Upload tokenizer

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 +1,13 @@
+{
+  "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 +1,39 @@
+{
+  "[PAD]": 36,
+  "[UNK]": 35,
+  "a": 20,
+  "b": 15,
+  "c": 26,
+  "g": 0,
+  "h": 5,
+  "i": 10,
+  "k": 24,
+  "l": 12,
+  "m": 21,
+  "n": 8,
+  "p": 27,
+  "q": 31,
+  "t": 34,
+  "u": 30,
+  "v": 3,
+  "|": 7,
+  "à": 16,
+  "á": 25,
+  "è": 2,
+  "ò": 22,
+  "ô": 11,
+  "ă": 29,
+  "đ": 19,
+  "ư": 14,
+  "ạ": 23,
+  "ậ": 17,
+  "ắ": 9,
+  "ặ": 33,
+  "ế": 28,
+  "ệ": 32,
+  "ố": 1,
+  "ổ": 6,
+  "ộ": 13,
+  "ờ": 4,
+  "ủ": 18
+}