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