ቦች": 50814,
+  "ቧ": 50975,
+  "ቧል": 51228,
+  "ቨ": 50983,
+  "ቪ": 50604,
+  "ቪድ": 51197,
+  "ቫ": 50658,
+  "ቫይ": 50821,
+  "ቫይረሱ": 51909,
+  "ቫይረስ": 51060,
+  "ቭ": 51224,
+  "ተ": 50277,
+  "ተር": 50673,
+  "ተት": 52110,
+  "ተና": 51959,
+  "ተን": 51124,
+  "ተኛ": 50443,
+  "ተኞች": 50908,
+  "ተዋል": 50642,
+  "ተው": 50614,
+  "ቱ": 50330,
+  "ቱም": 51388,
+  "ቱት": 52039,
+  "ቱን": 50531,
+  "ቲ": 50391,
+  "ቲን": 51537,
+  "ቲክ": 51829,
+  "ታ": 50293,
+  "ታለች": 52123,
+  "ታል": 50563,
+  "ታት": 50506,
+  "ታቸው": 50596,
+  "ታቸውን": 50768,
+  "ታችን": 51749,
+  "ታወ": 50560,
+  "ታወቀ": 51414,
+  "ታወቁ": 51789,
+  "ታዊ": 50798,
+  "ታው": 50591,
+  "ታይ": 51286,
+  "ታደ": 50757,
+  "ቴ": 50457,
+  "ት": 50266,
+  "ትል": 51168,
+  "ትር": 51575,
+  "ትስ": 50758,
+  "ትና": 50847,
+  "ትን": 50517,
+  "ቶ": 50336,
+  "ቶቹ": 51560,
+  "ቶች": 50388,
+  "ቶችን": 50872,
+  "ቷ": 50495,
+  "ቷል": 50631,
+  "ቷን": 51767,
+  "ቸ": 50306,
+  "ቸኳ": 51812,
+  "ቸኳይ": 51838,
+  "ቸዋል": 50979,
+  "ቸው": 50310,
+  "ቸውን": 50414,
+  "ቹ": 50441,
+  "ቹን": 52027,
+  "ቺ": 51991,
+  "ቻ": 50398,
+  "ቻል": 51994,
+  "ቻቸው": 51028,
+  "ቻቸውን": 51786,
+  "ቻይና": 51233,
+  "ቼ": 51315,
+  "ች": 50276,
+  "ችሁ": 51634,
+  "ችሉ": 51689,
+  "ችል": 51051,
+  "ችን": 50471,
+  "ችው": 50889,
+  "ቾ": 51309,
+  "ቾች": 51895,
+  "ቿ": 51494,
+  "ኃ": 51132,
+  "ኅ": 50705,
+  "ኅንነት": 52005,
+  "ነ": 50294,
+  "ነር": 51719,
+  "ነሱ": 51523,
+  "ነሳ": 51041,
+  "ነስ": 51203,
+  "ነበረ": 50990,
+  "ነበረው": 52102,
+  "ነበር": 51275,
+  "ነቱ": 51058,
+  "ነቱን": 52020,
+  "ነት": 50364,
+  "ነትን": 52196,
+  "ነው": 50737,
+  "ነዚህ": 50902,
+  "ነገ": 51225,
+  "ነጋ": 51084,
+  "ነግ": 51551,
+  "ኑ": 50356,
+  "ኑን": 51589,
+  "ኒ": 50387,
+  "ኒቨ": 51321,
+  "ኒት": 51968,
+  "ኒው": 52183,
+  "ኒያ": 51364,
+  "ና": 50278,
+  "ናል": 50595,
+  "ናልድ": 51924,
+  "ናት": 50548,
+  "ናቸው": 51734,
+  "ናን": 51672,
+  "ናዊ": 51373,
+  "ናው": 51497,
+  "ናይ": 51772,
+  "ናይት": 50706,
+  "ናይትድ": 50716,
+  "ናገ": 50676,
+  "ናገሩት": 51841,
+  "ኔ": 50403,
+  "ኔት": 52244,
+  "ኔፊ": 51643,
+  "ኔፊሊሞች": 51650,
+  "ን": 50265,
+  "ንም": 50485,
+  "ንስ": 50655,
+  "ንቀ": 51232,
+  "ንቀሳ": 51881,
+  "ንቅ": 51609,
+  "ንቋ": 51428,
+  "ንቲ": 51605,
+  "ንታ": 51975,
+  "ንት": 50446,
+  "ንነት": 51090,
+  "ንና": 51694,
+  "ንን": 50707,
+  "ንካ": 52143,
+  "ንክ": 51884,
+  "ንዘ": 50931,
+  "ንዘብ": 51077,
+  "ንያ": 50519,
+  "ንዳ": 50912,
+  "ንድ": 50380,
+  "ንጀ": 51883,
+  "ንጉ": 51914,
+  "ንግ": 50369,
+  "ንግሊዝ": 51685,
+  "ንግሥ": 50449,
+  "ንግሥት": 51152,
+  "ንግተን": 52161,
+  "ንግድ": 52063,
+  "ንጫ": 51552,
+  "ኖ": 50373,
+  "ኖሩ": 51343,
+  "ኖር": 51070,
+  "ኖች": 50786,
+  "ኗ": 51121,
+  "ኗል": 51818,
+  "ኘ": 50769,
+  "ኘው": 52228,
+  "ኙ": 50792,
+  "ኛ": 50338,
+  "ኛል": 51661,
+  "ኛው": 50637,
+  "ኛውም": 52073,
+  "ኝ": 50396,
+  "ኝነት": 51322,
+  "ኞ": 50470,
+  "ኞቹ": 51351,
+  "ኞች": 50584,
+  "ኞችን": 51757,
+  "አ": 50305,
+  "አአ": 52227,
+  "አዊ": 51752,
+  "አይ": 51982,
+  "ኢ": 51079,
+  "ኢትዮጵያ": 51007,
+  "ኤ": 50472,
+  "ኤል": 51069,
+  "እ": 50370,
+  "እን": 51342,
+  "እክት": 51490,
+  "ኦ": 50935,
+  "ከ": 50317,
+  "ከለ": 51580,
+  "ከላ": 50801,
+  "ከላከ": 51338,
+  "ከላከል": 51712,
+  "ከላከያ": 51451,
+  "ከል": 50557,
+  "ከረ": 51657,
+  "ከራ": 51390,
+  "ከር": 51260,
+  "ከሰ": 51044,
+  "ከብ": 51996,
+  "ከተ": 50686,
+  "ከተማ": 51600,
+  "ከታ": 51488,
+  "ከታተ": 51929,
+  "ከት": 51092,
+  "ከና": 52153,
+  "ከፈ": 52000,
+  "ከፋ": 52053,
+  "ከፍ": 51305,
+  "ከፍተኛ": 51714,
+  "ኩ": 50483,
+  "ኩስ": 51913,
+  "ኪ": 50590,
+  "ኪና": 51969,
+  "ካ": 50316,
+  "ካሄ": 50710,
+  "ካሄደ": 51581,
+  "ካሄደው": 51707,
+  "ካሄድ": 51835,
+  "ካል": 51840,
+  "ካም": 52040,
+  "ካባቢ": 51206,
+  "ካባቢው": 51518,
+  "ካታ": 50851,
+  "ካን": 52169,
+  "ኬ": 50991,
+  "ክ": 50303,
+  "ክለ": 52224,
+  "ክል": 50713,
+  "ክልሉ": 51513,
+  "ክልበ": 52118,
+  "ክምና": 51142,
+  "ክሬ": 50862,
+  "ክሬን": 51067,
+  "ክር": 51317,
+  "ክስ": 51062,
+  "ክተር": 51500,
+  "ክት": 50765,
+  "ኮ": 50476,
+  "ኮች": 52154,
+  "ኮኖ": 51725,
+  "ኮኖሚ": 51979,
+  "ኳ": 50774,
+  "ኹ": 51917,
+  "ወ": 50323,
+  "ወለ": 52072,
+  "ወሓ": 51378,
+  "ወሓት": 51459,
+  "ወር": 51930,
+  "ወሰ": 50827,
+  "ወስ": 51536,
+  "ወቅ": 51955,
+  "ወት": 51280,
+  "ወደ": 51645,
+  "ወጡ": 51697,
+  "ወጣ": 50804,
+  "ወጣው": 51571,
+  "ወጥ": 52251,
+  "ዉ": 51042,
+  "ዊ": 50345,
+  "ዊተር": 52198,
+  "ዊት": 52177,
+  "ዊያን": 51798,
+  "ዋ": 50314,
+  "ዋል": 50348,
+  "ዋሚ": 51591,
+  "ዋን": 51246,
+  "ዌ": 51479,
+  "ው": 50268,
+  "ውል": 51442,
+  "ውም": 51670,
+  "ውሞ": 51449,
+  "ውሮ": 50698,
+  "ውሮፓ": 50934,
+  "ውሮፕ": 51430,
+  "ውስ": 51253,
+  "ውን": 50395,
+  "ውያኑ": 52032,
+  "ውያን": 50741,
+  "ዎ": 50541,
+  "ዎቹ": 50702,
+  "ዎች": 50333,
+  "ዎችን": 50650,
+  "ዐ": 52050,
+  "ዑ": 51423,
+  "ዓ": 50427,
+  "ዓለም": 50691,
+  "ዓት": 50926,
+  "ዓዊ": 51104,
+  "ዔ": 51843,
+  "ዕ": 50444,
+  "ዕራ": 51081,
+  "ዕራብ": 51558,
+  "ዘ": 50366,
+  "ዘመ": 51533,
+  "ዘር": 51439,
+  "ዘን": 52208,
+  "ዘው": 51394,
+  "ዘገ": 52013,
+  "ዘጋ": 51086,
+  "ዘጋጀ": 52189,
+  "ዙ": 50492,
+  "ዚ": 50362,
+  "ዚሁ": 52003,
+  "ዚህ": 50429,
+  "ዚቃ": 51939,
+  "ዚያ": 50787,
+  "ዛ": 50417,
+  "ዛሬ": 51519,
+  "ዛት": 50904,
+  "ዛዝ": 52231,
+  "ዜ": 50430,
+  "ዜጠ": 51189,
+  "ዝ": 50357,
+  "ዝብ": 50743,
+  "ዞ": 50776,
+  "ዥ": 50918,
+  "የ": 50329,
+  "የም": 51808,
+  "የር": 50754,
+  "የተ": 52147,
+  "የት": 50811,
+  "የን": 51967,
+  "የአ": 51485,
+  "የው": 51429,
+  "ዩ": 50393,
+  "ያ": 50279,
+  "ያል": 51771,
+  "ያስ": 51872,
+  "ያቄ": 51080,
+  "ያቸው": 51822,
+  "ያኑ": 51487,
+  "ያን": 50458,
+  "ያንስ": 52191,
+  "ያዊ": 52011,
+  "ያው": 51608,
+  "ያዘ": 50693,
+  "ያዙ": 51466,
+  "ያዝ": 51509,
+  "ያያዘ": 50833,
+  "ያያዘው": 51607,
+  "ዬ": 50905,
+  "ይ": 50281,
+  "ይህ": 51938,
+  "ይል": 51642,
+  "ይማኖ": 51911,
+  "ይም": 50629,
+  "ይት": 50556,
+  "ይነት": 51510,
+  "ይና": 50796,
+  "ይን": 51380,
+  "ይወ": 50736,
+  "ይወት": 51115,
+  "ይጣ": 51564,
+  "ይጣንም": 51644,
+  "ዮ": 50352,
+  "ዮች": 50892,
+  "ዮን": 50730,
+  "ደ": 50284,
+  "ደል": 51755,
+  "ደም": 50822,
+  "ደረ": 50421,
+  "ደረሰ": 51172,
+  "ደረሰው": 52160,
+  "ደረገ": 50667,
+  "ደረገው": 51231,
+  "ደረጉ": 50887,
+  "ደረጉት": 51726,
+  "ደረግ": 51285,
+  "ደራ": 51443,
+  "ደራል": 51916,
+  "ደር": 50486,
+  "ደርስ": 51594,
+  "ደርጉ": 51453,
+  "ደርግ": 51722,
+  "ደበ": 52026,
+  "ደቡብ": 51107,
+  "ደብ": 51599,
+  "ደት": 51243,
+  "ደን": 50820,
+  "ደንት": 51655,
+  "ደኛ": 51905,
+  "ደው": 50881,
+  "ደገ": 52045,
+  "ደጋ": 50841,
+  "ደጋጋሚ": 52034,
+  "ደግ": 52004,
+  "ዱ": 50448,
+  "ዱስ": 51973,
+  "ዱት": 51763,
+  "ዲ": 50341,
+  "ዲህ": 51375,
+  "ዲሱ": 52059,
+  "ዲስ": 50656,
+  "ዲያ": 51091,
+  "ዲዮ": 51850,
+  "ዳ": 50307,
+  "ዳል": 52192,
+  "ዳም": 51034,
+  "ዳሪ": 52187,
+  "ዳር": 51639,
+  "ዳታ": 51029,
+  "ዳት": 52035,
+  "ዳን": 50617,
+  "ዳንቱ": 52049,
+  "ዳንት": 50677,
+  "ዳጅ": 51301,
+  "ዴ": 50569,
+  "ዴት": 51711,
+  "ድ": 50289,
+  "ድም": 50697,
+  "ድሞ": 50954,
+  "ድረ": 50618,
+  "ድረግ": 50875,
+  "ድር": 50621,
+  "ድስት": 51718,
+  "ድን": 50647,
+  "ዶ": 50508,
+  "ዶች": 51143,
+  "ዷ": 51400,
+  "ጀ": 50419,
+  "ጀመ": 50554,
+  "ጀመረ": 52253,
+  "ጀመሪያ": 50780,
+  "ጀር": 51857,
+  "ጁ": 51076,
+  "ጂ": 50632,
+  "ጃ": 50447,
+  "ጃሉ": 51622,
+  "ጄ": 51144,
+  "ጄሪያ": 52014,
+  "ጅ": 50451,
+  "ጅም": 52260,
+  "ጆ": 50547,
+  "ጆች": 50700,
+  "ገ": 50286,
+  "ገለ": 50880,
+  "ገል": 51169,
+  "ገሩ": 51662,
+  "ገሪ": 50764,
+  "ገሪቱ": 50874,
+  "ገር": 50432,
+  "ገቡ": 51141,
+  "ገባ": 50581,
+  "ገብ": 51638,
+  "ገት": 52182,
+  "ገና": 50923,
+  "ገናኛ": 51774,
+  "ገን": 51359,
+  "ገኘ": 50634,
+  "ገኘው": 50981,
+  "ገኙ": 50627,
+  "ገኛ": 50951,
+  "ገኝ": 50854,
+  "ገዋል": 51974,
+  "ገው": 51138,
+  "ገደ": 50855,
+  "ገድ": 50755,
+  "ጉ": 50438,
+  "ጊ": 50731,
+  "ጊዜ": 51366,
+  "ጋ": 50331,
+  "ጋል": 51415,
+  "ጋሚ": 51546,
+  "ጋሪ": 52141,
+  "ጋራ": 51700,
+  "ጋቢ": 51739,
+  "ጋት": 50996,
+  "ጌ": 51282,
+  "ግ": 50291,
+  "ግለ": 50685,
+  "ግለጫ": 50831,
+  "ግል": 52017,
+  "ግሞ": 50573,
+  "ግራ": 50586,
+  "ግራይ": 50767,
+  "ግር": 50639,
+  "ግባ": 50812,
+  "ግብ": 50785,
+  "ግቧል": 51781,
+  "ግኘ": 51236,
+  "ግኘት": 51465,
+  "ግዚ": 52263,
+  "ጎ": 50514,
+  "ጎት": 51921,
+  "ጎች": 51237,
+  "ጓ": 50899,
+  "ጠ": 50320,
+  "ጠል": 51945,
+  "ጠረ": 51264,
+  "ጠሩ": 51094,
+  "ጠራ": 51740,
+  "ጠር": 50778,
+  "ጠቀ": 50914,
+  "ጠቀም": 52094,
+  "ጠቃ": 51339,
+  "ጠቃላይ": 51906,
+  "ጠቅ": 51344,
+  "ጠቅላይ": 52060,
+  "ጠበ": 51043,
+  "ጠበቅ": 52071,
+  "ጠብ": 52058,
+  "ጠት": 51469,
+  "ጠና": 50879,
+  "ጠናቀ": 52190,
+  "ጠው": 51019,
+  "ጠየ": 51845,
+  "ጠይ": 52083,
+  "ጡ": 50445,
+  "ጡት": 50989,
+  "ጣ": 50334,
+  "ጣል": 51610,
+  "ጣም": 51056,
+  "ጣሪ": 52015,
+  "ጣቂ": 51554,
+  "ጣት": 50901,
+  "ጣቸው": 52184,
+  "ጣኔ": 52218,
+  "ጣው": 52142,
+  "ጤ": 50680,
+  "ጤና": 51187,
+  "ጥ": 50311,
+  "ጥረት": 51776,
+  "ጥር": 50620,
+  "ጥሮ": 51936,
+  "ጥታ": 51021,
+  "ጥጥር": 51266,
+  "ጦ": 51177,
+  "ጦር": 50997,
+  "ጧ": 51934,
+  "ጨ": 50464,
+  "ጨማሪ": 50723,
+  "ጨረ": 51128,
+  "ጨረሻ": 51227,
+  "ጩ": 51701,
+  "ጪ": 51001,
+  "ጫ": 50475,
+  "ጭ": 50459,
+  "ጮ": 51457,
+  "ጮች": 52119,
+  "ጵ": 50413,
+  "ጵያ": 50415,
+  "ጸ": 50533,
+  "ጹ": 51163,
+  "ጻ": 50561,
+  "ጽ": 50489,
+  "ጾ": 52226,
+  "ጿ": 51015,
+  "ጿል": 51049,
+  "ፀ": 50602,
+  "ፁ": 51548,
+  "ፃ": 50721,
+  "ፅ": 50568,
+  "ፈ": 50326,
+  "ፈለ": 51873,
+  "ፈል": 50762,
+  "ፈልጋ": 52166,
+  "ፈር": 51397,
+  "ፈት": 51586,
+  "ፈው": 50666,
+  "ፈጸ": 51016,
+  "ፈፀ": 52097,
+  "ፉ": 50525,
+  "ፉት": 51105,
+  "ፊ": 50408,
+  "ፊት": 50664,
+  "ፊያ": 51926,
+  "ፋ": 50390,
+  "ፋሉ": 51470,
+  "ፋር": 52006,
+  "ፋት": 51205,
+  "ፌ": 50790,
+  "ፍ": 50312,
+  "ፍሪካ": 50609,
+  "ፍራ": 51507,
+  "ፍራሉ": 51630,
+  "ፍት": 50842,
+  "ፎ": 50835,
+  "ፎች": 51826,
+  "ፏ": 51816,
+  "ፏል": 52232,
+  "ፐ": 51499,
+  "ፐብሊ": 52108,
+  "ፑ": 52216,
+  "ፒ": 50742,
+  "ፓ": 50582,
+  "ፔ": 51702,
+  "ፕ": 50496,
+  "ፕሬ": 51358,
+  "ፖ": 50550,
+  "ፖር": 51782,
+  "ፖርት": 51294,
+  "፡": 50322,
+  "፡፡": 50400,
+  "።": 50283,
+  "።\"": 51915,
+  "።<": 52065,
+  "፣": 50339,
+  "፤": 50431,
+  "፥": 51024,
+  "፦": 51336,
+  "’": 51651,
+  "”": 50520,
+  "›": 52238
+}

adapted_tokenizers/added-opt-amh/opt_2000-add_full-amh-opt/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

adapted_tokenizers/added-opt-amh/opt_500-add_full-amh-opt/added_tokens.json

@@ -0,0 +1,502 @@
+{
+  " ሀ": 50712,
+  " ሁ": 50428,
+  " ሁኔ": 50662,
+  " ሁኔታ": 50689,
+  " ሃ": 50567,
+  " ህ": 50528,
+  " ሆ": 50478,
+  " ለ": 50313,
+  " ለመ": 50452,
+  " ለማ": 50490,
+  " ሊ": 50463,
+  " ላይ": 50358,
+  " ሌ": 50593,
+  " ል": 50426,
+  " ሕ": 50493,
+  " መ": 50287,
+  " መሆኑ": 50616,
+  " መሆኑን": 50749,
+  " መል": 50747,
+  " መስ": 50690,
+  " መን": 50630,
+  " መንግሥ": 50491,
+  " መንግሥት": 50565,
+  " መካ": 50670,
+  " መካከል": 50724,
+  " ሙ": 50623,
+  " ሚ": 50439,
+  " ሚኒ": 50599,
+  " ሚኒስት": 50701,
+  " ማ": 50343,
+  " ም": 50344,
+  " ምክ": 50523,
+  " ምክንያ": 50674,
+  " ሞ": 50718,
+  " ሥ": 50498,
+  " ሰ": 50349,
+  " ሰው": 50763,
+  " ሰዎች": 50499,
+  " ሲ": 50354,
+  " ሲሆን": 50534,
+  " ሲሉ": 50717,
+  " ሳ": 50469,
+  " ሴ": 50722,
+  " ስ": 50340,
+  " ስለ": 50544,
+  " ቀ": 50407,
+  " ቁ": 50588,
+  " ቃ": 50744,
+  " ቅ": 50589,
+  " በ": 50271,
+  " በላይ": 50727,
+  " በመ": 50394,
+  " በሚ": 50512,
+  " በማ": 50500,
+  " በር": 50738,
+  " በተ": 50402,
+  " በኋላ": 50545,
+  " በአ": 50405,
+  " በእ": 50704,
+  " በዚህ": 50682,
+  " ቡ": 50659,
+  " ቢ": 50479,
+  " ባ": 50359,
+  " ባለ": 50460,
+  " ቤ": 50420,
+  " ቤት": 50552,
+  " ብ": 50351,
+  " ብለዋል": 50625,
+  " ብዙ": 50725,
+  " ተ": 50301,
+  " ተና": 50626,
+  " ተናግ": 50715,
+  " ተከ": 50610,
+  " ተገ": 50696,
+  " ታ": 50453,
+  " ት": 50385,
+  " ች": 50745,
+  " ኃ": 50543,
+  " ኃይ": 50675,
+  " ነ": 50308,
+  " ነበር": 50456,
+  " ነው": 50346,
+  " ነገር": 50575,
+  " ና": 50532,
+  " ናቸው": 50641,
+  " ን": 50562,
+  " አ": 50274,
+  " አለ": 50598,
+  " አል": 50526,
+  " አም": 50709,
+  " አስ": 50383,
+  " አስተ": 50635,
+  " አቀ": 50692,
+  " አባ": 50628,
+  " አብ": 50748,
+  " አን": 50503,
+  " አንድ": 50592,
+  " አካ": 50570,
+  " አይ": 50509,
+  " አገ": 50530,
