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