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 +1,28 @@
+{
+  "[PAD]": 25,
+  "[UNK]": 24,
+  "a": 17,
+  "b": 0,
+  "c": 9,
+  "d": 16,
+  "e": 7,
+  "f": 2,
+  "g": 4,
+  "h": 13,
+  "i": 3,
+  "j": 1,
+  "k": 20,
+  "l": 21,
+  "m": 12,
+  "n": 8,
+  "o": 11,
+  "p": 15,
+  "r": 22,
+  "s": 23,
+  "t": 10,
+  "u": 19,
+  "v": 5,
+  "y": 18,
+  "z": 6,
+  "|": 14
+}