Upload tokenizer

README.md

@@ -1,7 +1,7 @@
 ---
-base_model: batoula187/wav2vec2-large-xls-r-300m-arabic-colab
 tags:
 - generated_from_trainer
+base_model: batoula187/wav2vec2-large-xls-r-300m-arabic-colab
 datasets:
 - common_voice_12_0
 metrics:
@@ -10,8 +10,8 @@ model-index:
 - name: wav2vec2-large-xls-r-300m-arabic-colab
   results:
   - task:
-      name: Automatic Speech Recognition
       type: automatic-speech-recognition
+      name: Automatic Speech Recognition
     dataset:
       name: common_voice_12_0
       type: common_voice_12_0
@@ -19,9 +19,9 @@ model-index:
       split: test[:10%]
       args: ar
     metrics:
-    - name: Wer
-      type: wer
+    - type: wer
       value: 0.7661710754972002
+      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>": 67,
-  "<s>": 66
+  "</s>": 90,
+  "<s>": 89
 }

tokenizer_config.json

@@ -1,6 +1,6 @@
 {
   "added_tokens_decoder": {
-    "64": {
+    "87": {
       "content": "[UNK]",
       "lstrip": true,
       "normalized": false,
@@ -8,7 +8,7 @@
       "single_word": false,
       "special": false
     },
-    "65": {
+    "88": {
       "content": "[PAD]",
       "lstrip": true,
       "normalized": false,
@@ -16,7 +16,7 @@
       "single_word": false,
       "special": false
     },
-    "66": {
+    "89": {
       "content": "<s>",
       "lstrip": false,
       "normalized": false,
@@ -24,7 +24,7 @@
       "single_word": false,
       "special": true
     },
-    "67": {
+    "90": {
       "content": "</s>",
       "lstrip": false,
       "normalized": false,

vocab.json

@@ -1,68 +1,91 @@
 {
-  "[PAD]": 65,
-  "[UNK]": 64,
-  "a": 1,
-  "b": 2,
-  "d": 3,
-  "e": 4,
-  "i": 5,
-  "n": 6,
-  "r": 7,
-  "t": 8,
-  "v": 9,
-  "y": 10,
+  "[PAD]": 88,
+  "[UNK]": 87,
+  "_": 1,
+  "a": 2,
+  "b": 3,
+  "c": 4,
+  "d": 5,
+  "e": 6,
+  "f": 7,
+  "g": 8,
+  "h": 9,
+  "i": 10,
+  "l": 11,
+  "m": 12,
+  "n": 13,
+  "o": 14,
+  "r": 15,
+  "s": 16,
+  "t": 17,
+  "u": 18,
+  "v": 19,
+  "w": 20,
+  "y": 21,
   "|": 0,
-  "،": 11,
-  "؛": 12,
-  "؟": 13,
-  "ء": 14,
-  "آ": 15,
-  "أ": 16,
-  "ؤ": 17,
-  "إ": 18,
-  "ئ": 19,
-  "ا": 20,
-  "ب": 21,
-  "ة": 22,
-  "ت": 23,
-  "ث": 24,
-  "ج": 25,
-  "ح": 26,
-  "خ": 27,
-  "د": 28,
-  "ذ": 29,
-  "ر": 30,
-  "ز": 31,
-  "س": 32,
-  "ش": 33,
-  "ص": 34,
-  "ض": 35,
-  "ط": 36,
-  "ظ": 37,
-  "ع": 38,
-  "غ": 39,
-  "ـ": 40,
-  "ف": 41,
-  "ق": 42,
-  "ك": 43,
-  "ل": 44,
-  "م": 45,
-  "ن": 46,
-  "ه": 47,
-  "و": 48,
-  "ى": 49,
-  "ي": 50,
-  "ً": 51,
-  "ٌ": 52,
-  "ٍ": 53,
-  "َ": 54,
-  "ُ": 55,
-  "ِ": 56,
-  "ّ": 57,
-  "ْ": 58,
-  "ٰ": 59,
-  "چ": 60,
-  "ک": 61,
-  "ی": 62,
-  "ۖ": 63
+  "«": 22,
+  "»": 23,
+  "،": 24,
+  "؛": 25,
+  "؟": 26,
+  "ء": 27,
+  "آ": 28,
+  "أ": 29,
+  "ؤ": 30,
+  "إ": 31,
+  "ئ": 32,
+  "ا": 33,
+  "ب": 34,
+  "ة": 35,
+  "ت": 36,
+  "ث": 37,
+  "ج": 38,
+  "ح": 39,
+  "خ": 40,
+  "د": 41,
+  "ذ": 42,
+  "ر": 43,
+  "ز": 44,
+  "س": 45,
+  "ش": 46,
+  "ص": 47,
+  "ض": 48,
+  "ط": 49,
+  "ظ": 50,
+  "ع": 51,
+  "غ": 52,
+  "ـ": 53,
+  "ف": 54,
+  "ق": 55,
+  "ك": 56,
+  "ل": 57,
+  "م": 58,
+  "ن": 59,
+  "ه": 60,
+  "و": 61,
+  "ى": 62,
+  "ي": 63,
+  "ً": 64,
+  "ٌ": 65,
+  "ٍ": 66,
+  "َ": 67,
+  "ُ": 68,
+  "ِ": 69,
+  "ّ": 70,
+  "ْ": 71,
+  "ٰ": 72,
+  "چ": 73,
+  "ڨ": 74,
+  "ک": 75,
+  "ھ": 76,
+  "ی": 77,
+  "ۖ": 78,
+  "ۗ": 79,
+  "ۘ": 80,
+  "ۚ": 81,
+  "ۛ": 82,
+  "—": 83,
+  "☭": 84,
+  "ﺃ": 85,
+  "ﻻ": 86
 }