Upload tokenizer

README.md

@@ -1,8 +1,8 @@
 ---
 license: apache-2.0
-base_model: facebook/wav2vec2-xls-r-300m
 tags:
 - generated_from_trainer
+base_model: facebook/wav2vec2-xls-r-300m
 datasets:
 - make_dataset
 model-index:

added_tokens.json

@@ -1,4 +1,4 @@
 {
-  "</s>": 61,
-  "<s>": 60
+  "</s>": 52,
+  "<s>": 51
 }

tokenizer_config.json

@@ -1,6 +1,6 @@
 {
   "added_tokens_decoder": {
-    "58": {
+    "49": {
       "content": "[UNK]",
       "lstrip": true,
       "normalized": false,
@@ -8,7 +8,7 @@
       "single_word": false,
       "special": false
     },
-    "59": {
+    "50": {
       "content": "[PAD]",
       "lstrip": true,
       "normalized": false,
@@ -16,7 +16,7 @@
       "single_word": false,
       "special": false
     },
-    "60": {
+    "51": {
       "content": "<s>",
       "lstrip": false,
       "normalized": false,
@@ -24,7 +24,7 @@
       "single_word": false,
       "special": true
     },
-    "61": {
+    "52": {
       "content": "</s>",
       "lstrip": false,
       "normalized": false,

vocab.json

@@ -1,62 +1,53 @@
 {
-  "0": 1,
-  "1": 2,
-  "2": 3,
-  "3": 4,
-  "4": 5,
-  "5": 6,
-  "6": 7,
-  "7": 8,
-  "8": 9,
-  "9": 10,
-  "[PAD]": 59,
-  "[UNK]": 58,
+  "[PAD]": 50,
+  "[UNK]": 49,
   "|": 0,
-  "ㄱ": 11,
-  "ㄲ": 12,
-  "ㄳ": 13,
-  "ㄴ": 14,
-  "ㄵ": 15,
-  "ㄶ": 16,
-  "ㄷ": 17,
-  "ㄸ": 18,
-  "ㄹ": 19,
-  "ㄺ": 20,
-  "ㄼ": 21,
-  "ㅀ": 22,
-  "ㅁ": 23,
-  "ㅂ": 24,
-  "ㅃ": 25,
-  "ㅄ": 26,
-  "ㅅ": 27,
-  "ㅆ": 28,
-  "ㅇ": 29,
-  "ㅈ": 30,
-  "ㅉ": 31,
-  "ㅊ": 32,
-  "ㅋ": 33,
-  "ㅌ": 34,
-  "ㅍ": 35,
-  "ㅎ": 36,
-  "ㅏ": 37,
-  "ㅐ": 38,
-  "ㅑ": 39,
-  "ㅒ": 40,
-  "ㅓ": 41,
-  "ㅔ": 42,
-  "ㅕ": 43,
-  "ㅖ": 44,
-  "ㅗ": 45,
-  "ㅘ": 46,
-  "ㅙ": 47,
-  "ㅚ": 48,
-  "ㅛ": 49,
-  "ㅜ": 50,
-  "ㅝ": 51,
-  "ㅞ": 52,
-  "ㅟ": 53,
-  "ㅠ": 54,
-  "ㅡ": 55,
-  "ㅢ": 56,
-  "ㅣ": 57
+  "ㄱ": 1,
+  "ㄲ": 2,
+  "ㄳ": 3,
+  "ㄴ": 4,
+  "ㄵ": 5,
+  "ㄶ": 6,
+  "ㄷ": 7,
+  "ㄸ": 8,
+  "ㄹ": 9,
+  "ㄺ": 10,
+  "ㄻ": 11,
+  "ㄼ": 12,
+  "ㅀ": 13,
+  "ㅁ": 14,
+  "ㅂ": 15,
+  "ㅃ": 16,
+  "ㅄ": 17,
+  "ㅅ": 18,
+  "ㅆ": 19,
+  "ㅇ": 20,
+  "ㅈ": 21,
+  "ㅉ": 22,
+  "ㅊ": 23,
+  "ㅋ": 24,
+  "ㅌ": 25,
+  "ㅍ": 26,
+  "ㅎ": 27,
+  "ㅏ": 28,
+  "ㅐ": 29,
+  "ㅑ": 30,
+  "ㅒ": 31,
+  "ㅓ": 32,
+  "ㅔ": 33,
+  "ㅕ": 34,
+  "ㅖ": 35,
+  "ㅗ": 36,
+  "ㅘ": 37,
+  "ㅙ": 38,
+  "ㅚ": 39,
+  "ㅛ": 40,
+  "ㅜ": 41,
+  "ㅝ": 42,
+  "ㅞ": 43,
+  "ㅟ": 44,
+  "ㅠ": 45,
+  "ㅡ": 46,
+  "ㅢ": 47,
+  "ㅣ": 48
 }