Upload tokenizer

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "</s>": 103,
+  "<pad>": 104,
+  "<s>": 102
+}

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 +1,104 @@
+{
+  "!": 1,
+  "'": 2,
+  ",": 3,
+  "-": 4,
+  ".": 5,
+  ";": 6,
+  "?": 7,
+  "A": 8,
+  "B": 9,
+  "C": 10,
+  "D": 11,
+  "E": 12,
+  "F": 13,
+  "G": 14,
+  "H": 15,
+  "I": 16,
+  "J": 17,
+  "K": 18,
+  "L": 19,
+  "M": 20,
+  "N": 21,
+  "O": 22,
+  "P": 23,
+  "R": 24,
+  "S": 25,
+  "T": 26,
+  "U": 27,
+  "W": 28,
+  "Y": 29,
+  "[": 30,
+  "[PAD]": 101,
+  "[UNK]": 100,
+  "]": 31,
+  "a": 32,
+  "b": 33,
+  "c": 34,
+  "d": 35,
+  "e": 36,
+  "f": 37,
+  "g": 38,
+  "h": 39,
+  "i": 40,
+  "j": 41,
+  "k": 42,
+  "l": 43,
+  "m": 44,
+  "n": 45,
+  "o": 46,
+  "p": 47,
+  "r": 48,
+  "s": 49,
+  "t": 50,
+  "u": 51,
+  "v": 52,
+  "w": 53,
+  "x": 54,
+  "y": 55,
+  "|": 0,
+  "À": 56,
+  "Á": 57,
+  "È": 58,
+  "É": 59,
+  "Ì": 60,
+  "Í": 61,
+  "Ò": 62,
+  "Ó": 63,
+  "à": 64,
+  "á": 65,
+  "è": 66,
+  "é": 67,
+  "ì": 68,
+  "í": 69,
+  "ò": 70,
+  "ó": 71,
+  "ù": 72,
+  "ú": 73,
+  "ĺ": 74,
+  "ń": 75,
+  "ś": 76,
+  "Ǹ": 77,
+  "ǹ": 78,
+  "̀": 79,
+  "́": 80,
+  "̄": 81,
+  "̣": 82,
+  "ḷ": 83,
+  "ṕ": 84,
+  "ṛ": 85,
+  "Ṣ": 86,
+  "ṣ": 87,
+  "ẃ": 88,
+  "ạ": 89,
+  "Ẹ": 90,
+  "ẹ": 91,
+  "Ọ": 92,
+  "ọ": 93,
+  "ụ": 94,
+  "—": 95,
+  "‘": 96,
+  "’": 97,
+  "“": 98,
+  "”": 99
+}