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