+  " ኢ": 50579,
+  " ኢትዮጵያ": 50574,
+  " ኤ": 50636,
+  " እ": 50280,
+  " እር": 50660,
+  " እስ": 50516,
+  " እስከ": 50740,
+  " እና": 50361,
+  " እን": 50304,
+  " እንደ": 50350,
+  " እንደሚ": 50487,
+  " እንዲ": 50389,
+  " እንዲሁ": 50760,
+  " እንዳ": 50507,
+  " እየ": 50474,
+  " እየተ": 50646,
+  " እያ": 50671,
+  " ከ": 50299,
+  " ከመ": 50708,
+  " ከተ": 50454,
+  " ከተማ": 50645,
+  " ከአ": 50605,
+  " ከፍ": 50606,
+  " ከፍተኛ": 50703,
+  " ካ": 50488,
+  " ክ": 50381,
+  " ክል": 50624,
+  " ክልል": 50733,
+  " ክፍ": 50679,
+  " ኮ": 50535,
+  " ወ": 50324,
+  " ወቅ": 50751,
+  " ወደ": 50422,
+  " ዋ": 50540,
+  " ው": 50353,
+  " ውስጥ": 50409,
+  " ዓ": 50378,
+  " ዓመ": 50497,
+  " ዓመት": 50665,
+  " ዕ": 50601,
+  " ዘ": 50435,
+  " ዝ": 50613,
+  " የ": 50267,
+  " የመ": 50425,
+  " የሚ": 50332,
+  " የሚያ": 50539,
+  " የማ": 50597,
+  " የም": 50538,
+  " የሰ": 50750,
+  " የቀ": 50746,
+  " የተ": 50342,
+  " የተባ": 50729,
+  " የነ": 50559,
+  " የአ": 50375,
+  " የኢትዮጵያ": 50688,
+  " የእ": 50657,
+  " የወ": 50622,
+  " ዩ": 50687,
+  " ያ": 50327,
+  " ያለ": 50726,
+  " ያለው": 50653,
+  " ይ": 50319,
+  " ይህ": 50465,
+  " ይች": 50756,
+  " ደ": 50379,
+  " ደግሞ": 50580,
+  " ዳ": 50732,
+  " ድ": 50382,
+  " ድርጅ": 50661,
+  " ዶ": 50619,
+  " ጀ": 50648,
+  " ገ": 50397,
+  " ገል": 50652,
+  " ጉ": 50450,
+  " ጉዳ": 50524,
+  " ጉዳይ": 50739,
+  " ጊዜ": 50521,
+  " ጋ": 50436,
+  " ጋር": 50473,
+  " ግ": 50355,
+  " ግን": 50442,
+  " ጠ": 50477,
+  " ጥ": 50377,
+  " ጥቃ": 50638,
+  " ጦር": 50684,
+  " ጨ": 50672,
+  " ፈ": 50571,
+  " ፍ": 50518,
+  " ፓ": 50699,
+  " ፕ": 50502,
+  " ፕሬ": 50576,
+  " ፖ": 50649,
+  " “": 50529,
+  "ሀ": 50728,
+  "ሁ": 50363,
+  "ሁን": 50587,
+  "ሃ": 50466,
+  "ሄ": 50501,
+  "ህ": 50318,
+  "ሆ": 50328,
+  "ሆነ": 50482,
+  "ሆኑ": 50423,
+  "ሆን": 50411,
+  "ለ": 50275,
+  "ለም": 50437,
+  "ለት": 50440,
+  "ለች": 50510,
+  "ለዋል": 50546,
+  "ለው": 50372,
+  "ለያ": 50683,
+  "ሉ": 50315,
+  "ሉት": 50577,
+  "ሊ": 50365,
+  "ላ": 50290,
+  "ላሉ": 50644,
+  "ላል": 50537,
+  "ላት": 50611,
+  "ላቸው": 50566,
+  "ላይ": 50481,
+  "ሌ": 50392,
+  "ል": 50270,
+  "ልክ": 50663,
+  "ልጣ": 50594,
+  "ሎ": 50384,
+  "ሎች": 50480,
+  "ሏ": 50564,
+  "ሏል": 50643,
+  "ሐ": 50640,
+  "ሕ": 50504,
+  "መ": 50282,
+  "መለ": 50585,
+  "መራ": 50633,
+  "መን": 50615,
+  "ሙ": 50416,
+  "ሚ": 50298,
+  "ማ": 50296,
+  "ማሪ": 50553,
+  "ማር": 50694,
+  "ሜ": 50406,
+  "ሜሪካ": 50536,
+  "ም": 50272,
+  "ምህ": 50734,
+  "ምሮ": 50651,
+  "ምና": 50759,
+  "ሞ": 50360,
+  "ሠ": 50578,
+  "ሣ": 50761,
+  "ሥ": 50368,
+  "ረ": 50285,
+  "ረስ": 50549,
+  "ረት": 50494,
+  "ረዋል": 50668,
+  "ረው": 50600,
+  "ረጃ": 50603,
+  "ሩ": 50337,
+  "ሪ": 50302,
+  "ሪካ": 50434,
+  "ሪዎች": 50714,
+  "ሪያ": 50424,
+  "ራ": 50288,
+  "ራሉ": 50753,
+  "ራል": 50681,
+  "ራት": 50468,
+  "ራዊ": 50522,
+  "ሬ": 50367,
+  "ር": 50269,
+  "ርስ": 50612,
+  "ርት": 50511,
+  "ርድ": 50711,
+  "ርጅ": 50607,
+  "ርጫ": 50752,
+  "ሮ": 50335,
+  "ሮች": 50542,
+  "ሯ": 50678,
+  "ሰ": 50300,
+  "ሰብ": 50555,
+  "ሰው": 50669,
+  "ሱ": 50401,
+  "ሲ": 50404,
+  "ሲያ": 50695,
+  "ሳ": 50321,
+  "ሳይ": 50720,
+  "ሴ": 50527,
+  "ስ": 50273,
+  "ስተ": 50551,
+  "ስት": 50410,
+  "ስጥ": 50399,
+  "ሶ": 50513,
+  "ሸ": 50515,
+  "ሻ": 50461,
+  "ሽ": 50374,
+  "ቀ": 50309,
+  "ቁ": 50433,
+  "ቂ": 50505,
+  "ቃ": 50347,
+  "ቅ": 50325,
+  "ቅር": 50654,
+  "ቆ": 50418,
+  "ቋ": 50455,
+  "በ": 50292,
+  "በረ": 50467,
+  "በሩ": 50558,
+  "በር": 50376,
+  "በት": 50412,
+  "ቡ": 50386,
+  "ቢ": 50371,
+  "ቢያ": 50735,
+  "ባ": 50297,
+  "ባቢ": 50583,
+  "ባት": 50572,
+  "ባቸው": 50608,
+  "ቤ": 50484,
+  "ብ": 50295,
+  "ብር": 50719,
+  "ቦ": 50462,
+  "ቪ": 50604,
+  "ቫ": 50658,
+  "ተ": 50277,
+  "ተር": 50673,
+  "ተኛ": 50443,
+  "ተዋል": 50642,
+  "ተው": 50614,
+  "ቱ": 50330,
+  "ቱን": 50531,
+  "ቲ": 50391,
+  "ታ": 50293,
+  "ታል": 50563,
+  "ታት": 50506,
+  "ታቸው": 50596,
+  "ታወ": 50560,
+  "ታው": 50591,
+  "ታደ": 50757,
+  "ቴ": 50457,
+  "ት": 50266,
+  "ትስ": 50758,
+  "ትን": 50517,
+  "ቶ": 50336,
+  "ቶች": 50388,
+  "ቷ": 50495,
+  "ቷል": 50631,
+  "ቸ": 50306,
+  "ቸው": 50310,
+  "ቸውን": 50414,
+  "ቹ": 50441,
+  "ቻ": 50398,
+  "ች": 50276,
+  "ችን": 50471,
+  "ኅ": 50705,
+  "ነ": 50294,
+  "ነት": 50364,
+  "ነው": 50737,
+  "ኑ": 50356,
+  "ኒ": 50387,
+  "ና": 50278,
+  "ናል": 50595,
+  "ናት": 50548,
+  "ናይት": 50706,
+  "ናይትድ": 50716,
+  "ናገ": 50676,
+  "ኔ": 50403,
+  "ን": 50265,
+  "ንም": 50485,
+  "ንስ": 50655,
+  "ንት": 50446,
+  "ንን": 50707,
+  "ንያ": 50519,
+  "ንድ": 50380,
+  "ንግ": 50369,
+  "ንግሥ": 50449,
+  "ኖ": 50373,
+  "ኛ": 50338,
+  "ኛው": 50637,
+  "ኝ": 50396,
+  "ኞ": 50470,
+  "ኞች": 50584,
+  "አ": 50305,
+  "ኤ": 50472,
+  "እ": 50370,
+  "ከ": 50317,
+  "ከል": 50557,
+  "ከተ": 50686,
+  "ኩ": 50483,
+  "ኪ": 50590,
+  "ካ": 50316,
+  "ካሄ": 50710,
+  "ክ": 50303,
+  "ክል": 50713,
+  "ኮ": 50476,
+  "ወ": 50323,
+  "ዊ": 50345,
+  "ዋ": 50314,
+  "ዋል": 50348,
+  "ው": 50268,
+  "ውሮ": 50698,
+  "ውን": 50395,
+  "ውያን": 50741,
+  "ዎ": 50541,
+  "ዎቹ": 50702,
+  "ዎች": 50333,
+  "ዎችን": 50650,
+  "ዓ": 50427,
+  "ዓለም": 50691,
+  "ዕ": 50444,
+  "ዘ": 50366,
+  "ዙ": 50492,
+  "ዚ": 50362,
+  "ዚህ": 50429,
+  "ዛ": 50417,
+  "ዜ": 50430,
+  "ዝ": 50357,
+  "ዝብ": 50743,
+  "የ": 50329,
+  "የር": 50754,
+  "ዩ": 50393,
+  "ያ": 50279,
+  "ያን": 50458,
+  "ያዘ": 50693,
+  "ይ": 50281,
+  "ይም": 50629,
+  "ይት": 50556,
+  "ይወ": 50736,
+  "ዮ": 50352,
+  "ዮን": 50730,
+  "ደ": 50284,
+  "ደረ": 50421,
+  "ደረገ": 50667,
+  "ደር": 50486,
+  "ዱ": 50448,
+  "ዲ": 50341,
+  "ዲስ": 50656,
+  "ዳ": 50307,
+  "ዳን": 50617,
+  "ዳንት": 50677,
+  "ዴ": 50569,
+  "ድ": 50289,
+  "ድም": 50697,
+  "ድረ": 50618,
+  "ድር": 50621,
+  "ድን": 50647,
+  "ዶ": 50508,
+  "ጀ": 50419,
+  "ጀመ": 50554,
+  "ጂ": 50632,
+  "ጃ": 50447,
+  "ጅ": 50451,
+  "ጆ": 50547,
+  "ጆች": 50700,
+  "ገ": 50286,
+  "ገሪ": 50764,
+  "ገር": 50432,
+  "ገባ": 50581,
+  "ገኘ": 50634,
+  "ገኙ": 50627,
+  "ገድ": 50755,
+  "ጉ": 50438,
+  "ጊ": 50731,
+  "ጋ": 50331,
+  "ግ": 50291,
+  "ግለ": 50685,
+  "ግሞ": 50573,
+  "ግራ": 50586,
+  "ግር": 50639,
+  "ጎ": 50514,
+  "ጠ": 50320,
+  "ጡ": 50445,
+  "ጣ": 50334,
+  "ጤ": 50680,
+  "ጥ": 50311,
+  "ጥር": 50620,
+  "ጨ": 50464,
+  "ጨማሪ": 50723,
+  "ጫ": 50475,
+  "ጭ": 50459,
+  "ጵ": 50413,
+  "ጵያ": 50415,
+  "ጸ": 50533,
+  "ጻ": 50561,
+  "ጽ": 50489,
+  "ፀ": 50602,
+  "ፃ": 50721,
+  "ፅ": 50568,
+  "ፈ": 50326,
+  "ፈል": 50762,
+  "ፈው": 50666,
+  "ፉ": 50525,
+  "ፊ": 50408,
+  "ፊት": 50664,
+  "ፋ": 50390,
+  "ፍ": 50312,
+  "ፍሪካ": 50609,
+  "ፒ": 50742,
+  "ፓ": 50582,
+  "ፕ": 50496,
+  "ፖ": 50550,
+  "፡": 50322,
+  "፡፡": 50400,
+  "።": 50283,
+  "፣": 50339,
+  "፤": 50431,
+  "”": 50520
+}

adapted_tokenizers/added-opt-amh/opt_500-add_full-amh-opt/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

adapted_tokenizers/added-opt-amh/opt_500-add_full-amh-opt/tokenizer_config.json

@@ -0,0 +1,4030 @@
+{
+  "add_bos_token": true,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50265": {
+      "content": "ን",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50266": {
+      "content": "ት",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50267": {
+      "content": " የ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50268": {
+      "content": "ው",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50269": {
+      "content": "ር",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50270": {
+      "content": "ል",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50271": {
+      "content": " በ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50272": {
+      "content": "ም",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50273": {
+      "content": "ስ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50274": {
+      "content": " አ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50275": {
+      "content": "ለ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50276": {
+      "content": "ች",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50277": {
+      "content": "ተ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50278": {
+      "content": "ና",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50279": {
+      "content": "ያ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50280": {
+      "content": " እ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50281": {
+      "content": "ይ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50282": {
+      "content": "መ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50283": {
+      "content": "።",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50284": {
+      "content": "ደ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50285": {
+      "content": "ረ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50286": {
+      "content": "ገ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50287": {
+      "content": " መ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50288": {
+      "content": "ራ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50289": {
+      "content": "ድ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50290": {
+      "content": "ላ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50291": {
+      "content": "ግ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50292": {
+      "content": "በ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50293": {
+      "content": "ታ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50294": {
+      "content": "ነ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50295": {
+      "content": "ብ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50296": {
+      "content": "ማ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50297": {
+      "content": "ባ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50298": {
+      "content": "ሚ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50299": {
+      "content": " ከ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50300": {
+      "content": "ሰ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50301": {
+      "content": " ተ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50302": {
+      "content": "ሪ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50303": {
+      "content": "ክ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50304": {
+      "content": " እን",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50305": {
+      "content": "አ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50306": {
+      "content": "ቸ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50307": {
+      "content": "ዳ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50308": {
+      "content": " ነ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50309": {
+      "content": "ቀ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50310": {
+      "content": "ቸው",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50311": {
+      "content": "ጥ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50312": {
+      "content": "ፍ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50313": {
+      "content": " ለ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50314": {
+      "content": "ዋ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50315": {
+      "content": "ሉ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50316": {
+      "content": "ካ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50317": {
+      "content": "ከ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50318": {
+      "content": "ህ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50319": {
+      "content": " ይ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50320": {
+      "content": "ጠ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50321": {
+      "content": "ሳ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50322": {
+      "content": "፡",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50323": {
