Upload tokenizer

tokenizer_config.json

@@ -1,38 +1,4 @@
 {
-  "added_tokens_decoder": {
-    "27": {
-      "content": "[UNK]",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": false
-    },
-    "28": {
-      "content": "[PAD]",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": false
-    },
-    "29": {
-      "content": "<s>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "30": {
-      "content": "</s>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    }
-  },
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
   "do_lower_case": false,
@@ -40,7 +6,6 @@
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "[PAD]",
   "replace_word_delimiter_char": " ",
-  "target_lang": null,
   "tokenizer_class": "Wav2Vec2CTCTokenizer",
   "unk_token": "[UNK]",
   "word_delimiter_token": "|"

vocab.json

@@ -1,31 +1,31 @@
 {
   "[PAD]": 28,
   "[UNK]": 27,
-  "a": 12,
-  "b": 14,
-  "c": 17,
-  "d": 8,
-  "e": 0,
-  "f": 19,
-  "g": 1,
-  "h": 25,
-  "i": 20,
-  "j": 22,
-  "k": 21,
-  "l": 2,
+  "a": 16,
+  "b": 1,
+  "c": 18,
+  "d": 9,
+  "e": 14,
+  "f": 0,
+  "g": 25,
+  "h": 3,
+  "i": 24,
+  "j": 4,
+  "k": 11,
+  "l": 12,
   "m": 5,
-  "n": 23,
-  "o": 11,
-  "p": 18,
-  "q": 9,
-  "r": 16,
-  "s": 4,
+  "n": 22,
+  "o": 23,
+  "p": 21,
+  "q": 19,
+  "r": 10,
+  "s": 7,
   "t": 6,
-  "u": 26,
-  "v": 3,
-  "w": 15,
-  "x": 10,
-  "y": 24,
-  "z": 13,
-  "|": 7
+  "u": 20,
+  "v": 26,
+  "w": 13,
+  "x": 15,
+  "y": 17,
+  "z": 8,
+  "|": 2
 }