Upload tokenizer

README.md

@@ -11,8 +11,8 @@ model-index:
 - name: ethiopic-asr-characters
   results:
   - task:
-      name: Automatic Speech Recognition
       type: automatic-speech-recognition
+      name: Automatic Speech Recognition
     dataset:
       name: alffa_amharic
       type: alffa_amharic
@@ -20,9 +20,9 @@ model-index:
       split: None
       args: clean
     metrics:
-    - name: Wer
-      type: wer
+    - type: wer
       value: 0.29963354171157575
+      name: Wer
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You

added_tokens.json

@@ -1,6 +1,4 @@
 {
-  "</s>": 211,
-  "<s>": 210,
-  "[PAD]": 0,
-  "[UNK]": 1
+  "</s>": 271,
+  "<s>": 270
 }

special_tokens_map.json

@@ -1,6 +1,30 @@
 {
-  "bos_token": "<s>",
-  "eos_token": "</s>",
-  "pad_token": "[PAD]",
-  "unk_token": "[UNK]"
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": true,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": true,
+    "single_word": false
+  }
 }

vocab.json

@@ -2,271 +2,271 @@
   "[PAD]": 0,
   "[UNK]": 1,
   "|": 2,
-  "ኋ":3,
-  "ሏ":4,
-  "ሟ":5,
-  "ሯ":6,
-  "ሷ":7,
-  "ሿ":8,
-  "ቋ":9,
-  "ቧ":10,
-  "ቯ":11,
-  "ቷ":12,
-  "ቿ":13,
-  "ኗ":14,
-  "ኟ":15,
-  "ኳ":16,
-  "ዟ":17,
-  "ዧ":18,
-  "ዷ":19,
-  "ጇ":20,
-  "ጓ":21,
-  "ጧ":22,
-  "ጯ":23,
-  "ጷ":24,
-  "ጿ":25,
-  "ፏ":26,
-  "ፗ":27,
-  "ጔ":28,
-  "ኴ":29,
-  "ኌ":30,
-  "ጒ":31,
-  "ኲ":32,
-  "ኊ":33,
-  "ᎉ":34,
-  "ጕ":35,
-  "ፙ":36,
-  "ፚ":37,
-  "ᎊ":38,
-  "ᎋ":39,
-  "ፘ":40,
-  "ᎌ":41,
-  "ᎍ":42,
-  "ᎎ":43,
-  "ᎏ":44,
-  "ቘ":45,
-  "ቚ":46,
-  "ቛ":47,
-  "ቜ":48,
-  "ኧ":49,
-  "ኡ":50,
-  "ኢ":51,
-  "ኤ":52,
-  "እ":53,
-  "ኦ":54,
-  "ሓ":55,
-  "ሑ":56,
-  "ሒ":57,
-  "ሔ":58,
-  "ሖ":59,
-  "ለ":60,
-  "ሉ":61,
-  "ሊ":62,
-  "ላ":63,
-  "ሌ":64,
-  "ሎ":65,
-  "መ":66,
-  "ሙ":67,
-  "ሚ":68,
-  "ማ":69,
-  "ሜ":70,
