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": "|", "tokenizer_class": "Wav2Vec2CTCTokenizer"}

vocab.json

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