Upload tokenizer

added_tokens.json

@@ -1,4 +1,4 @@
 {
-  "</s>": 29,
-  "<s>": 28
+  "</s>": 25,
+  "<s>": 24
 }

tokenizer_config.json

@@ -1,6 +1,6 @@
 {
   "added_tokens_decoder": {
-    "26": {
+    "22": {
       "content": "[UNK]",
       "lstrip": true,
       "normalized": false,
@@ -8,7 +8,7 @@
       "single_word": false,
       "special": false
     },
-    "27": {
+    "23": {
       "content": "[PAD]",
       "lstrip": true,
       "normalized": false,
@@ -16,7 +16,7 @@
       "single_word": false,
       "special": false
     },
-    "28": {
+    "24": {
       "content": "<s>",
       "lstrip": false,
       "normalized": false,
@@ -24,7 +24,7 @@
       "single_word": false,
       "special": true
     },
-    "29": {
+    "25": {
       "content": "</s>",
       "lstrip": false,
       "normalized": false,
@@ -40,7 +40,6 @@
   "extra_special_tokens": {},
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "[PAD]",
-  "processor_class": "Wav2Vec2Processor",
   "replace_word_delimiter_char": " ",
   "target_lang": "awc",
   "tokenizer_class": "Wav2Vec2CTCTokenizer",

vocab.json

@@ -1,32 +1,28 @@
 {
   "awc": {
-    "\t": 0,
-    "\n": 1,
-    "[PAD]": 27,
-    "[UNK]": 26,
-    "a": 3,
-    "b": 4,
-    "c": 5,
-    "d": 6,
-    "e": 7,
-    "g": 8,
-    "h": 9,
-    "i": 10,
-    "j": 11,
-    "k": 12,
-    "l": 13,
-    "m": 14,
-    "n": 15,
-    "o": 16,
-    "p": 17,
-    "r": 18,
-    "s": 19,
-    "t": 20,
-    "u": 21,
-    "v": 22,
-    "w": 23,
-    "y": 24,
-    "|": 2,
-    "ï": 25
+    "[PAD]": 23,
+    "[UNK]": 22,
+    "a": 1,
+    "b": 2,
+    "d": 3,
+    "e": 4,
+    "g": 5,
+    "h": 6,
+    "i": 7,
+    "j": 8,
+    "k": 9,
+    "l": 10,
+    "m": 11,
+    "n": 12,
+    "o": 13,
+    "p": 14,
+    "r": 15,
+    "s": 16,
+    "t": 17,
+    "u": 18,
+    "w": 19,
+    "y": 20,
+    "|": 0,
+    "ï": 21
   }
 }