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 +1,87 @@
+{
+  "\t": 0,
+  "!": 2,
+  "\"": 3,
+  "$": 4,
+  "%": 5,
+  "'": 6,
+  "(": 7,
+  ")": 8,
+  ",": 9,
+  "-": 10,
+  ".": 11,
+  "/": 12,
+  "0": 13,
+  "1": 14,
+  "2": 15,
+  "3": 16,
+  "4": 17,
+  "5": 18,
+  "6": 19,
+  "7": 20,
+  "8": 21,
+  "9": 22,
+  ":": 23,
+  ";": 24,
+  "?": 25,
+  "A": 26,
+  "B": 27,
+  "C": 28,
+  "D": 29,
+  "E": 30,
+  "F": 31,
+  "G": 32,
+  "H": 33,
+  "I": 34,
+  "J": 35,
+  "K": 36,
+  "L": 37,
+  "M": 38,
+  "N": 39,
+  "O": 40,
+  "P": 41,
+  "Q": 42,
+  "R": 43,
+  "S": 44,
+  "T": 45,
+  "U": 46,
+  "V": 47,
+  "W": 48,
+  "Y": 49,
+  "Z": 50,
+  "[PAD]": 84,
+  "[UNK]": 83,
+  "a": 51,
+  "b": 52,
+  "c": 53,
+  "d": 54,
+  "e": 55,
+  "f": 56,
+  "g": 57,
+  "h": 58,
+  "i": 59,
+  "j": 60,
+  "k": 61,
+  "l": 62,
+  "m": 63,
+  "n": 64,
+  "o": 65,
+  "p": 66,
+  "q": 67,
+  "r": 68,
+  "s": 69,
+  "t": 70,
+  "u": 71,
+  "v": 72,
+  "w": 73,
+  "x": 74,
+  "y": 75,
+  "z": 76,
+  "|": 1,
+  "‘": 77,
+  "’": 78,
+  "“": 79,
+  "”": 80,
+  "…": 81,
+  "": 82
+}