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