Upload tokenizer

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 91,
+  "<s>": 90
+}

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 +1,47 @@
+{
+  "added_tokens_decoder": {
+    "88": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "89": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "90": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "91": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "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

@@ -0,0 +1,92 @@
+{
+  "!": 1,
+  "\"": 2,
+  "%": 3,
+  "'": 4,
+  "(": 5,
+  ")": 6,
+  ",": 7,
+  "-": 8,
+  ".": 9,
+  ":": 10,
+  ";": 11,
+  "?": 12,
+  "A": 13,
+  "B": 14,
+  "C": 15,
+  "D": 16,
+  "E": 17,
+  "F": 18,
+  "G": 19,
+  "H": 20,
+  "I": 21,
+  "J": 22,
+  "K": 23,
+  "L": 24,
+  "M": 25,
+  "N": 26,
+  "O": 27,
+  "P": 28,
+  "Q": 29,
+  "R": 30,
+  "S": 31,
+  "T": 32,
+  "U": 33,
+  "V": 34,
+  "W": 35,
+  "X": 36,
+  "Y": 37,
+  "Z": 38,
+  "[PAD]": 89,
+  "[UNK]": 88,
+  "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,
+  "Â": 65,
+  "Ç": 66,
+  "Ö": 67,
+  "Ü": 68,
+  "â": 69,
+  "ç": 70,
+  "é": 71,
+  "ë": 72,
+  "î": 73,
+  "ö": 74,
+  "û": 75,
+  "ü": 76,
+  "ğ": 77,
+  "İ": 78,
+  "ı": 79,
+  "Ş": 80,
+  "ş": 81,
+  "‘": 82,
+  "’": 83,
+  "“": 84,
+  "”": 85,
+  "…": 86,
+  "�": 87
+}