add tokenizer

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"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

@@ -0,0 +1 @@
+{"d": 0, "h": 1, "t": 2, "n": 3, "s": 4, "b": 5, "0": 6, "q": 7, "j": 8, "9": 9, "2": 10, "z": 11, "5": 12, "g": 13, "'": 14, "3": 15, "a": 16, "w": 17, "v": 19, "4": 20, "p": 21, "i": 22, "6": 23, "8": 24, "u": 25, "r": 26, "m": 27, "e": 28, "y": 29, "x": 30, "o": 31, "k": 32, "1": 33, "c": 34, "l": 35, "f": 36, "|": 18, "[UNK]": 37, "[PAD]": 38}