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