Upload tokenizer

tokenizer_config.json

@@ -1,9 +1,12 @@
 {
   "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
   "do_lower_case": false,
   "eos_token": "</s>",
+  "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

@@ -1,32 +1,32 @@
 {
-  "'": 6,
+  "'": 1,
   "[PAD]": 29,
   "[UNK]": 28,
-  "a": 5,
-  "b": 10,
-  "c": 25,
-  "d": 19,
-  "e": 13,
-  "f": 8,
-  "g": 4,
-  "h": 23,
-  "i": 9,
-  "j": 27,
-  "k": 24,
-  "l": 16,
-  "m": 0,
-  "n": 22,
-  "o": 1,
-  "p": 12,
-  "q": 18,
-  "r": 3,
-  "s": 20,
-  "t": 26,
-  "u": 14,
-  "v": 17,
-  "w": 15,
-  "x": 2,
-  "y": 11,
-  "z": 21,
-  "|": 7
+  "a": 12,
+  "b": 3,
+  "c": 16,
+  "d": 11,
+  "e": 15,
+  "f": 27,
+  "g": 6,
+  "h": 25,
+  "i": 5,
+  "j": 23,
+  "k": 14,
+  "l": 21,
+  "m": 10,
+  "n": 7,
+  "o": 26,
+  "p": 2,
+  "q": 8,
+  "r": 22,
+  "s": 17,
+  "t": 4,
+  "u": 18,
+  "v": 13,
+  "w": 20,
+  "x": 24,
+  "y": 19,
+  "z": 0,
+  "|": 9
 }