Upload tokenizer

README.md

@@ -1,8 +1,8 @@
 ---
 license: apache-2.0
-base_model: facebook/wav2vec2-large-xlsr-53
 tags:
 - generated_from_trainer
+base_model: facebook/wav2vec2-large-xlsr-53
 datasets:
 - common_voice_17_0
 metrics:
@@ -11,8 +11,8 @@ model-index:
 - name: xlsr-am-adap-phon
   results:
   - task:
-      name: Automatic Speech Recognition
       type: automatic-speech-recognition
+      name: Automatic Speech Recognition
     dataset:
       name: common_voice_17_0
       type: common_voice_17_0
@@ -20,9 +20,9 @@ model-index:
       split: validation
       args: am
     metrics:
-    - name: Wer
-      type: wer
+    - type: wer
       value: 0.9302421009437833
+      name: Wer
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You

added_tokens.json

@@ -1,4 +1,4 @@
 {
-  "</s>": 231,
-  "<s>": 230
+  "</s>": 240,
+  "<s>": 239
 }

tokenizer_config.json

@@ -1,6 +1,6 @@
 {
   "added_tokens_decoder": {
-    "228": {
+    "237": {
       "content": "[UNK]",
       "lstrip": true,
       "normalized": false,
@@ -8,7 +8,7 @@
       "single_word": false,
       "special": false
     },
-    "229": {
+    "238": {
       "content": "[PAD]",
       "lstrip": true,
       "normalized": false,
@@ -16,7 +16,7 @@
       "single_word": false,
       "special": false
     },
-    "230": {
+    "239": {
       "content": "<s>",
       "lstrip": false,
       "normalized": false,
@@ -24,7 +24,7 @@
       "single_word": false,
       "special": true
     },
-    "231": {
+    "240": {
       "content": "</s>",
       "lstrip": false,
       "normalized": false,

