Upload tokenizer

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 52,
+  "<s>": 51
+}

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": {
+    "49": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "50": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "51": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "52": {
+      "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 +1,53 @@
+{
+  "!": 1,
+  "\"": 2,
+  "'": 3,
+  "(": 4,
+  ")": 5,
+  ",": 6,
+  "-": 7,
+  ".": 8,
+  ":": 9,
+  ";": 10,
+  "?": 11,
+  "A": 12,
+  "B": 13,
+  "C": 14,
+  "D": 15,
+  "E": 16,
+  "F": 17,
+  "G": 18,
+  "H": 19,
+  "I": 20,
+  "J": 21,
+  "K": 22,
+  "L": 23,
+  "M": 24,
+  "N": 25,
+  "O": 26,
+  "P": 27,
+  "Q": 28,
+  "R": 29,
+  "S": 30,
+  "T": 31,
+  "U": 32,
+  "V": 33,
+  "W": 34,
+  "Y": 35,
+  "Z": 36,
+  "[PAD]": 50,
+  "[UNK]": 49,
+  "|": 0,
+  "Ç": 37,
+  "Ö": 38,
+  "Ü": 39,
+  "â": 40,
+  "û": 41,
+  "İ": 42,
+  "Ş": 43,
+  "‘": 44,
+  "’": 45,
+  "“": 46,
+  "”": 47,
+  "…": 48
+}