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": " ", "special_tokens_map_file": null, "name_or_path": "/tmp/tmpx74l66dt", "tokenizer_class": "Wav2Vec2CTCTokenizer"}

vocab.json

@@ -0,0 +1 @@
+{"<pad>": 0, "<s>": 1, "</s>": 2, "<unk>": 3, "?": 4, ".": 5, "n": 6, "e": 7, "s": 8, "h": 9, "'": 10, "l": 11, "u": 12, "!": 13, "i": 14, "g": 15, "o": 16, "c": 17, "t": 18, "b": 19, "\"": 20, "k": 21, "w": 22, "-": 23, "y": 24, "f": 26, "q": 27, "d": 28, "r": 29, "z": 30, "j": 31, "x": 32, "v": 33, ",": 34, "a": 35, "p": 36, "m": 37, "|": 25}