-  "ሞ":71,
-  "ረ":72,
-  "ሩ":73,
-  "ሪ":74,
-  "ራ":75,
-  "ሬ":76,
-  "ሮ":77,
-  "ሰ":78,
-  "ሱ":79,
-  "ሲ":80,
-  "ሳ":81,
-  "ሴ":82,
-  "ሶ":83,
-  "ሸ":84,
-  "ሹ":85,
-  "ሺ":86,
-  "ሻ":87,
-  "ሼ":88,
-  "ሾ":89,
-  "ቀ":90,
-  "ቁ":91,
-  "ቂ":92,
-  "ቃ":93,
-  "ቄ":94,
-  "ቆ":95,
-  "ቌ":96,
-  "ቊ":97,
-  "ቍ":98,
-  "ቈ":99,
-  "ቐ":100,
-  "ቑ":101,
-  "ቒ":102,
-  "ቓ":103,
-  "ቖ":105,
-  "ቔ":104,
-  "በ":106,
-  "ቡ":107,
-  "ቢ":108,
-  "ባ":109,
-  "ቤ":110,
-  "ቦ":111,
-  "ቨ":112,
-  "ቩ":113,
-  "ቪ":114,
-  "ቫ":115,
-  "ቬ":116,
-  "ቮ":117,
-  "ተ":118,
-  "ቱ":119,
-  "ቲ":120,
-  "ታ":121,
-  "ቴ":122,
-  "ቶ":123,
-  "ቸ":124,
-  "ቹ":125,
-  "ቺ":126,
-  "ቻ":127,
-  "ቼ":128,
-  "ቾ":129,
-  "ነ":130,
-  "ኑ":131,
-  "ኒ":132,
-  "ና":133,
-  "ኔ":134,
-  "ኖ":135,
-  "ኘ":136,
-  "ኙ":137,
-  "ኚ":138,
-  "ኛ":139,
-  "ኜ":140,
-  "ኞ":141,
-  "ከ":142,
-  "ኩ":143,
-  "ኪ":144,
-  "ካ":145,
-  "ኬ":146,
-  "ኮ":147,
-  "ኰ":148,
-  "ኵ":149,
-  "ኸ":150,
-  "ኹ":151,
-  "ኺ":152,
-  "ኻ":153,
-  "ኼ":154,
-  "ኾ":155,
-  "ዀ":156,
-  "ዃ":157,
-  "ዄ":158,
-  "ዂ":159,
-  "ዅ":160,
-  "ወ":161,
-  "ዉ":162,
-  "ዊ":163,
-  "ዋ":164,
-  "ዌ":165,
-  "ዎ":166,
-  "ዘ":167,
-  "ዙ":168,
-  "ዚ":169,
-  "ዛ":170,
-  "ዜ":171,
-  "ዞ":172,
-  "ዠ":173,
-  "ዡ":174,
-  "ዢ":175,
-  "ዣ":176,
-  "ዤ":177,
-  "ዦ":178,
-  "የ":179,
-  "ዩ":180,
-  "ዪ":181,
-  "ያ":182,
-  "ዬ":183,
-  "ዮ":184,
-  "ደ":185,
-  "ዱ":186,
-  "ዲ":187,
-  "ዳ":188,
-  "ዴ":189,
-  "ዶ":190,
-  "ጀ":191,
-  "ጁ":192,
-  "ጂ":193,
-  "ጃ":194,
-  "ጄ":195,
-  "ጆ":196,
-  "ገ":197,
-  "ጉ":198,
-  "ጊ":199,
-  "ጋ":200,
-  "ጌ":201,
-  "ጎ":202,
-  "ጐ":203,
-  "ጠ":204,
-  "ጡ":205,
-  "ጢ":206,
-  "ጣ":207,
-  "ጤ":208,
-  "ጦ":209,
-  "ጨ":210,
-  "ጩ":211,
-  "ጪ":212,
-  "ጫ":213,
-  "ጬ":214,
-  "ጮ":215,
-  "ጰ":216,
-  "ጱ":217,
-  "ጲ":218,
-  "ጳ":219,
-  "ጴ":220,
-  "ጶ":221,
-  "ጸ":222,
