Upload tokenizer

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 109,
+  "<s>": 108
+}

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": {
+    "106": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "107": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "108": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "109": {
+      "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": "vie",
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

vocab.json

@@ -0,0 +1,112 @@
+{
+  "vie": {
+    "/": 1,
+    "0": 2,
+    "1": 3,
+    "2": 4,
+    "3": 5,
+    "4": 6,
+    "5": 7,
+    "6": 8,
+    "7": 9,
+    "8": 10,
+    "9": 11,
+    "[": 12,
+    "[PAD]": 107,
+    "[UNK]": 106,
+    "]": 13,
+    "a": 14,
+    "b": 15,
+    "c": 16,
+    "d": 17,
+    "e": 18,
+    "f": 19,
+    "g": 20,
+    "h": 21,
+    "i": 22,
+    "j": 23,
+    "k": 24,
+    "l": 25,
+    "m": 26,
+    "n": 27,
+    "o": 28,
+    "p": 29,
+    "q": 30,
+    "r": 31,
+    "s": 32,
+    "t": 33,
+    "u": 34,
+    "v": 35,
+    "w": 36,
+    "x": 37,
+    "y": 38,
+    "|": 0,
+    "à": 39,
+    "á": 40,
+    "â": 41,
+    "ã": 42,
+    "è": 43,
+    "é": 44,
+    "ê": 45,
+    "ì": 46,
+    "í": 47,
+    "ò": 48,
+    "ó": 49,
+    "ô": 50,
+    "õ": 51,
+    "ù": 52,
+    "ú": 53,
+    "ý": 54,
+    "ă": 55,
+    "đ": 56,
+    "ĩ": 57,
+    "ũ": 58,
+    "ơ": 59,
+    "ư": 60,
+    "ạ": 61,
+    "ả": 62,
+    "ấ": 63,
+    "ầ": 64,
+    "ẩ": 65,
+    "ẫ": 66,
+    "ậ": 67,
+    "ắ": 68,
+    "ằ": 69,
+    "ẳ": 70,
+    "ẵ": 71,
+    "ặ": 72,
+    "ẹ": 73,
+    "ẻ": 74,
+    "ẽ": 75,
+    "ế": 76,
+    "ề": 77,
+    "ể": 78,
+    "ễ": 79,
+    "ệ": 80,
+    "ỉ": 81,
+    "ị": 82,
+    "ọ": 83,
+    "ỏ": 84,
+    "ố": 85,
+    "ồ": 86,
+    "ổ": 87,
+    "ỗ": 88,
+    "ộ": 89,
+    "ớ": 90,
+    "ờ": 91,
+    "ở": 92,
+    "ỡ": 93,
+    "ợ": 94,
+    "ụ": 95,
+    "ủ": 96,
+    "ứ": 97,
+    "ừ": 98,
+    "ử": 99,
+    "ữ": 100,
+    "ự": 101,
+    "ỳ": 102,
+    "ỵ": 103,
+    "ỷ": 104,
+    "ỹ": 105
+  }
+}