+      "content": "ወ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50324": {
+      "content": " ወ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50325": {
+      "content": "ቅ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50326": {
+      "content": "ፈ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50327": {
+      "content": " ያ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50328": {
+      "content": "ሆ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50329": {
+      "content": "የ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50330": {
+      "content": "ቱ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50331": {
+      "content": "ጋ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50332": {
+      "content": " የሚ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50333": {
+      "content": "ዎች",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50334": {
+      "content": "ጣ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50335": {
+      "content": "ሮ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50336": {
+      "content": "ቶ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50337": {
+      "content": "ሩ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50338": {
+      "content": "ኛ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50339": {
+      "content": "፣",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50340": {
+      "content": " ስ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50341": {
+      "content": "ዲ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50342": {
+      "content": " የተ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50343": {
+      "content": " ማ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50344": {
+      "content": " ም",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50345": {
+      "content": "ዊ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50346": {
+      "content": " ነው",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50347": {
+      "content": "ቃ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50348": {
+      "content": "ዋል",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50349": {
+      "content": " ሰ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50350": {
+      "content": " እንደ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50351": {
+      "content": " ብ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50352": {
+      "content": "ዮ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50353": {
+      "content": " ው",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50354": {
+      "content": " ሲ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50355": {
+      "content": " ግ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50356": {
+      "content": "ኑ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50357": {
+      "content": "ዝ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50358": {
+      "content": " ላይ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50359": {
+      "content": " ባ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50360": {
+      "content": "ሞ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50361": {
+      "content": " እና",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50362": {
+      "content": "ዚ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50363": {
+      "content": "ሁ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50364": {
+      "content": "ነት",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50365": {
+      "content": "ሊ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50366": {
+      "content": "ዘ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50367": {
+      "content": "ሬ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50368": {
+      "content": "ሥ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50369": {
+      "content": "ንግ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50370": {
+      "content": "እ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50371": {
+      "content": "ቢ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50372": {
+      "content": "ለው",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50373": {
+      "content": "ኖ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50374": {
+      "content": "ሽ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50375": {
+      "content": " የአ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50376": {
+      "content": "በር",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50377": {
+      "content": " ጥ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50378": {
+      "content": " ዓ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50379": {
+      "content": " ደ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50380": {
+      "content": "ንድ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50381": {
+      "content": " ክ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50382": {
+      "content": " ድ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50383": {
+      "content": " አስ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50384": {
+      "content": "ሎ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50385": {
+      "content": " ት",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50386": {
+      "content": "ቡ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50387": {
+      "content": "ኒ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50388": {
+      "content": "ቶች",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50389": {
+      "content": " እንዲ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50390": {
+      "content": "ፋ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50391": {
+      "content": "ቲ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50392": {
+      "content": "ሌ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50393": {
+      "content": "ዩ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50394": {
+      "content": " በመ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50395": {
+      "content": "ውን",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50396": {
+      "content": "ኝ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50397": {
+      "content": " ገ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50398": {
+      "content": "ቻ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50399": {
+      "content": "ስጥ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50400": {
+      "content": "፡፡",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50401": {
+      "content": "ሱ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50402": {
+      "content": " በተ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50403": {
+      "content": "ኔ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50404": {
+      "content": "ሲ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50405": {
+      "content": " በአ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50406": {
+      "content": "ሜ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50407": {
+      "content": " ቀ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50408": {
+      "content": "ፊ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50409": {
+      "content": " ውስጥ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50410": {
+      "content": "ስት",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50411": {
+      "content": "ሆን",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50412": {
+      "content": "በት",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50413": {
+      "content": "ጵ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50414": {
+      "content": "ቸውን",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50415": {
+      "content": "ጵያ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50416": {
+      "content": "ሙ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50417": {
+      "content": "ዛ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50418": {
+      "content": "ቆ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50419": {
+      "content": "ጀ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50420": {
+      "content": " ቤ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50421": {
+      "content": "ደረ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50422": {
+      "content": " ወደ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50423": {
+      "content": "ሆኑ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50424": {
+      "content": "ሪያ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50425": {
+      "content": " የመ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50426": {
+      "content": " ል",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50427": {
+      "content": "ዓ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50428": {
+      "content": " ሁ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50429": {
+      "content": "ዚህ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50430": {
+      "content": "ዜ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50431": {
+      "content": "፤",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50432": {
+      "content": "ገር",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50433": {
+      "content": "ቁ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50434": {
+      "content": "ሪካ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50435": {
+      "content": " ዘ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50436": {
+      "content": " ጋ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50437": {
+      "content": "ለም",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50438": {
+      "content": "ጉ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50439": {
+      "content": " ሚ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50440": {
+      "content": "ለት",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50441": {
+      "content": "ቹ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50442": {
+      "content": " ግን",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50443": {
+      "content": "ተኛ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50444": {
+      "content": "ዕ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50445": {
+      "content": "ጡ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50446": {
+      "content": "ንት",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50447": {
+      "content": "ጃ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50448": {
+      "content": "ዱ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50449": {
+      "content": "ንግሥ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50450": {
+      "content": " ጉ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50451": {
+      "content": "ጅ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50452": {
+      "content": " ለመ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50453": {
+      "content": " ታ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50454": {
+      "content": " ከተ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50455": {
+      "content": "ቋ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50456": {
+      "content": " ነበር",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50457": {
+      "content": "ቴ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50458": {
+      "content": "ያን",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50459": {
