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 @@
+{"t": 0, "h": 1, "n": 2, "a": 3, "r": 4, "f": 5, "u": 6, "c": 7, "y": 8, "p": 9, "k": 10, "m": 12, "w": 13, "l": 14, "i": 15, "o": 16, "d": 17, "g": 18, "s": 19, "b": 20, "e": 21, "|": 11, "[UNK]": 22, "[PAD]": 23}