Upload tokenizer

added_tokens.json

@@ -1,4 +1,4 @@
 {
-  "</s>": 92,
-  "<s>": 91
+  "</s>": 111,
+  "<s>": 110
 }

special_tokens_map.json

@@ -1 +1,6 @@
-{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -1 +1,49 @@
-{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "<pad>", "do_lower_case": false, "word_delimiter_token": "|", "tokenizer_class": "Wav2Vec2CTCTokenizer"}
+{
+  "added_tokens_decoder": {
+    "108": {
+      "content": "<unk>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "109": {
+      "content": "<pad>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "110": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "111": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "config": null,
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "replace_word_delimiter_char": " ",
+  "target_lang": null,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "tokenizer_type": "wav2vec2",
+  "unk_token": "<unk>",
+  "word_delimiter_token": "|"
+}

vocab.json

@@ -1 +1,112 @@
-{"ẻ": 0, "6": 1, "ụ": 2, "í": 3, "3": 4, "ỹ": 5, "ý": 6, "ẩ": 7, "ở": 8, "ề": 9, "õ": 10, "7": 11, "ê": 12, "ứ": 13, "ỏ": 14, "v": 15, "ỷ": 16, "a": 17, "l": 18, "ự": 19, "q": 20, "ờ": 21, "j": 22, "ố": 23, "à": 24, "ỗ": 25, "n": 26, "é": 27, "ủ": 28, "у": 29, "ô": 30, "u": 31, "y": 32, "ằ": 33, "4": 34, "w": 35, "b": 36, "ệ": 37, "ễ": 38, "s": 39, "ì": 40, "ầ": 41, "ỵ": 42, "8": 43, "d": 44, "ể": 45, "r": 47, "ũ": 48, "c": 49, "ạ": 50, "9": 51, "ế": 52, "ù": 53, "ỡ": 54, "2": 55, "t": 56, "i": 57, "g": 58, "́": 59, "ử": 60, "̀": 61, "á": 62, "0": 63, "ậ": 64, "e": 65, "ộ": 66, "m": 67, "ẳ": 68, "ợ": 69, "ĩ": 70, "h": 71, "â": 72, "ú": 73, "ọ": 74, "ồ": 75, "ặ": 76, "f": 77, "ữ": 78, "ắ": 79, "ỳ": 80, "x": 81, "ó": 82, "ã": 83, "ổ": 84, "ị": 85, "̣": 86, "z": 87, "ả": 88, "đ": 89, "è": 90, "ừ": 91, "ò": 92, "ẵ": 93, "1": 94, "ơ": 95, "k": 96, "ẫ": 97, "p": 98, "ấ": 99, "ẽ": 100, "ỉ": 101, "ớ": 102, "ẹ": 103, "ă": 104, "o": 105, "ư": 106, "5": 107, "|": 46, "<unk>": 108, "<pad>": 109}
+{
+  "0": 63,
+  "1": 94,
+  "2": 55,
+  "3": 4,
+  "4": 34,
+  "5": 107,
+  "6": 1,
+  "7": 11,
+  "8": 43,
+  "9": 51,
+  "<pad>": 109,
+  "<unk>": 108,
+  "a": 17,
+  "b": 36,
+  "c": 49,
+  "d": 44,
+  "e": 65,
+  "f": 77,
+  "g": 58,
+  "h": 71,
+  "i": 57,
+  "j": 22,
+  "k": 96,
+  "l": 18,
+  "m": 67,
+  "n": 26,
+  "o": 105,
+  "p": 98,
+  "q": 20,
+  "r": 47,
+  "s": 39,
+  "t": 56,
+  "u": 31,
+  "v": 15,
+  "w": 35,
+  "x": 81,
+  "y": 32,
+  "z": 87,
+  "|": 46,
+  "à": 24,
+  "á": 62,
+  "â": 72,
+  "ã": 83,
+  "è": 90,
+  "é": 27,
+  "ê": 12,
+  "ì": 40,
+  "í": 3,
+  "ò": 92,
+  "ó": 82,
+  "ô": 30,
+  "õ": 10,
+  "ù": 53,
+  "ú": 73,
+  "ý": 6,
+  "ă": 104,
+  "đ": 89,
+  "ĩ": 70,
+  "ũ": 48,
+  "ơ": 95,
+  "ư": 106,
+  "̀": 61,
+  "́": 59,
+  "̣": 86,
+  "у": 29,
+  "ạ": 50,
+  "ả": 88,
+  "ấ": 99,
+  "ầ": 41,
+  "ẩ": 7,
+  "ẫ": 97,
+  "ậ": 64,
+  "ắ": 79,
+  "ằ": 33,
+  "ẳ": 68,
+  "ẵ": 93,
+  "ặ": 76,
+  "ẹ": 103,
+  "ẻ": 0,
+  "ẽ": 100,
+  "ế": 52,
+  "ề": 9,
+  "ể": 45,
+  "ễ": 38,
+  "ệ": 37,
+  "ỉ": 101,
+  "ị": 85,
+  "ọ": 74,
+  "ỏ": 14,
+  "ố": 23,
+  "ồ": 75,
+  "ổ": 84,
+  "ỗ": 25,
+  "ộ": 66,
+  "ớ": 102,
+  "ờ": 21,
+  "ở": 8,
+  "ỡ": 54,
+  "ợ": 69,
+  "ụ": 2,
+  "ủ": 28,
+  "ứ": 13,
+  "ừ": 91,
+  "ử": 60,
+  "ữ": 78,
+  "ự": 19,
+  "ỳ": 80,
+  "ỵ": 42,
+  "ỷ": 16,
+  "ỹ": 5
+}