+      "content": "ጭ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50460": {
+      "content": " ባለ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50461": {
+      "content": "ሻ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50462": {
+      "content": "ቦ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50463": {
+      "content": " ሊ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50464": {
+      "content": "ጨ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50465": {
+      "content": " ይህ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50466": {
+      "content": "ሃ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50467": {
+      "content": "በረ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50468": {
+      "content": "ራት",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50469": {
+      "content": " ሳ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50470": {
+      "content": "ኞ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50471": {
+      "content": "ችን",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50472": {
+      "content": "ኤ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50473": {
+      "content": " ጋር",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50474": {
+      "content": " እየ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50475": {
+      "content": "ጫ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50476": {
+      "content": "ኮ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50477": {
+      "content": " ጠ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50478": {
+      "content": " ሆ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50479": {
+      "content": " ቢ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50480": {
+      "content": "ሎች",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50481": {
+      "content": "ላይ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50482": {
+      "content": "ሆነ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50483": {
+      "content": "ኩ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50484": {
+      "content": "ቤ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50485": {
+      "content": "ንም",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50486": {
+      "content": "ደር",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50487": {
+      "content": " እንደሚ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50488": {
+      "content": " ካ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50489": {
+      "content": "ጽ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50490": {
+      "content": " ለማ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50491": {
+      "content": " መንግሥ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50492": {
+      "content": "ዙ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50493": {
+      "content": " ሕ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50494": {
+      "content": "ረት",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50495": {
+      "content": "ቷ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50496": {
+      "content": "ፕ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50497": {
+      "content": " ዓመ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50498": {
+      "content": " ሥ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50499": {
+      "content": " ሰዎች",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50500": {
+      "content": " በማ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50501": {
+      "content": "ሄ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50502": {
+      "content": " ፕ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50503": {
+      "content": " አን",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50504": {
+      "content": "ሕ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50505": {
+      "content": "ቂ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50506": {
+      "content": "ታት",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50507": {
+      "content": " እንዳ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50508": {
+      "content": "ዶ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50509": {
+      "content": " አይ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50510": {
+      "content": "ለች",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50511": {
+      "content": "ርት",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50512": {
+      "content": " በሚ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50513": {
+      "content": "ሶ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50514": {
+      "content": "ጎ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50515": {
+      "content": "ሸ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50516": {
+      "content": " እስ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50517": {
+      "content": "ትን",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50518": {
+      "content": " ፍ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50519": {
+      "content": "ንያ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50520": {
+      "content": "”",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50521": {
+      "content": " ጊዜ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50522": {
+      "content": "ራዊ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50523": {
+      "content": " ምክ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50524": {
+      "content": " ጉዳ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50525": {
+      "content": "ፉ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50526": {
+      "content": " አል",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50527": {
+      "content": "ሴ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50528": {
+      "content": " ህ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50529": {
+      "content": " “",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50530": {
+      "content": " አገ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50531": {
+      "content": "ቱን",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50532": {
+      "content": " ና",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50533": {
+      "content": "ጸ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50534": {
+      "content": " ሲሆን",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50535": {
+      "content": " ኮ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50536": {
+      "content": "ሜሪካ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50537": {
+      "content": "ላል",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50538": {
+      "content": " የም",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50539": {
+      "content": " የሚያ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50540": {
+      "content": " ዋ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50541": {
+      "content": "ዎ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50542": {
+      "content": "ሮች",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50543": {
+      "content": " ኃ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50544": {
+      "content": " ስለ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50545": {
+      "content": " በኋላ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50546": {
+      "content": "ለዋል",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50547": {
+      "content": "ጆ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50548": {
+      "content": "ናት",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50549": {
+      "content": "ረስ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50550": {
+      "content": "ፖ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50551": {
+      "content": "ስተ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50552": {
+      "content": " ቤት",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50553": {
+      "content": "ማሪ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50554": {
+      "content": "ጀመ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50555": {
+      "content": "ሰብ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50556": {
+      "content": "ይት",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50557": {
+      "content": "ከል",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50558": {
+      "content": "በሩ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50559": {
+      "content": " የነ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50560": {
+      "content": "ታወ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50561": {
+      "content": "ጻ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50562": {
+      "content": " ን",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50563": {
+      "content": "ታል",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50564": {
+      "content": "ሏ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50565": {
+      "content": " መንግሥት",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50566": {
+      "content": "ላቸው",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50567": {
+      "content": " ሃ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50568": {
+      "content": "ፅ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50569": {
+      "content": "ዴ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50570": {
+      "content": " አካ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50571": {
+      "content": " ፈ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50572": {
+      "content": "ባት",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50573": {
+      "content": "ግሞ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50574": {
+      "content": " ኢትዮጵያ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50575": {
+      "content": " ነገር",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50576": {
+      "content": " ፕሬ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50577": {
+      "content": "ሉት",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50578": {
+      "content": "ሠ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50579": {
+      "content": " ኢ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50580": {
+      "content": " ደግሞ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50581": {
+      "content": "ገባ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50582": {
+      "content": "ፓ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50583": {
+      "content": "ባቢ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50584": {
+      "content": "ኞች",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50585": {
+      "content": "መለ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50586": {
+      "content": "ግራ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50587": {
+      "content": "ሁን",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50588": {
+      "content": " ቁ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50589": {
+      "content": " ቅ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50590": {
+      "content": "ኪ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50591": {
+      "content": "ታው",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50592": {
+      "content": " አንድ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50593": {
+      "content": " ሌ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50594": {
+      "content": "ልጣ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50595": {
