Upload tokenizer

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "[PAD]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "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

@@ -0,0 +1,83 @@
+{
+  "$": 13,
+  "%": 22,
+  "&": 65,
+  "'": 26,
+  "(": 11,
+  ")": 37,
+  "+": 23,
+  "/": 41,
+  "0": 51,
+  "1": 24,
+  "2": 64,
+  "3": 2,
+  "4": 58,
+  "5": 7,
+  "6": 49,
+  "7": 15,
+  "8": 36,
+  "9": 68,
+  "[": 10,
+  "[PAD]": 80,
+  "[UNK]": 79,
+  "\\": 17,
+  "a": 0,
+  "b": 71,
+  "c": 57,
+  "d": 62,
+  "e": 50,
+  "f": 67,
+  "g": 6,
+  "h": 4,
+  "i": 32,
+  "j": 47,
+  "k": 66,
+  "l": 63,
+  "m": 20,
+  "n": 74,
+  "o": 78,
+  "p": 16,
+  "q": 19,
+  "r": 54,
+  "s": 9,
+  "t": 52,
+  "u": 77,
+  "v": 69,
+  "w": 8,
+  "x": 34,
+  "y": 1,
+  "z": 21,
+  "|": 38,
+  "¡": 12,
+  "£": 44,
+  "¥": 60,
+  "§": 39,
+  "©": 55,
+  "­": 27,
+  "°": 61,
+  "²": 25,
+  "³": 18,
+  "µ": 30,
+  "¶": 53,
+  "º": 45,
+  "á": 29,
+  "â": 70,
+  "ã": 40,
+  "ä": 72,
+  "å": 73,
+  "é": 31,
+  "ÿ": 59,
+  "ł": 5,
+  "ń": 46,
+  "ō": 3,
+  "ƒ": 76,
+  "–": 48,
+  "—": 28,
+  "‘": 75,
+  "’": 42,
+  "“": 35,
+  "”": 56,
+  "•": 14,
+  "€": 33,
+  "，": 43
+}