Upload tokenizer

added_tokens.json

@@ -1,4 +1,4 @@
 {
-  "</s>": 11,
-  "<s>": 10
+  "</s>": 7,
+  "<s>": 6
 }

tokenizer_config.json

@@ -1,6 +1,6 @@
 {
   "added_tokens_decoder": {
-    "8": {
+    "4": {
       "content": "[UNK]",
       "lstrip": true,
       "normalized": false,
@@ -8,7 +8,7 @@
       "single_word": false,
       "special": false
     },
-    "9": {
+    "5": {
       "content": "[PAD]",
       "lstrip": true,
       "normalized": false,
@@ -16,7 +16,7 @@
       "single_word": false,
       "special": false
     },
-    "10": {
+    "6": {
       "content": "<s>",
       "lstrip": false,
       "normalized": false,
@@ -24,7 +24,7 @@
       "single_word": false,
       "special": true
     },
-    "11": {
+    "7": {
       "content": "</s>",
       "lstrip": false,
       "normalized": false,
@@ -39,7 +39,6 @@
   "eos_token": "</s>",
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "[PAD]",
-  "processor_class": "Wav2Vec2BertProcessor",
   "replace_word_delimiter_char": " ",
   "target_lang": null,
   "tokenizer_class": "Wav2Vec2CTCTokenizer",

vocab.json

@@ -1,12 +1,8 @@
 {
-  "(": 1,
-  ")": 2,
-  "[PAD]": 9,
-  "[UNK]": 8,
+  "[PAD]": 5,
+  "[UNK]": 4,
   "|": 0,
-  "â": 3,
-  "û": 4,
-  "̇": 5,
-  "’": 6,
-  "…": 7
+  "â": 1,
+  "û": 2,
+  "̇": 3
 }