+      "content": "ናል",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50596": {
+      "content": "ታቸው",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50597": {
+      "content": " የማ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50598": {
+      "content": " አለ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50599": {
+      "content": " ሚኒ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50600": {
+      "content": "ረው",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50601": {
+      "content": " ዕ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50602": {
+      "content": "ፀ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50603": {
+      "content": "ረጃ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50604": {
+      "content": "ቪ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50605": {
+      "content": " ከአ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50606": {
+      "content": " ከፍ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50607": {
+      "content": "ርጅ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50608": {
+      "content": "ባቸው",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50609": {
+      "content": "ፍሪካ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50610": {
+      "content": " ተከ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50611": {
+      "content": "ላት",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50612": {
+      "content": "ርስ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50613": {
+      "content": " ዝ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50614": {
+      "content": "ተው",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50615": {
+      "content": "መን",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50616": {
+      "content": " መሆኑ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50617": {
+      "content": "ዳን",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50618": {
+      "content": "ድረ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50619": {
+      "content": " ዶ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50620": {
+      "content": "ጥር",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50621": {
+      "content": "ድር",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50622": {
+      "content": " የወ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50623": {
+      "content": " ሙ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50624": {
+      "content": " ክል",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50625": {
+      "content": " ብለዋል",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50626": {
+      "content": " ተና",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50627": {
+      "content": "ገኙ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50628": {
+      "content": " አባ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50629": {
+      "content": "ይም",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50630": {
+      "content": " መን",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50631": {
+      "content": "ቷል",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50632": {
+      "content": "ጂ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50633": {
+      "content": "መራ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50634": {
+      "content": "ገኘ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50635": {
+      "content": " አስተ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50636": {
+      "content": " ኤ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50637": {
+      "content": "ኛው",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50638": {
+      "content": " ጥቃ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50639": {
+      "content": "ግር",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50640": {
+      "content": "ሐ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50641": {
+      "content": " ናቸው",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50642": {
+      "content": "ተዋል",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50643": {
+      "content": "ሏል",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50644": {
+      "content": "ላሉ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50645": {
+      "content": " ከተማ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50646": {
+      "content": " እየተ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50647": {
+      "content": "ድን",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50648": {
+      "content": " ጀ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50649": {
+      "content": " ፖ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50650": {
+      "content": "ዎችን",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50651": {
+      "content": "ምሮ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50652": {
+      "content": " ገል",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50653": {
+      "content": " ያለው",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50654": {
+      "content": "ቅር",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50655": {
+      "content": "ንስ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50656": {
+      "content": "ዲስ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50657": {
+      "content": " የእ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50658": {
+      "content": "ቫ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50659": {
+      "content": " ቡ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50660": {
+      "content": " እር",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50661": {
+      "content": " ድርጅ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50662": {
+      "content": " ሁኔ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50663": {
+      "content": "ልክ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50664": {
+      "content": "ፊት",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50665": {
+      "content": " ዓመት",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50666": {
+      "content": "ፈው",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50667": {
+      "content": "ደረገ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50668": {
+      "content": "ረዋል",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50669": {
+      "content": "ሰው",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50670": {
+      "content": " መካ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50671": {
+      "content": " እያ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50672": {
+      "content": " ጨ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50673": {
+      "content": "ተር",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50674": {
+      "content": " ምክንያ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50675": {
+      "content": " ኃይ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50676": {
+      "content": "ናገ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50677": {
+      "content": "ዳንት",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50678": {
+      "content": "ሯ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50679": {
+      "content": " ክፍ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50680": {
+      "content": "ጤ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50681": {
+      "content": "ራል",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50682": {
+      "content": " በዚህ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50683": {
+      "content": "ለያ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50684": {
+      "content": " ጦር",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50685": {
+      "content": "ግለ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50686": {
+      "content": "ከተ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50687": {
+      "content": " ዩ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50688": {
+      "content": " የኢትዮጵያ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50689": {
+      "content": " ሁኔታ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50690": {
+      "content": " መስ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50691": {
+      "content": "ዓለም",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50692": {
+      "content": " አቀ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50693": {
+      "content": "ያዘ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50694": {
+      "content": "ማር",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50695": {
+      "content": "ሲያ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50696": {
+      "content": " ተገ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50697": {
+      "content": "ድም",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50698": {
+      "content": "ውሮ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50699": {
+      "content": " ፓ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50700": {
+      "content": "ጆች",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50701": {
+      "content": " ሚኒስት",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50702": {
+      "content": "ዎቹ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50703": {
+      "content": " ከፍተኛ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50704": {
+      "content": " በእ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50705": {
+      "content": "ኅ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50706": {
+      "content": "ናይት",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50707": {
+      "content": "ንን",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50708": {
+      "content": " ከመ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50709": {
+      "content": " አም",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50710": {
+      "content": "ካሄ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50711": {
+      "content": "ርድ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50712": {
+      "content": " ሀ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50713": {
+      "content": "ክል",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50714": {
+      "content": "ሪዎች",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50715": {
+      "content": " ተናግ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50716": {
+      "content": "ናይትድ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50717": {
+      "content": " ሲሉ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50718": {
+      "content": " ሞ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50719": {
+      "content": "ብር",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50720": {
+      "content": "ሳይ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50721": {
+      "content": "ፃ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50722": {
+      "content": " ሴ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50723": {
+      "content": "ጨማሪ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50724": {
+      "content": " መካከል",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50725": {
+      "content": " ብዙ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50726": {
+      "content": " ያለ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50727": {
+      "content": " በላይ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50728": {
+      "content": "ሀ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50729": {
+      "content": " የተባ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50730": {
