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