-  "ጹ":223,
-  "ጺ":224,
-  "ጻ":225,
-  "ጼ":226,
-  "ጾ":227,
-  "ፈ":228,
-  "ፉ":229,
-  "ፊ":230,
-  "ፋ":231,
-  "ፌ":232,
-  "ፎ":233,
-  "ፐ":234,
-  "ፑ":235,
-  "ፒ":236,
-  "ፓ":237,
-  "ፔ":238,
-  "ፖ":239,
+  "ለ": 60,
+  "ሉ": 61,
+  "ሊ": 62,
+  "ላ": 63,
+  "ሌ": 64,
   "ል": 240,
+  "ሎ": 65,
+  "ሏ": 4,
+  "ሑ": 56,
+  "ሒ": 57,
+  "ሓ": 55,
+  "ሔ": 58,
   "ሕ": 241,
+  "ሖ": 59,
+  "መ": 66,
+  "ሙ": 67,
+  "ሚ": 68,
+  "ማ": 69,
+  "ሜ": 70,
   "ም": 242,
+  "ሞ": 71,
+  "ሟ": 5,
+  "ረ": 72,
+  "ሩ": 73,
+  "ሪ": 74,
+  "ራ": 75,
+  "ሬ": 76,
   "ር": 243,
+  "ሮ": 77,
+  "ሯ": 6,
+  "ሰ": 78,
+  "ሱ": 79,
+  "ሲ": 80,
+  "ሳ": 81,
+  "ሴ": 82,
   "ስ": 244,
+  "ሶ": 83,
+  "ሷ": 7,
+  "ሸ": 84,
+  "ሹ": 85,
+  "ሺ": 86,
+  "ሻ": 87,
+  "ሼ": 88,
   "ሽ": 245,
+  "ሾ": 89,
+  "ሿ": 8,
+  "ቀ": 90,
+  "ቁ": 91,
+  "ቂ": 92,
+  "ቃ": 93,
+  "ቄ": 94,
   "ቅ": 246,
+  "ቆ": 95,
+  "ቈ": 99,
+  "ቊ": 97,
+  "ቋ": 9,
+  "ቌ": 96,
+  "ቍ": 98,
+  "ቐ": 100,
+  "ቑ": 101,
+  "ቒ": 102,
+  "ቓ": 103,
+  "ቔ": 104,
   "ቕ": 247,
+  "ቖ": 105,
+  "ቘ": 45,
+  "ቚ": 46,
+  "ቛ": 47,
+  "ቜ": 48,
+  "በ": 106,
+  "ቡ": 107,
+  "ቢ": 108,
+  "ባ": 109,
+  "ቤ": 110,
   "ብ": 248,
+  "ቦ": 111,
+  "ቧ": 10,
+  "ቨ": 112,
+  "ቩ": 113,
+  "ቪ": 114,
+  "ቫ": 115,
+  "ቬ": 116,
   "ቭ": 249,
+  "ቮ": 117,
+  "ቯ": 11,
+  "ተ": 118,
+  "ቱ": 119,
+  "ቲ": 120,
+  "ታ": 121,
+  "ቴ": 122,
   "ት": 250,
+  "ቶ": 123,
+  "ቷ": 12,
+  "ቸ": 124,
+  "ቹ": 125,
+  "ቺ": 126,
+  "ቻ": 127,
+  "ቼ": 128,
   "ች": 251,
+  "ቾ": 129,
+  "ቿ": 13,
+  "ኊ": 33,
+  "ኋ": 3,
+  "ኌ": 30,
+  "ነ": 130,
+  "ኑ": 131,
+  "ኒ": 132,
+  "ና": 133,
+  "ኔ": 134,
   "ን": 252,
+  "ኖ": 135,
+  "ኗ": 14,
+  "ኘ": 136,
+  "ኙ": 137,
+  "ኚ": 138,
+  "ኛ": 139,
+  "ኜ": 140,
   "ኝ": 253,
+  "ኞ": 141,
+  "ኟ": 15,
+  "ኡ": 50,
+  "ኢ": 51,
   "ኣ": 254,
+  "ኤ": 52,
+  "እ": 53,
+  "ኦ": 54,
+  "ኧ": 49,
+  "ከ": 142,