+      "content": "ዮን",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50731": {
+      "content": "ጊ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50732": {
+      "content": " ዳ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50733": {
+      "content": " ክልል",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50734": {
+      "content": "ምህ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50735": {
+      "content": "ቢያ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50736": {
+      "content": "ይወ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50737": {
+      "content": "ነው",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50738": {
+      "content": " በር",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50739": {
+      "content": " ጉዳይ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50740": {
+      "content": " እስከ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50741": {
+      "content": "ውያን",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50742": {
+      "content": "ፒ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50743": {
+      "content": "ዝብ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50744": {
+      "content": " ቃ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50745": {
+      "content": " ች",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50746": {
+      "content": " የቀ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50747": {
+      "content": " መል",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50748": {
+      "content": " አብ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50749": {
+      "content": " መሆኑን",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50750": {
+      "content": " የሰ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50751": {
+      "content": " ወቅ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50752": {
+      "content": "ርጫ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50753": {
+      "content": "ራሉ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50754": {
+      "content": "የር",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50755": {
+      "content": "ገድ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50756": {
+      "content": " ይች",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50757": {
+      "content": "ታደ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50758": {
+      "content": "ትስ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50759": {
+      "content": "ምና",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50760": {
+      "content": " እንዲሁ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50761": {
+      "content": "ሣ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50762": {
+      "content": "ፈል",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50763": {
+      "content": " ሰው",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50764": {
+      "content": "ገሪ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "</s>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "errors": "replace",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "</s>"
+}

adapted_tokenizers/added-opt-amh/opt_5000-add_full-amh-opt/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

adapted_tokenizers/added-opt-eng/opt_100-add_full-eng-opt/added_tokens.json

@@ -0,0 +1,102 @@
+{
+  " Academ": 50331,
+  " Biography": 50362,
+  " Emp": 50360,
+  " Geor": 50300,
+  " Histor": 50353,
+  " Legit": 50351,
+  " Oly": 50310,
+  " Pla": 50350,
+  " Profess": 50358,
+  " anc": 50363,
+  " appoin": 50313,
+  " becom": 50335,
+  " colla": 50346,
+  " consid": 50303,
+  " constru": 50308,
+  " daugh": 50325,
+  " dif": 50287,
+  " earl": 50336,
+  " emp": 50320,
+  " examp": 50323,
+  " gradu": 50324,
+  " nomin": 50355,
+  " nov": 50327,
+  " performan": 50322,
+  " pla": 50265,
+  " plann": 50359,
+  " poin": 50296,
+  " produc": 50330,
+  " publ": 50271,
+  " repla": 50314,
+  " sele": 50339,
+  " tourn": 50334,
+  " villa": 50289,
+  " “": 50306,
+  "adio": 50311,
+  "ampionship": 50291,
+  "areer": 50276,
+  "arliam": 50326,
+  "arliament": 50328,
+  "arly": 50270,
+  "arri": 50279,
+  "arried": 50301,
+  "cted": 50269,
+  "ctober": 50286,
+  "duced": 50292,
+  "ebru": 50293,
+  "ebruary": 50294,
+  "ecess": 50364,
+  "eck": 50338,
+  "ecut": 50312,
+  "ecutive": 50333,
+  "eep": 50340,
+  "eleb": 50349,
+  "ely": 50267,
+  "embers": 50295,
+  "embly": 50337,
+  "emor": 50344,
+  "eneral": 50309,
+  "eptember": 50285,
+  "etwork": 50321,
+  "fess": 50281,
+  "fic": 50342,
+  "forman": 50316,
+  "gether": 50329,
+  "iforn": 50317,
+  "ifornia": 50318,
+  "ilm": 50268,
+  "incip": 50347,
+  "istory": 50275,
+  "ivision": 50297,
+  "lack": 50298,
+  "lant": 50356,
+  "loy": 50305,
+  "ociety": 50315,
+  "ollowing": 50348,
+  "ootball": 50274,
+  "ounc": 50299,
+  "ouncil": 50302,
+  "overn": 50272,
+  "overnment": 50278,
+  "overnor": 50332,
+  "oviet": 50352,
+  "owever": 50280,
+  "pril": 50288,
+  "reland": 50343,
+  "retary": 50354,
+  "stit": 50277,
+  "stitut": 50361,
+  "stitute": 50319,
+  "tend": 50284,
+  "tended": 50304,
+  "ternational": 50283,
+  "thlet": 50341,
+  "ubl": 50266,
+  "ugust": 50282,
+  "ularly": 50345,
+  "usic": 50273,
+  "zil": 50357,
+  "’": 50290,
+  "”": 50307
+}

adapted_tokenizers/added-opt-eng/opt_100-add_full-eng-opt/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

adapted_tokenizers/added-opt-eng/opt_100-add_full-eng-opt/tokenizer_config.json

@@ -0,0 +1,830 @@
+{
+  "add_bos_token": true,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50265": {
+      "content": " pla",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50266": {
+      "content": "ubl",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50267": {
+      "content": "ely",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50268": {
+      "content": "ilm",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50269": {
+      "content": "cted",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50270": {
+      "content": "arly",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50271": {
+      "content": " publ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50272": {
+      "content": "overn",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50273": {
+      "content": "usic",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50274": {
+      "content": "ootball",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50275": {
+      "content": "istory",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50276": {
+      "content": "areer",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50277": {
+      "content": "stit",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50278": {
+      "content": "overnment",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50279": {
+      "content": "arri",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50280": {
+      "content": "owever",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50281": {
+      "content": "fess",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50282": {
+      "content": "ugust",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50283": {
+      "content": "ternational",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50284": {
+      "content": "tend",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50285": {
+      "content": "eptember",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50286": {
+      "content": "ctober",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50287": {
+      "content": " dif",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50288": {
+      "content": "pril",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50289": {
+      "content": " villa",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50290": {
+      "content": "’",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50291": {
+      "content": "ampionship",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50292": {
+      "content": "duced",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50293": {
+      "content": "ebru",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50294": {
+      "content": "ebruary",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50295": {
+      "content": "embers",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50296": {
+      "content": " poin",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50297": {
+      "content": "ivision",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50298": {
+      "content": "lack",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50299": {
+      "content": "ounc",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50300": {
+      "content": " Geor",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50301": {
+      "content": "arried",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50302": {
+      "content": "ouncil",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50303": {
+      "content": " consid",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50304": {
+      "content": "tended",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50305": {
+      "content": "loy",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50306": {
+      "content": " “",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50307": {
+      "content": "”",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50308": {
+      "content": " constru",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50309": {
+      "content": "eneral",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50310": {
+      "content": " Oly",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50311": {
+      "content": "adio",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50312": {
+      "content": "ecut",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50313": {
+      "content": " appoin",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50314": {
+      "content": " repla",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50315": {
+      "content": "ociety",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50316": {
+      "content": "forman",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50317": {
+      "content": "iforn",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50318": {
+      "content": "ifornia",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50319": {
+      "content": "stitute",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50320": {
+      "content": " emp",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50321": {
+      "content": "etwork",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50322": {
+      "content": " performan",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50323": {
+      "content": " examp",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50324": {
+      "content": " gradu",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50325": {
+      "content": " daugh",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50326": {
+      "content": "arliam",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50327": {
+      "content": " nov",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50328": {
+      "content": "arliament",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50329": {
+      "content": "gether",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50330": {
+      "content": " produc",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50331": {
