Upload tokenizer

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "</s>": 109,
+  "<pad>": 110,
+  "<s>": 108
+}

special_tokens_map.json

@@ -0,0 +1,29 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +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": " ",
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "<unk>",
+  "word_delimiter_token": "|"
+}

vocab.json

@@ -0,0 +1,110 @@
+{
+  "!": 1,
+  "\"": 2,
+  "$": 3,
+  "%": 4,
+  "&": 5,
+  "'": 6,
+  "+": 7,
+  ",": 8,
+  "-": 9,
+  ".": 10,
+  "/": 11,
+  "0": 12,
+  "1": 13,
+  "2": 14,
+  "3": 15,
+  "4": 16,
+  "5": 17,
+  "6": 18,
+  "7": 19,
+  "8": 20,
+  "9": 21,
+  ":": 22,
+  ";": 23,
+  "A": 24,
+  "C": 25,
+  "D": 26,
+  "E": 27,
+  "G": 28,
+  "H": 29,
+  "I": 30,
+  "M": 31,
+  "N": 32,
+  "O": 33,
+  "R": 34,
+  "S": 35,
+  "[": 36,
+  "[PAD]": 107,
+  "[UNK]": 106,
+  "]": 37,
+  "_": 38,
+  "a": 39,
+  "b": 40,
+  "c": 41,
+  "d": 42,
+  "e": 43,
+  "f": 44,
+  "g": 45,
+  "h": 46,
+  "i": 47,
+  "j": 48,
+  "k": 49,
+  "l": 50,
+  "m": 51,
+  "n": 52,
+  "o": 53,
+  "p": 54,
+  "q": 55,
+  "r": 56,
+  "s": 57,
+  "t": 58,
+  "u": 59,
+  "v": 60,
+  "w": 61,
+  "x": 62,
+  "y": 63,
+  "z": 64,
+  "|": 0,
+  "~": 65,
+  "£": 66,
+  "¥": 67,
+  "°": 68,
+  "²": 69,
+  "½": 70,
+  "¾": 71,
+  "à": 72,
+  "á": 73,
+  "ã": 74,
+  "ç": 75,
+  "è": 76,
+  "é": 77,
+  "ì": 78,
+  "í": 79,
+  "ñ": 80,
+  "ò": 81,
+  "ó": 82,
+  "õ": 83,
+  "ù": 84,
+  "ú": 85,
+  "ü": 86,
+  "ă": 87,
+  "ē": 88,
+  "ī": 89,
+  "ł": 90,
+  "ū": 91,
+  "ǹ": 92,
+  "ș": 93,
+  "̀": 94,
+  "̄": 95,
+  "ṅ": 96,
+  "ị": 97,
+  "Ọ": 98,
+  "ọ": 99,
+  "ụ": 100,
+  "–": 101,
+  "—": 102,
+  "‘": 103,
+  "’": 104,
+  "”": 105
+}