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 @@
+{"i": 0, "b": 1, "t": 2, "d": 3, "v": 4, "l": 5, "g": 6, "a": 7, "y": 8, "f": 9, "s": 10, "k": 11, "o": 12, "e": 13, "n": 14, "z": 15, "q": 16, "x": 17, "p": 19, "j": 20, "r": 21, "w": 22, "m": 23, "h": 24, "u": 25, "c": 26, "|": 18, "[UNK]": 27, "[PAD]": 28}