Upload tokenizer

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 31,
+  "<s>": 30
+}

tokenizer_config.json

@@ -1,9 +1,46 @@
 {
+  "added_tokens_decoder": {
+    "28": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "29": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "30": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "31": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
   "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 @@
 {
-  "'": 2,
+  "'": 7,
   "[PAD]": 29,
   "[UNK]": 28,
-  "a": 1,
-  "b": 19,
-  "c": 10,
-  "d": 7,
+  "a": 5,
+  "b": 8,
+  "c": 25,
+  "d": 0,
   "e": 6,
-  "f": 20,
-  "g": 14,
-  "h": 15,
-  "i": 22,
-  "j": 11,
-  "k": 5,
-  "l": 25,
+  "f": 4,
+  "g": 24,
+  "h": 22,
+  "i": 14,
+  "j": 27,
+  "k": 9,
+  "l": 2,
   "m": 16,
-  "n": 24,
-  "o": 21,
-  "p": 23,
-  "q": 26,
-  "r": 0,
-  "s": 17,
-  "t": 27,
-  "u": 3,
-  "v": 18,
-  "w": 9,
+  "n": 3,
+  "o": 11,
+  "p": 20,
+  "q": 15,
+  "r": 19,
+  "s": 26,
+  "t": 23,
+  "u": 10,
+  "v": 1,
+  "w": 18,
   "x": 12,
-  "y": 13,
-  "z": 8,
-  "|": 4
+  "y": 21,
+  "z": 17,
+  "|": 13
 }