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 @@
+{"<pad>": 0, "<s>": 1, "</s>": 2, "<unk>": 3, "|": 4, "'": 5, "a": 6, "b": 7, "c": 8, "d": 9, "e": 10, "f": 11, "g": 12, "h": 13, "i": 14, "j": 15, "k": 16, "l": 17, "m": 18, "n": 19, "o": 20, "p": 21, "q": 22, "r": 23, "s": 24, "t": 25, "u": 26, "v": 27, "w": 28, "x": 29, "y": 30, "z": 31}