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