+      "content": " Academ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50332": {
+      "content": "overnor",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50333": {
+      "content": "ecutive",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50334": {
+      "content": " tourn",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50335": {
+      "content": " becom",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50336": {
+      "content": " earl",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50337": {
+      "content": "embly",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50338": {
+      "content": "eck",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50339": {
+      "content": " sele",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50340": {
+      "content": "eep",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50341": {
+      "content": "thlet",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50342": {
+      "content": "fic",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50343": {
+      "content": "reland",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50344": {
+      "content": "emor",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50345": {
+      "content": "ularly",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50346": {
+      "content": " colla",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50347": {
+      "content": "incip",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50348": {
+      "content": "ollowing",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50349": {
+      "content": "eleb",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50350": {
+      "content": " Pla",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50351": {
+      "content": " Legit",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50352": {
+      "content": "oviet",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50353": {
+      "content": " Histor",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50354": {
+      "content": "retary",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50355": {
+      "content": " nomin",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50356": {
+      "content": "lant",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50357": {
+      "content": "zil",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50358": {
+      "content": " Profess",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50359": {
+      "content": " plann",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50360": {
+      "content": " Emp",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50361": {
+      "content": "stitut",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50362": {
+      "content": " Biography",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50363": {
+      "content": " anc",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50364": {
+      "content": "ecess",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "</s>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "errors": "replace",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "</s>"
+}

adapted_tokenizers/added-opt-eng/opt_1000-add_full-eng-opt/added_tokens.json

@@ -0,0 +1,997 @@
+{
+  "  ": 50959,
+  " !|": 50684,
+  " \"\",": 50713,
+  " \"\".": 50839,
+  " (,": 50383,
+  " (;": 50386,
+  " 1812": 51073,
+  " 1820": 51111,
+  " 1832": 51188,
+  " 1835": 51185,
+  " 1836": 51173,
+  " 1837": 51108,
+  " 1838": 51156,
+  " 1839": 51190,
+  " 1841": 51162,
+  " 1842": 51213,
+  " 1843": 51166,
+  " 1844": 51161,
+  " 1845": 51086,
+  " 1846": 51089,
+  " 1847": 51050,
+  " 1848": 50852,
+  " 1849": 51049,
+  " 1851": 50991,
+  " 1852": 50984,
+  " 1853": 51023,
+  " 1854": 50914,
+  " 1855": 50925,
+  " 1856": 50972,
+  " 1857": 50874,
+  " 1858": 50915,
+  " 1859": 50868,
+  " 1864": 50700,
+  " 1866": 50791,
+  " 1867": 50773,
+  " 1868": 50792,
+  " 1869": 50825,
+  " 1871": 50742,
+  " 1872": 50774,
+  " 1873": 50789,
+  " 1874": 50787,
+  " 1875": 50765,
+  " 1876": 50745,
+  " 1877": 50788,
+  " 1878": 50757,
+  " 1879": 50768,
+  " 1881": 50722,
+  " 1882": 50724,
+  " 1883": 50736,
+  " 1884": 50707,
+  " 1885": 50667,
+  " 1887": 50686,
+  " 1891": 50666,
+  " 1892": 50654,
+  " 1894": 50642,
+  " 2023": 50971,
+  " APC": 50997,
+  " ATTENTION": 50485,
+  " Abb": 50461,
+  " Academ": 50331,
+  " Achie": 51038,
+  " Addition": 50497,
+  " Adela": 50694,
+  " Agre": 51043,
+  " Agricult": 50597,
+  " Alab": 50528,
+  " Albanian": 50884,
+  " Alber": 50526,
+  " Albums": 50782,
+  " Aleks": 51021,
+  " Amaz": 50672,
+  " André": 50817,
+  " Angl": 50645,
+  " Anglican": 50754,
+  " Artillery": 50819,
+  " Atlant": 50387,
+  " Bagh": 51112,
+  " Ballet": 51181,
+  " Banglades": 50530,
+  " Barcel": 50635,
+  " Baronet": 50805,
+  " Batter": 51109,
+  " Bavaria": 51082,
+  " Bea": 50987,
+  " Belf": 50958,
+  " Belgrade": 50957,
+  " Bengali": 51257,
+  " Bey": 50691,
+  " Biography": 50362,
+  " Bla": 50476,
+  " Blo": 50688,
+  " Bonn": 50938,
+  " Bruns": 50806,
+  " Buhari": 50815,
+  " Bulld": 51157,
+  " CDP": 50939,
+  " COVID": 50494,
+  " Canton": 50869,
+  " Carne": 51066,
+  " Categ": 51047,
+  " Cauc": 51045,
+  " Cavalry": 50898,
+  " Ceramby": 50935,
+  " Cerambycidae": 50943,
+  " Cinc": 50692,
+  " Clif": 50940,
+  " Colle": 50838,
+  " Commer": 50554,
+  " Comple": 50661,
+  " Concer": 50830,
+  " Congreg": 51115,
+  " Constitu": 51069,
+  " Controvers": 51211,
+  " Copa": 50933,
+  " Cypr": 50904,
+  " Czechoslov": 50883,
+  " Darl": 51127,
+  " Demographics": 50543,
+  " Deuts": 51012,
+  " Diam": 50717,
+  " Diocese": 50640,
+  " Dipl": 51042,
+  " Distinguished": 51029,
+  " División": 51061,
+  " Doubles": 51205,
+  " Dougl": 50515,
+  " Eis": 50964,
+  " Eliz": 50413,
+  " Emp": 50360,
+  " Epis": 50970,
+  " Estonian": 51037,
+  " Etymology": 50983,
+  " Eurovision": 50947,
+  " Examp": 50809,
+  " Excell": 51206,
+  " Exped": 50835,
+  " Ferdin": 50855,
+  " Ferg": 51001,
+  " Fergus": 51085,
+  " Founded": 50857,
+  " Francesco": 51253,
+  " Fras": 50917,
+  " Frid": 50562,
+  " Gaelic": 51104,
+  " García": 51176,
+  " Gav": 51141,
+  " Geography": 50404,
+  " Geor": 50300,
+  " Georges": 51216,
+  " Gloucester": 50896,
+  " Gmina": 50525,
+  " Grammar": 51152,
+  " Gymn": 50965,
+  " Gó": 51186,
+  " Harv": 50462,
+  " Heinrich": 51120,
+  " Hern": 51046,
+  " Herzegovina": 50976,
+  " Histor": 50353,
+  " Honours": 50665,
+  " Hous": 50870,
+  " Independ": 50436,
+  " Indoor": 50999,
+  " Ira": 50448,
+  " Isab": 50818,
+  " Kann": 50998,
+  " Karnataka": 51183,
+  " Kras": 51218,
+  " Lagos": 50807,
+  " Lancashire": 50912,
+  " Legit": 50351,
+  " Leip": 51140,
+  " Leipzig": 51197,
+  " Leop": 50992,
+  " Lig": 50897,
+  " Lithuanian": 51160,
+  " Lut": 51136,
+  " Luxemb": 50923,
+  " Lé": 51117,
+  " MacD": 51222,
+  " Madh": 51128,
+  " Malay": 50778,
+  " Marl": 51135,
+  " Marri": 50986,
+  " María": 50934,
+  " Mater": 51231,
+  " Merced": 51133,
+  " Mey": 50708,
+  " Midd": 50843,
+  " Mikh": 51123,
+  " Minn": 50415,
+  " Moham": 50619,
+  " Mugabe": 51075,
+  " Muham": 50547,
+  " Municipality": 50564,
+  " Myan": 51039,
+  " Mā": 51096,
+  " NAIJ": 51098,
+  " Nacional": 51058,
+  " Napole": 50816,
+  " Natal": 51054,
+  " Niel": 51094,
+  " Nigerians": 50876,
+  " Nol": 51143,
+  " Northampton": 51254,
+  " Notable": 50452,
+  " Oblast": 50551,
+  " Oly": 50310,
+  " Outstanding": 50974,
+  " PDP": 51027,
+  " Pab": 51122,
+  " Paralymp": 50659,
+  " Paralympics": 50856,
+  " Patric": 51125,
+  " Phoen": 50689,
+  " Pitts": 50553,
+  " Pla": 50350,
+  " Pomer": 50929,
+  " Prad": 50578,
+  " Prefecture": 50932,
+  " Princip": 50685,
+  " Profess": 50358,
+  " Prote": 50569,
+  " Pseud": 51210,
+  " Publ": 50643,
+  " Pé": 50996,
+  " Railways": 50796,
+  " Raja": 51248,
+  " Ral": 50719,
+  " Rang": 50541,
+  " Reception": 50477,
+  " Rever": 51204,
+  " Rhine": 51072,
+  " Rif": 50848,
+  " Rol": 50618,
+  " Romanized": 50606,
+  " Rovers": 50891,
+  " Rup": 51243,
+  " Sacram": 51114,
+  " Sain": 50593,
+  " Santo": 51235,
+  " Saxony": 51240,
+  " Seminary": 51100,
+  " Sene": 51192,
+  " Serb": 50445,
+  " Sey": 50812,
+  " Shakes": 50893,
+  " Sib": 51132,
+  " Singles": 50561,
+  " Slovak": 51163,
+  " Spen": 50793,
+  " Stakes": 50837,
+  " Subsequently": 51084,
+  " Sustain": 50886,
+  " Swimming": 51017,
+  " Synopsis": 51146,
+  " São": 50718,
+  " Taxonomy": 51087,
+  " Teh": 50927,
+  " Telugu": 51195,
+  " Theod": 50682,
+  " Thir": 50752,
+  " Tod": 50418,
+  " Tourn": 50471,
+  " Treas": 50846,
+  " UCI": 51165,
+  " Underg": 51238,
+  " Urugu": 50859,
+  " Vat": 51113,
+  " Venez": 50594,
+  " Verm": 50638,
+  " Vinc": 50589,
+  " Voiv": 50460,
+  " Voivodeship": 50467,
+  " Warri": 50750,
+  " Wednes": 50710,
+  " Wimb": 51228,
+  " Yank": 50826,
+  " YouT": 50628,
+  " aband": 50449,
+  " abbrev": 50920,
+  " absol": 50794,
+  " adap": 50535,
+  " agricult": 50428,
+  " airfield": 51024,
+  " alcoh": 50625,
+  " alumin": 51053,
+  " anc": 50363,
+  " announc": 50963,
+  " appoin": 50313,
+  " apprec": 50775,
+  " apprent": 51011,
+  " arran": 50397,
+  " asp": 50427,
+  " attra": 50488,
+  " avo": 50785,
+  " bassist": 50953,
+  " battalions": 51233,
+  " becom": 50335,
+  " bey": 50508,
+  " bord": 50853,
+  " bordered": 51150,
+  " botan": 50941,
+  " bran": 50573,
+  " canc": 50613,
+  " canton": 50956,
+  " carri": 50479,
+  " catal": 50693,
+  " cerem": 50430,
+  " codice": 51025,
+  " colla": 50346,
+  " commune": 50495,
+  " competes": 51201,
+  " compla": 50731,
+  " complet": 50399,
+  " composers": 51142,
+  " compris": 50492,
+  " concer": 50394,
+  " confron": 50954,
+  " cong": 51044,
+  " conne": 50435,
+  " consid": 50303,
+  " consort": 51202,
+  " consp": 50711,
+  " constitut": 50704,
+  " constru": 50308,
+  " controll": 50760,
+  " cosm": 51007,
+  " craf": 51116,
+  " cricketer": 50650,
+  " danc": 50675,
+  " dang": 50657,
+  " datab": 50766,
+  " daugh": 50325,
+  " decla": 50405,
+  " declar": 51000,
+  " degrad": 51234,
+  " deliv": 50545,
+  " demonst": 50559,
+  " determ": 50365,
+  " dia": 50457,
+  " dif": 50287,
+  " diocese": 50924,
+  " dipl": 50469,
+  " disagre": 51081,
+  " disch": 50763,
+  " discip": 50663,
+  " discography": 51083,
+  " displa": 50568,
+  " doctorate": 50899,
+  " draf": 50616,
+  " earl": 50336,
+  " eigh": 50762,
+  " els": 50771,
+  " emigrated": 51064,
+  " emp": 50320,
+  " encoura": 50503,
+  " encourag": 51078,
+  " enfor": 50549,
+  " engra": 51159,
+  " enj": 50470,
+  " enl": 50557,
+  " ere": 50539,
+  " examp": 50323,
+  " excell": 50651,
+  " exchang": 50995,
+  " exclud": 50744,
+  " expla": 50406,
+  " extens": 50626,
+  " fier": 51230,
+  " financ": 51209,
+  " fla": 51068,
+  " forewings": 51207,
+  " freestyle": 50770,
+  " fron": 51026,
+  " gastropod": 50723,
+  " genera": 50926,
+  " geomet": 50740,
+  " gla": 51052,
+  " gradu": 50324,
+  " guar": 50764,
+  " hamlet": 50908,
+  " hap": 50453,
+  " headqu": 50407,
+  " herit": 50581,
+  " honours": 50936,
+  " householder": 50810,
+  " ille": 50536,
+  " immigr": 50558,
+  " impr": 50533,
+  " inaugurated": 51070,
+  " inducted": 50761,
+  " insc": 50592,
+  " inse": 50674,
+  " insp": 50379,
+  " inspe": 51227,
+  " institut": 50429,
+  " instru": 50523,
+  " interp": 50450,
+  " interse": 50518,
+  " irreg": 50980,
