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": "|", "tokenizer_class": "Wav2Vec2CTCTokenizer"}

vocab.json

@@ -0,0 +1 @@
+{"[PAD]": 0, "<s>": 1, "</s>": 2, "[UNK]": 3, "|": 4, "e": 5, "t": 6, "a": 7, "o": 8, "n": 9, "i": 10, "h": 11, "s": 12, "r": 13, "d": 14, "l": 15, "u": 16, "m": 17, "w": 18, "c": 19, "f": 20, "g": 21, "y": 22, "p": 23, "b": 24, "v": 25, "k": 26, "'": 27, "x": 28, "j": 29, "q": 30, "z": 31}