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