+  " journ": 50498,
+  " judg": 50781,
+  " libr": 50746,
+  " locomot": 50519,
+  " locomotive": 50844,
+  " locomotives": 50715,
+  " manor": 51013,
+  " marri": 51101,
+  " memb": 50905,
+  " merg": 50402,
+  " moll": 50664,
+  " mollusk": 50981,
+  " moths": 51252,
+  " nam": 50799,
+  " negot": 50501,
+  " nickn": 50577,
+  " ninet": 50730,
+  " nomin": 50355,
+  " nov": 50327,
+  " obl": 51015,
+  " orch": 51178,
+  " orchest": 50889,
+  " organiz": 50401,
+  " pandemic": 50566,
+  " parishes": 51196,
+  " partn": 50403,
+  " passeng": 50410,
+  " performan": 50322,
+  " pianist": 50833,
+  " pilgrim": 51134,
+  " pla": 50265,
+  " plann": 50359,
+  " playwright": 51129,
+  " poin": 50296,
+  " portfol": 51147,
+  " portra": 50811,
+  " posthum": 51048,
+  " predecess": 50649,
+  " premi": 50583,
+  " produc": 50330,
+  " promin": 50780,
+  " prosp": 50772,
+  " publ": 50271,
+  " purp": 50389,
+  " rebu": 50544,
+  " referend": 50841,
+  " regiments": 51225,
+  " reinfor": 50907,
+  " rejoin": 51137,
+  " remn": 51124,
+  " remov": 50373,
+  " reop": 50850,
+  " repla": 50314,
+  " resol": 50827,
+  " ri": 50534,
+  " rif": 50636,
+  " sacrif": 51032,
+  " samp": 50506,
+  " schem": 51110,
+  " schol": 50514,
+  " screenwriter": 51154,
+  " sculptor": 50951,
+  " seg": 50510,
+  " sele": 50339,
+  " shrub": 50824,
+  " sla": 50422,
+  " snails": 51059,
+  " soci": 50571,
+  " songwriter": 50749,
+  " spok": 50489,
+  " subd": 50624,
+  " subfamily": 50767,
+  " subsidi": 50610,
+  " subspecies": 50985,
+  " subtropical": 51092,
+  " suppor": 50511,
+  " surre": 50614,
+  " surrend": 51028,
+  " swimmer": 51242,
+  " swit": 50702,
+  " terminus": 50681,
+  " theore": 50582,
+  " thir": 50473,
+  " tonn": 51194,
+  " tourn": 50334,
+  " transp": 50863,
+  " trav": 50512,
+  " treas": 51106,
+  " tribut": 50560,
+  " tributary": 50648,
+  " trigg": 51138,
+  " troubl": 51093,
+  " underst": 50490,
+  " unexp": 50955,
+  " unincorporated": 50605,
+  " unsuccess": 50588,
+  " upgrad": 50620,
+  " urg": 50603,
+  " variab": 51232,
+  " vess": 50455,
+  " villa": 50289,
+  " vocalist": 50777,
+  " warri": 51006,
+  " wick": 50660,
+  " wickets": 51010,
+  " wides": 50615,
+  " wingspan": 50977,
+  " winn": 50368,
+  " worksh": 50690,
+  " Á": 50695,
+  " Ç": 51107,
+  " Č": 51005,
+  " Đ": 51022,
+  " İ": 51189,
+  " Ł": 50747,
+  " Ś": 51091,
+  " Š": 50669,
+  " Ž": 51090,
+  " ‘": 50468,
+  " “": 50306,
+  "\"\".": 51182,
+  ",”": 50585,
+  ".\\": 51199,
+  ".”": 50438,
+  "2021": 51067,
+  "::::\"": 50487,
+  "Amer": 50366,
+  "Billboard": 50507,
+  "CAA": 50437,
+  "EAD": 50584,
+  "Geor": 50822,
+  "Ital": 51035,
+  "Jos": 51148,
+  "Rol": 51220,
+  "SCO": 51071,
+  "TENT": 50482,
+  "TENTION": 50484,
+  "acional": 50877,
+  "adio": 50311,
+  "agre": 50677,
+  "airman": 50374,
+  "akk": 50982,
+  "alymp": 50646,
+  "ambig": 50580,
+  "ambiguation": 50595,
+  "amby": 50911,
+  "amese": 50705,
+  "amics": 50714,
+  "ampionship": 50291,
+  "ancell": 50641,
+  "ancellor": 50696,
+  "andin": 51153,
+  "anner": 50464,
+  "anning": 50491,
+  "anskrit": 51219,
+  "appe": 50769,
+  "appeared": 50871,
+  "aptist": 50598,
+  "apur": 50804,
+  "areer": 50276,
+  "arged": 50709,
+  "arked": 50697,
+  "arliam": 50326,
+  "arliament": 50328,
+  "arly": 50270,
+  "arri": 50279,
+  "arriage": 50378,
+  "arried": 50301,
+  "arrier": 50734,
+  "artered": 50779,
+  "artet": 50946,
+  "arting": 50671,
+  "arv": 50678,
+  "arvae": 50840,
+  "asan": 50612,
+  "ashire": 50894,
+  "asium": 51014,
+  "atab": 50662,
+  "atty": 51105,
+  "auf": 51198,
+  "auge": 50721,
+  "autiful": 50521,
+  "auty": 50611,
+  "avalry": 50556,
+  "avel": 50629,
+  "avian": 50832,
+  "avirus": 50990,
+  "bidae": 51079,
+  "brahim": 50973,
+  "brev": 50784,
+  "canic": 51051,
+  "ceae": 50994,
+  "celand": 50658,
+  "cement": 50392,
+  "chang": 50609,
+  "chestra": 50465,
+  "chez": 51018,
+  "cidae": 50885,
+  "cio": 51229,
+  "clesiast": 51118,
+  "clesiastical": 51179,
+  "coh": 50587,
+  "compass": 50741,
+  "cted": 50269,
+  "ctober": 50286,
+  "ctoral": 50412,
+  "ctorate": 50910,
+  "cts": 50480,
+  "designated": 51217,
+  "dess": 50872,
+  "died": 50733,
+  "diocese": 51239,
+  "dire": 50821,
+  "disambiguation": 50599,
+  "dorf": 50902,
+  "duce": 50442,
+  "duced": 50292,
+  "ducer": 51130,
+  "duces": 50890,
+  "ducing": 50555,
+  "ducted": 50670,
+  "ductive": 51126,
+  "eastern": 50845,
+  "ebru": 50293,
+  "ebruary": 50294,
+  "ecess": 50364,
+  "eck": 50338,
+  "ecting": 50496,
+  "ections": 51177,
+  "ects": 50375,
+  "ecut": 50312,
+  "ecution": 50516,
+  "ecutive": 50333,
+  "edding": 50579,
+  "eech": 50505,
+  "eep": 50340,
+  "eld": 50451,
+  "eleb": 50349,
+  "eler": 50531,
+  "elic": 51245,
+  "ellers": 50945,
+  "ellite": 50563,
+  "ely": 50267,
+  "emann": 51255,
+  "embers": 50295,
+  "emble": 50567,
+  "embly": 50337,
+  "emeter": 50447,
+  "emor": 50344,
+  "emorial": 50398,
+  "empor": 51172,
+  "eneral": 50309,
+  "enesis": 50922,
+  "enheim": 51149,
+  "enia": 50633,
+  "ennium": 51099,
+  "eo": 50656,
+  "eppe": 51121,
+  "eptember": 50285,
+  "erals": 51060,
+  "eras": 50790,
+  "erbai": 50572,
+  "erner": 51164,
+  "ersey": 50393,
+  "erted": 50673,
+  "erts": 51019,
+  "esota": 50454,
+  "estion": 51158,
+  "estock": 51174,
+  "estrian": 50930,
+  "ething": 50443,
+  "etwork": 50321,
+  "ević": 51215,
+  "evo": 51033,
+  "ewhere": 50680,
+  "ewise": 51214,
+  "families": 50864,
+  "ferences": 50411,
+  "fers": 50630,
+  "fess": 50281,
+  "fic": 50342,
+  "ficult": 50385,
+  "fielder": 50542,
+  "footballer": 50540,
+  "forman": 50316,
+  "fra": 50966,
+  "gend": 50423,
+  "gether": 50329,
+  "getown": 51237,
+  "habilit": 50944,
+  "hanced": 51063,
+  "hausen": 51236,
+  "heme": 50600,
+  "hev": 50829,
+  "histor": 50952,
+  "iab": 50499,
+  "iast": 50786,
+  "ibn": 50729,
+  "icine": 50426,
+  "icul": 51088,
+  "iec": 50441,
+  "ieces": 50493,
+  "ieuten": 50419,
+  "ieutenant": 50424,
+  "iffer": 50854,
+  "ifically": 50483,
+  "ifican": 50652,
+  "ificance": 50655,
+  "iformes": 51057,
+  "iforn": 50317,
+  "ifornia": 50318,
+  "igade": 50444,
+  "iggest": 50548,
+  "igital": 50390,
+  "ignated": 50834,
+  "ilarly": 50621,
+  "ilding": 50417,
+  "illiant": 51244,
+  "ilm": 50268,
+  "imensions": 51020,
+  "inae": 50644,
+  "inced": 50865,
+  "incip": 50347,
+  "includ": 50431,
+  "incorporated": 50591,
+  "inded": 51250,
+  "inental": 50676,
+  "inist": 50627,
+  "innati": 50699,
+  "inned": 51009,
+  "inum": 50738,
+  "ipur": 50937,
+  "iracy": 50836,
+  "irical": 51175,
+  "iscount": 51249,
+  "isión": 50931,
+  "islav": 51004,
+  "istory": 50275,
+  "itively": 51169,
+  "itro": 50813,
+  "ivision": 50297,
+  "ión": 50867,
+  "ić": 50367,
+  "ič": 50962,
+  "jord": 51155,
+  "kal": 51168,
+  "lac": 50538,
+  "lach": 51065,
+  "lacier": 50748,
+  "lack": 50298,
+  "lades": 50517,
+  "laimed": 50601,
+  "lair": 50900,
+  "lant": 50356,
+  "lave": 51170,
+  "lax": 50800,
+  "ledon": 51151,
+  "legiate": 50882,
+  "lend": 50596,
+  "leyball": 50604,
+  "licated": 50758,
+  "lications": 50668,
+  "licit": 50703,
+  "linary": 51055,
+  "loy": 50305,
+  "loyd": 50550,
+  "lywood": 50472,
+  "mina": 50486,
+  "minton": 51180,
+  "miral": 50602,
+  "mphony": 50639,
+  "mpt": 50631,
+  "nal": 50851,
+  "ndez": 50906,
+  "nez": 51031,
+  "nold": 50575,
+  "nolds": 51036,
+  "nowiki": 50753,
+  "ntario": 50434,
+  "née": 50687,
+  "occer": 50432,
+  "ociety": 50315,
+  "odeship": 50463,
+  "odia": 50892,
+  "oeing": 50901,
+  "oints": 50913,
+  "olished": 50509,
+  "ollowing": 50348,
+  "omat": 51203,
+  "omber": 50950,
+  "ommended": 50433,
+  "ommission": 51241,
+  "omot": 50466,
+  "onald": 50481,
+  "onlyinclude": 50647,
+  "onn": 50369,
+  "onnell": 51200,
+  "onsin": 50459,
+  "ootball": 50274,
+  "oque": 51008,
+  "ordin": 50475,
+  "orey": 50895,
+  "orms": 51171,
+  "orning": 50425,
+  "osely": 51256,
+  "osex": 50802,
+  "osm": 50565,
+  "osoph": 50416,
+  "osopher": 50756,
+  "osophical": 50975,
+  "osophy": 50478,
+  "ospitals": 50726,
+  "osy": 50820,
+  "osystem": 51131,
+  "otan": 50637,
+  "oucester": 50881,
+  "ounc": 50299,
+  "ouncil": 50302,
+  "ouncill": 50706,
+  "ouns": 51095,
+  "ounsel": 50683,
+  "ounted": 51003,
+  "ountry": 50921,
+  "oura": 50408,
+  "ourag": 50968,
+  "ourg": 50801,
+  "overn": 50272,
+  "overnment": 50278,
+  "overnor": 50332,
+  "oviet": 50352,
+  "ović": 50522,
+  "ovsk": 51226,
+  "ová": 51258,
+  "owever": 50280,
+  "owo": 50875,
+  "oyalty": 51191,
+  "oye": 50653,
+  "peare": 50888,
+  "pective": 50622,
+  "phab": 50847,
+  "pla": 50860,
+  "politician": 50988,
+  "poration": 50400,
+  "pow": 50823,
+  "pril": 50288,
+  "quir": 50727,
+  "quiry": 50909,
+  "quis": 51251,
+  "racks": 50849,
+  "racy": 50537,
+  "rague": 50737,
+  "randed": 50878,
+  "rapped": 50916,
+  "rapy": 50617,
+  "raska": 50679,
+  "rass": 50720,
+  "reater": 50395,
+  "reland": 50343,
+  "rena": 50590,
+  "retary": 50354,
+  "rews": 51223,
+  "ricket": 50396,
+  "ricketer": 50546,
+  "ricts": 50446,
+  "ricult": 50380,
+  "riculum": 50861,
+  "rif": 50421,
+  "rific": 50948,
+  "riptions": 50716,
+  "rizona": 50500,
+  "roat": 51184,
+  "roke": 50524,
+  "rong": 50574,
+  "ronze": 50439,
+  "ropical": 50414,
+  "ropod": 50634,
+  "roscop": 50979,
+  "rud": 50989,
+  "ryst": 50520,
+  "rystal": 50698,
+  "rí": 51080,
+  "seud": 50529,
+  "shan": 51002,
+  "ska": 50701,
+  "songwriter": 50808,
+  "sor": 50732,
+  "stance": 50743,
+  "stances": 50608,
+  "stit": 50277,
+  "stitu": 50887,
+  "stitut": 50361,
+  "stitute": 50319,
+  "stitutes": 50949,
+  "stitution": 50388,
+  "stitutional": 50725,
+  "surname": 50969,
+  "tage": 51016,
+  "teg": 50371,
+  "tend": 50284,
+  "tended": 50304,
+  "teneg": 50928,
+  "tenham": 51074,
+  "tense": 50831,
+  "terbury": 50903,
+  "ternational": 50283,
+  "ternet": 50456,
+  "thlet": 50341,
+  "thlete": 50712,
+  "thm": 50623,
+  "tingham": 50803,
+  "titled": 51167,
+  "tlement": 50842,
+  "took": 50978,
+  "ture": 50570,
+  "tym": 50751,
+  "ubl": 50266,
+  "ublican": 50382,
+  "ublin": 50502,
+  "uccess": 50504,
+  "uchy": 50961,
+  "uerto": 50527,
+  "ugby": 50372,
+  "ugust": 50282,
+  "uis": 50739,
+  "uisine": 51224,
+  "ularly": 50345,
+  "umbent": 50632,
+  "umberland": 50866,
+  "unar": 51077,
+  "unior": 50377,
+  "unnel": 50586,
+  "urday": 50513,
+  "urname": 50381,
+  "uros": 50858,
+  "usband": 50370,
+  "usic": 50273,
+  "ussels": 50828,
+  "usz": 51246,
+  "uxiliary": 51041,
+  "vanced": 50879,
+  "veill": 51103,
+  "veillance": 51119,
+  "veloped": 51034,
+  "velopment": 50391,
+  "vement": 50409,
+  "vements": 50552,
+  "vens": 50797,
+  "viv": 51187,
+  "wara": 51247,
+  "warf": 51208,
+  "weep": 50795,
+  "yal": 50440,
+  "ych": 50993,
+  "ycl": 51102,
+  "ydro": 50420,
+  "ygen": 50755,
+  "yler": 50783,
+  "ylvan": 50376,
+  "ylvania": 50384,
+  "ymn": 50474,
+  "zegov": 50918,
+  "zegovina": 50942,
+  "zil": 50357,
+  "ález": 51259,
+  "ández": 51097,
+  "ár": 50862,
+  "âte": 51212,
+  "är": 50873,
+  "ès": 51062,
+  "éd": 51221,
+  "él": 50759,
+  "ém": 51040,
+  "ód": 51030,
+  "ów": 50458,
+  "ør": 50919,
+  "ün": 50798,
+  "āb": 51145,
+  "ād": 51139,
+  "ān": 50814,
+  "ław": 50735,
+  "ń": 50532,
+  "ř": 50880,
+  "ś": 50776,
+  "ź": 51076,
+  "ż": 51056,
+  "ž": 50607,
+  "ș": 50576,
+  "ț": 50960,
+  "ə": 51144,
+  "’": 50290,
+  "“": 51193,
+  "”": 50307,
+  "”,": 50967,
+  "”.": 50728
+}