Upload tokenizer

README.md

@@ -1,18 +1,18 @@
 ---
-license: apache-2.0
 base_model: facebook/wav2vec2-base
-tags:
-- generated_from_trainer
 datasets:
 - common_voice_13_0
+license: apache-2.0
 metrics:
 - wer
+tags:
+- generated_from_trainer
 model-index:
 - name: wav2vec2-large-xls-r-vi-colab
   results:
   - task:
-      name: Automatic Speech Recognition
       type: automatic-speech-recognition
+      name: Automatic Speech Recognition
     dataset:
       name: common_voice_13_0
       type: common_voice_13_0
@@ -20,9 +20,9 @@ model-index:
       split: test[:50%]
       args: vi
     metrics:
-    - name: Wer
-      type: wer
+    - type: wer
       value: 1.0
+      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>": 96,
-  "<s>": 95
+  "</s>": 101,
+  "<s>": 100
 }

tokenizer_config.json

@@ -1,6 +1,6 @@
 {
   "added_tokens_decoder": {
-    "93": {
+    "98": {
       "content": "[UNK]",
       "lstrip": true,
       "normalized": false,
@@ -8,7 +8,7 @@
       "single_word": false,
       "special": false
     },
-    "94": {
+    "99": {
       "content": "[PAD]",
       "lstrip": true,
       "normalized": false,
@@ -16,7 +16,7 @@
       "single_word": false,
       "special": false
     },
-    "95": {
+    "100": {
       "content": "<s>",
       "lstrip": false,
       "normalized": false,
@@ -24,7 +24,7 @@
       "single_word": false,
       "special": true
     },
-    "96": {
+    "101": {
       "content": "</s>",
       "lstrip": false,
       "normalized": false,

vocab.json

@@ -1,6 +1,6 @@
 {
-  "[PAD]": 94,
-  "[UNK]": 93,
+  "[PAD]": 99,
+  "[UNK]": 98,
   "a": 1,
   "b": 2,
   "c": 3,
@@ -26,72 +26,77 @@
   "w": 23,
   "x": 24,
   "y": 25,
+  "z": 26,
   "|": 0,
-  "à": 26,
-  "á": 27,
-  "â": 28,
-  "ã": 29,
-  "è": 30,
-  "é": 31,
-  "ê": 32,
-  "ì": 33,
-  "í": 34,
-  "ò": 35,
-  "ó": 36,
-  "ô": 37,
-  "õ": 38,
-  "ù": 39,
-  "ú": 40,
-  "ý": 41,
-  "ă": 42,
-  "đ": 43,
-  "ĩ": 44,
-  "ũ": 45,
-  "ơ": 46,
-  "ư": 47,
-  "ạ": 48,
-  "ả": 49,
-  "ấ": 50,
-  "ầ": 51,
-  "ẩ": 52,
-  "ẫ": 53,
-  "ậ": 54,
-  "ắ": 55,
-  "ằ": 56,
-  "ẳ": 57,
-  "ẵ": 58,
-  "ặ": 59,
-  "ẹ": 60,
-  "ẻ": 61,
-  "ẽ": 62,
-  "ế": 63,
-  "ề": 64,
-  "ể": 65,
-  "ễ": 66,
-  "ệ": 67,
-  "ỉ": 68,
-  "ị": 69,
-  "ọ": 70,
-  "ỏ": 71,
-  "ố": 72,
-  "ồ": 73,
-  "ổ": 74,
-  "ỗ": 75,
-  "ộ": 76,
-  "ớ": 77,
-  "ờ": 78,
-  "ở": 79,
-  "ỡ": 80,
-  "ợ": 81,
-  "ụ": 82,
-  "ủ": 83,
-  "ứ": 84,
-  "ừ": 85,
-  "ử": 86,
-  "ữ": 87,
-  "ự": 88,
-  "ỳ": 89,
-  "ỵ": 90,
-  "ỷ": 91,
-  "ỹ": 92
+  "à": 27,
+  "á": 28,
+  "â": 29,
+  "ã": 30,
+  "è": 31,
+  "é": 32,
+  "ê": 33,
+  "ì": 34,
+  "í": 35,
+  "ò": 36,
+  "ó": 37,
+  "ô": 38,
+  "õ": 39,
+  "ù": 40,
+  "ú": 41,
+  "ý": 42,
+  "ă": 43,
+  "đ": 44,
+  "ĩ": 45,
+  "ũ": 46,
+  "ơ": 47,
+  "ư": 48,
+  "̀": 49,
+  "́": 50,
+  "̃": 51,
+  "̉": 52,
+  "̣": 53,
+  "ạ": 54,
+  "ả": 55,
+  "ấ": 56,
+  "ầ": 57,
+  "ẩ": 58,
+  "ẫ": 59,
+  "ậ": 60,
+  "ắ": 61,
+  "ằ": 62,
+  "ẵ": 63,
+  "ặ": 64,
+  "ẹ": 65,
+  "ẻ": 66,
+  "ẽ": 67,
+  "ế": 68,
+  "ề": 69,
+  "ể": 70,
+  "ễ": 71,
+  "ệ": 72,
+  "ỉ": 73,
+  "ị": 74,
+  "ọ": 75,
+  "ỏ": 76,
+  "ố": 77,
+  "ồ": 78,
+  "ổ": 79,
+  "ỗ": 80,
+  "ộ": 81,
+  "ớ": 82,
+  "ờ": 83,
+  "ở": 84,
+  "ỡ": 85,
+  "ợ": 86,
+  "ụ": 87,
+  "ủ": 88,
+  "ứ": 89,
+  "ừ": 90,
+  "ử": 91,
+  "ữ": 92,
+  "ự": 93,
+  "ỳ": 94,
+  "ỷ": 95,
+  "ỹ": 96,
+  "​": 97
 }