add tokenizer

special_tokens_map.json

@@ -1,6 +1 @@
-{
-  "bos_token": "<s>",
-  "eos_token": "</s>",
-  "pad_token": "[PAD]",
-  "unk_token": "[UNK]"
-}
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]"}

tokenizer_config.json

@@ -1,10 +1 @@
-{
-  "bos_token": "<s>",
-  "do_lower_case": false,
-  "eos_token": "</s>",
-  "pad_token": "[PAD]",
-  "replace_word_delimiter_char": " ",
-  "tokenizer_class": "Wav2Vec2CTCTokenizer",
-  "unk_token": "[UNK]",
-  "word_delimiter_token": "|"
-}
+{"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "replace_word_delimiter_char": " ", "tokenizer_class": "Wav2Vec2CTCTokenizer"}

vocab.json

@@ -1,37 +1 @@
-{
-  "'": 11,
-  "2": 7,
-  "3": 31,
-  "4": 14,
-  "5": 10,
-  "6": 27,
-  "[PAD]": 34,
-  "[UNK]": 33,
-  "a": 24,
-  "b": 13,
-  "c": 16,
-  "d": 26,
-  "e": 12,
-  "f": 1,
-  "g": 18,
-  "h": 19,
-  "i": 2,
-  "j": 5,
-  "k": 6,
-  "l": 3,
-  "m": 29,
-  "n": 30,
-  "o": 0,
-  "p": 22,
-  "q": 21,
-  "r": 8,
-  "s": 23,
-  "t": 4,
-  "u": 17,
-  "v": 32,
-  "w": 15,
-  "x": 25,
-  "y": 20,
-  "z": 28,
-  "|": 9
-}
+{"d": 0, "2": 2, "4": 3, "g": 4, "e": 5, "l": 6, "s": 7, "j": 8, "6": 9, "3": 10, "r": 11, "v": 12, "o": 13, "w": 14, "c": 15, "n": 16, "y": 17, "b": 18, "k": 19, "f": 20, "t": 21, "x": 22, "m": 23, "z": 24, "u": 25, "'": 26, "a": 27, "5": 28, "i": 29, "p": 30, "q": 31, "h": 32, "|": 1, "[UNK]": 33, "[PAD]": 34}