add tokenizer

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "[PAD]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,10 @@
+{
+  "bos_token": "<s>",
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "pad_token": "[PAD]",
+  "replace_word_delimiter_char": " ",
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

vocab.json

@@ -0,0 +1,32 @@
+{
+  "'": 11,
+  "A": 6,
+  "B": 24,
+  "C": 0,
+  "D": 10,
+  "E": 17,
+  "F": 9,
+  "G": 13,
+  "H": 14,
+  "I": 8,
+  "J": 2,
+  "K": 16,
+  "L": 22,
+  "M": 26,
+  "N": 19,
+  "O": 1,
+  "P": 20,
+  "Q": 4,
+  "R": 15,
+  "S": 25,
+  "T": 3,
+  "U": 21,
+  "V": 18,
+  "W": 5,
+  "X": 12,
+  "Y": 7,
+  "Z": 23,
+  "[PAD]": 29,
+  "[UNK]": 28,
+  "|": 27
+}