Update tokenizer

added_tokens.json

@@ -1,4 +1,4 @@
 {
-  "</s>": 34,
-  "<s>": 33
+  "</s>": 36,
+  "<s>": 35
 }

tokenizer_config.json

@@ -1,6 +1,6 @@
 {
   "added_tokens_decoder": {
-    "31": {
+    "33": {
       "content": "[UNK]",
       "lstrip": true,
       "normalized": false,
@@ -8,7 +8,7 @@
       "single_word": false,
       "special": false
     },
-    "32": {
+    "34": {
       "content": "[PAD]",
       "lstrip": true,
       "normalized": false,
@@ -16,7 +16,7 @@
       "single_word": false,
       "special": false
     },
-    "33": {
+    "35": {
       "content": "<s>",
       "lstrip": false,
       "normalized": false,
@@ -24,7 +24,7 @@
       "single_word": false,
       "special": true
     },
-    "34": {
+    "36": {
       "content": "</s>",
       "lstrip": false,
       "normalized": false,
@@ -40,7 +40,6 @@
   "extra_special_tokens": {},
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "[PAD]",
-  "processor_class": "Wav2Vec2BertProcessor",
   "replace_word_delimiter_char": " ",
   "target_lang": null,
   "tokenizer_class": "Wav2Vec2CTCTokenizer",

vocab.json

@@ -1,35 +1,37 @@
 {
-  "[PAD]": 32,
-  "[UNK]": 31,
+  "[PAD]": 34,
+  "[UNK]": 33,
   "a": 1,
   "b": 2,
-  "d": 3,
-  "e": 4,
-  "f": 5,
-  "g": 6,
-  "h": 7,
-  "i": 8,
-  "k": 9,
-  "l": 10,
-  "m": 11,
-  "n": 12,
-  "o": 13,
-  "p": 14,
-  "r": 15,
-  "s": 16,
-  "t": 17,
-  "u": 18,
-  "v": 19,
-  "w": 20,
-  "y": 21,
-  "z": 22,
+  "c": 3,
+  "d": 4,
+  "e": 5,
+  "f": 6,
+  "g": 7,
+  "h": 8,
+  "i": 9,
+  "k": 10,
+  "l": 11,
+  "m": 12,
+  "n": 13,
+  "o": 14,
+  "p": 15,
+  "q": 16,
+  "r": 17,
+  "s": 18,
+  "t": 19,
+  "u": 20,
+  "v": 21,
+  "w": 22,
+  "y": 23,
+  "z": 24,
   "|": 0,
-  "ã": 23,
-  "õ": 24,
-  "ĩ": 25,
-  "ũ": 26,
-  "ɛ": 27,
-  "ɩ": 28,
-  "ʋ": 29,
-  "ẽ": 30
+  "ã": 25,
+  "õ": 26,
+  "ĩ": 27,
+  "ũ": 28,
+  "ɛ": 29,
+  "ɩ": 30,
+  "ʋ": 31,
+  "ẽ": 32
 }