+  "ኩ": 143,
+  "ኪ": 144,
+  "ካ": 145,
+  "ኬ": 146,
   "ክ": 255,
+  "ኮ": 147,
+  "ኰ": 148,
+  "ኲ": 32,
+  "ኳ": 16,
+  "ኴ": 29,
+  "ኵ": 149,
+  "ኸ": 150,
+  "ኹ": 151,
+  "ኺ": 152,
+  "ኻ": 153,
+  "ኼ": 154,
   "ኽ": 256,
+  "ኾ": 155,
+  "ዀ": 156,
+  "ዂ": 159,
+  "ዃ": 157,
+  "ዄ": 158,
+  "ዅ": 160,
+  "ወ": 161,
+  "ዉ": 162,
+  "ዊ": 163,
+  "ዋ": 164,
+  "ዌ": 165,
   "ው": 257,
+  "ዎ": 166,
+  "ዘ": 167,
+  "ዙ": 168,
+  "ዚ": 169,
+  "ዛ": 170,
+  "ዜ": 171,
   "ዝ": 258,
+  "ዞ": 172,
+  "ዟ": 17,
+  "ዠ": 173,
+  "ዡ": 174,
+  "ዢ": 175,
+  "ዣ": 176,
+  "ዤ": 177,
   "ዥ": 259,
+  "ዦ": 178,
+  "ዧ": 18,
+  "የ": 179,
+  "ዩ": 180,
+  "ዪ": 181,
+  "ያ": 182,
+  "ዬ": 183,
   "ይ": 260,
+  "ዮ": 184,
+  "ደ": 185,
+  "ዱ": 186,
+  "ዲ": 187,
+  "ዳ": 188,
+  "ዴ": 189,
   "ድ": 261,
+  "ዶ": 190,
+  "ዷ": 19,
+  "ጀ": 191,
+  "ጁ": 192,
+  "ጂ": 193,
+  "ጃ": 194,
+  "ጄ": 195,
   "ጅ": 262,
+  "ጆ": 196,
+  "ጇ": 20,
+  "ገ": 197,
+  "ጉ": 198,
+  "ጊ": 199,
+  "ጋ": 200,
+  "ጌ": 201,
   "ግ": 263,
+  "ጎ": 202,
+  "ጐ": 203,
+  "ጒ": 31,
+  "ጓ": 21,
+  "ጔ": 28,
+  "ጕ": 35,
+  "ጠ": 204,
+  "ጡ": 205,
+  "ጢ": 206,
+  "ጣ": 207,
+  "ጤ": 208,
   "ጥ": 264,
+  "ጦ": 209,
+  "ጧ": 22,
+  "ጨ": 210,
+  "ጩ": 211,
+  "ጪ": 212,
+  "ጫ": 213,
+  "ጬ": 214,
   "ጭ": 265,
+  "ጮ": 215,
+  "ጯ": 23,
+  "ጰ": 216,
+  "ጱ": 217,
+  "ጲ": 218,
+  "ጳ": 219,
+  "ጴ": 220,
   "ጵ": 266,
+  "ጶ": 221,
+  "ጷ": 24,
+  "ጸ": 222,
+  "ጹ": 223,
+  "ጺ": 224,
+  "ጻ": 225,
+  "ጼ": 226,
   "ጽ": 267,
+  "ጾ": 227,
+  "ጿ": 25,
+  "ፈ": 228,
+  "ፉ": 229,
+  "ፊ": 230,
+  "ፋ": 231,
+  "ፌ": 232,
   "ፍ": 268,
-  "ፕ": 269
+  "ፎ": 233,
+  "ፏ": 26,
+  "ፐ": 234,
+  "ፑ": 235,
+  "ፒ": 236,
+  "ፓ": 237,
+  "ፔ": 238,
+  "ፕ": 269,
+  "ፖ": 239,
+  "ፗ": 27,
+  "ፘ": 40,
+  "ፙ": 36,
+  "ፚ": 37,
+  "ᎉ": 34,
+  "ᎊ": 38,
+  "ᎋ": 39,
+  "ᎌ": 41,
+  "ᎍ": 42,
+  "ᎎ": 43,
+  "ᎏ": 44
 }