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