Upload tokenizer

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 79,
+  "<s>": 78
+}

special_tokens_map.json

@@ -0,0 +1,22 @@
+{
+  "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
+    }
+  ],
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "[PAD]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token": "<s>",
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "name_or_path": "./",
+  "pad_token": "[PAD]",
+  "replace_word_delimiter_char": " ",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

vocab.json

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