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