add tokenizer

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "</s>": 54,
+  "<s>": 53,
+  "[PAD]": 55
+}

special_tokens_map.json

@@ -0,0 +1,29 @@
+{
+  "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
+    },
+    {
+      "content": "[PAD]",
+      "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 +1,56 @@
+{
+  "0": 1,
+  "1": 2,
+  "2": 3,
+  "3": 4,
+  "4": 5,
+  "5": 6,
+  "6": 7,
+  "7": 8,
+  "8": 9,
+  "9": 10,
+  "<": 11,
+  ">": 12,
+  "[PAD]": 54,
+  "[UNK]": 54,
+  "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,
+  "|": 0,
+  " ": 39,
+  "à": 40,
+  "ä": 41,
+  "å": 42,
+  "æ": 43,
+  "è": 44,
+  "é": 45,
+  "ò": 46,
+  "ó": 47,
+  "ô": 48,
+  "ö": 49,
+  "ø": 50,
+  "ü": 51
+}