vocab.json

@@ -1,6 +1,6 @@
 {
-  "[PAD]": 229,
-  "[UNK]": 228,
+  "[PAD]": 238,
+  "[UNK]": 237,
   "|": 0,
   "ሀ": 1,
   "ሁ": 2,
@@ -77,156 +77,165 @@
   "ቨ": 73,
   "ቪ": 74,
   "ቫ": 75,
-  "ቭ": 76,
-  "ቮ": 77,
-  "ተ": 78,
-  "ቱ": 79,
-  "ቲ": 80,
-  "ታ": 81,
-  "ቴ": 82,
-  "ት": 83,
-  "ቶ": 84,
-  "ቷ": 85,
-  "ቸ": 86,
-  "ቹ": 87,
-  "ቺ": 88,
-  "ቻ": 89,
-  "ቼ": 90,
-  "ች": 91,
-  "ቾ": 92,
-  "ቿ": 93,
-  "ኃ": 94,
-  "ኅ": 95,
-  "ኋ": 96,
-  "ነ": 97,
-  "ኑ": 98,
-  "ኒ": 99,
-  "ና": 100,
-  "ኔ": 101,
-  "ን": 102,
-  "ኖ": 103,
-  "ኗ": 104,
-  "ኘ": 105,
-  "ኙ": 106,
-  "ኛ": 107,
-  "ኝ": 108,
-  "ኞ": 109,
-  "ኟ": 110,
-  "አ": 111,
-  "ኡ": 112,
-  "ኢ": 113,
-  "ኣ": 114,
-  "ኤ": 115,
-  "እ": 116,
-  "ኦ": 117,
-  "ከ": 118,
-  "ኩ": 119,
-  "ኪ": 120,
-  "ካ": 121,
-  "ኬ": 122,
-  "ክ": 123,
-  "ኮ": 124,
-  "ኳ": 125,
-  "ኸ": 126,
-  "ኽ": 127,
-  "ወ": 128,
-  "ዊ": 129,
-  "ዋ": 130,
-  "ዌ": 131,
-  "ው": 132,
-  "ዎ": 133,
-  "ዐ": 134,
-  "ዑ": 135,
-  "ዒ": 136,
-  "ዓ": 137,
-  "ዕ": 138,
-  "ዖ": 139,
-  "ዘ": 140,
-  "ዙ": 141,
-  "ዚ": 142,
-  "ዛ": 143,
-  "ዜ": 144,
-  "ዝ": 145,
-  "ዞ": 146,
-  "ዢ": 147,
-  "ዣ": 148,
-  "ዤ": 149,
-  "ዥ": 150,
-  "ዦ": 151,
-  "የ": 152,
-  "ዩ": 153,
-  "ያ": 154,
-  "ዬ": 155,
-  "ይ": 156,
-  "ዮ": 157,
-  "ደ": 158,
-  "ዱ": 159,
-  "ዲ": 160,
-  "ዳ": 161,
-  "ዴ": 162,
-  "ድ": 163,
-  "ዶ": 164,
-  "ዷ": 165,
-  "ጀ": 166,
-  "ጁ": 167,
-  "ጂ": 168,
-  "ጃ": 169,
-  "ጄ": 170,
-  "ጅ": 171,
-  "ጆ": 172,
-  "ገ": 173,
-  "ጉ": 174,
-  "ጊ": 175,
-  "ጋ": 176,
-  "ጌ": 177,
-  "ግ": 178,
-  "ጎ": 179,
-  "ጓ": 180,
-  "ጠ": 181,
-  "ጡ": 182,
-  "ጢ": 183,
-  "ጣ": 184,
-  "ጤ": 185,
-  "ጥ": 186,
-  "ጦ": 187,
-  "ጧ": 188,
-  "ጨ": 189,
-  "ጩ": 190,
-  "ጪ": 191,
-  "ጫ": 192,
-  "ጬ": 193,
-  "ጭ": 194,
-  "ጮ": 195,
-  "ጲ": 196,
-  "ጴ": 197,
-  "ጵ": 198,
-  "ጶ": 199,
-  "ጸ": 200,
-  "ጹ": 201,
-  "ጺ": 202,
-  "ጻ": 203,
-  "ጽ": 204,
-  "ጾ": 205,
-  "ጿ": 206,
-  "ፀ": 207,
-  "ፁ": 208,
-  "ፃ": 209,
-  "ፅ": 210,
-  "ፈ": 211,
-  "ፉ": 212,
-  "ፊ": 213,
-  "ፋ": 214,
-  "ፌ": 215,
-  "ፍ": 216,
-  "ፎ": 217,
-  "ፏ": 218,
-  "ፑ": 219,
-  "ፒ": 220,
-  "ፓ": 221,
-  "ፔ": 222,
-  "ፕ": 223,
-  "ፖ": 224,
-  "፡": 225,
-  "።": 226,
-  "፣": 227
+  "ቬ": 76,
+  "ቭ": 77,
+  "ቮ": 78,
+  "ተ": 79,
+  "ቱ": 80,
+  "ቲ": 81,
+  "ታ": 82,
+  "ቴ": 83,
+  "ት": 84,
+  "ቶ": 85,
+  "ቷ": 86,
+  "ቸ": 87,
+  "ቹ": 88,
+  "ቺ": 89,
+  "ቻ": 90,
+  "ቼ": 91,
+  "ች": 92,
+  "ቾ": 93,
+  "ቿ": 94,
+  "ኃ": 95,
+  "ኅ": 96,
+  "ኋ": 97,
+  "ነ": 98,
+  "ኑ": 99,
+  "ኒ": 100,
+  "ና": 101,
+  "ኔ": 102,
+  "ን": 103,
+  "ኖ": 104,
+  "ኗ": 105,
+  "ኘ": 106,
+  "ኙ": 107,
+  "ኛ": 108,
+  "ኜ": 109,
+  "ኝ": 110,
+  "ኞ": 111,
+  "ኟ": 112,
+  "አ": 113,
+  "ኡ": 114,
+  "ኢ": 115,
+  "ኣ": 116,
+  "ኤ": 117,
+  "እ": 118,
+  "ኦ": 119,
+  "ከ": 120,
+  "ኩ": 121,
+  "ኪ": 122,
+  "ካ": 123,
+  "ኬ": 124,
+  "ክ": 125,
+  "ኮ": 126,
+  "ኳ": 127,
+  "ኸ": 128,
+  "ኹ": 129,
+  "ኽ": 130,
+  "ወ": 131,
+  "ዊ": 132,
+  "ዋ": 133,
+  "ዌ": 134,
+  "ው": 135,
+  "ዎ": 136,
+  "ዐ": 137,
+  "ዑ": 138,
+  "ዒ": 139,
+  "ዓ": 140,
+  "ዔ": 141,
+  "ዕ": 142,
+  "ዖ": 143,
+  "ዘ": 144,
+  "ዙ": 145,
+  "ዚ": 146,
+  "ዛ": 147,
+  "ዜ": 148,
+  "ዝ": 149,
+  "ዞ": 150,
+  "ዟ": 151,
+  "ዢ": 152,
+  "ዣ": 153,
+  "ዤ": 154,
+  "ዥ": 155,
+  "ዦ": 156,
+  "የ": 157,
+  "ዩ": 158,
+  "ያ": 159,
+  "ዬ": 160,
+  "ይ": 161,
+  "ዮ": 162,
+  "ደ": 163,
+  "ዱ": 164,
+  "ዲ": 165,
+  "ዳ": 166,
+  "ዴ": 167,
+  "ድ": 168,
+  "ዶ": 169,
+  "ዷ": 170,
+  "ዽ": 171,
+  "ጀ": 172,
+  "ጁ": 173,
+  "ጂ": 174,
+  "ጃ": 175,
+  "ጄ": 176,
+  "ጅ": 177,
+  "ጆ": 178,
+  "ጇ": 179,
+  "ገ": 180,
+  "ጉ": 181,
+  "ጊ": 182,
+  "ጋ": 183,
+  "ጌ": 184,
+  "ግ": 185,
+  "ጎ": 186,
+  "ጓ": 187,
+  "ጠ": 188,
+  "ጡ": 189,
+  "ጢ": 190,
+  "ጣ": 191,
+  "ጤ": 192,
+  "ጥ": 193,
+  "ጦ": 194,
+  "ጧ": 195,
+  "ጨ": 196,
+  "ጩ": 197,
+  "ጪ": 198,
+  "ጫ": 199,
+  "ጬ": 200,
+  "ጭ": 201,
+  "ጮ": 202,
+  "ጲ": 203,
+  "ጴ": 204,
+  "ጵ": 205,
+  "ጶ": 206,
+  "ጸ": 207,
+  "ጹ": 208,
+  "ጺ": 209,
+  "ጻ": 210,
+  "ጽ": 211,
+  "ጾ": 212,
+  "ጿ": 213,
+  "ፀ": 214,
+  "ፁ": 215,
+  "ፃ": 216,
+  "ፅ": 217,
+  "ፈ": 218,
+  "ፉ": 219,
+  "ፊ": 220,
+  "ፋ": 221,
+  "ፌ": 222,
+  "ፍ": 223,
+  "ፎ": 224,
+  "ፏ": 225,
+  "ፐ": 226,
+  "ፑ": 227,
+  "ፒ": 228,
+  "ፓ": 229,
+  "ፔ": 230,
+  "ፕ": 231,
+  "ፖ": 232,
+  "፡": 233,
+  "።": 234,
+  "፣": 235,
+  "’": 236
 }