add tokenizer

special_tokens_map.json

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

tokenizer_config.json

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

@@ -1 +1,32 @@
-{"p": 0, "m": 1, "o": 2, "g": 3, "s": 4, "d": 6, "n": 7, "v": 8, "a": 9, "u": 10, "z": 11, "e": 12, "l": 13, "f": 14, "t": 15, "j": 16, "w": 17, "k": 18, "c": 19, "x": 20, "q": 21, "y": 22, "r": 23, "h": 24, "'": 25, "b": 26, "i": 27, "|": 5, "[UNK]": 28, "[PAD]": 29}
+{
+  "'": 4,
+  "[PAD]": 29,
+  "[UNK]": 28,
+  "a": 12,
+  "b": 18,
+  "c": 20,
+  "d": 0,
+  "e": 8,
+  "f": 15,
+  "g": 27,
+  "h": 14,
+  "i": 22,
+  "j": 6,
+  "k": 25,
+  "l": 7,
+  "m": 9,
+  "n": 13,
+  "o": 26,
+  "p": 19,
+  "q": 1,
+  "r": 24,
+  "s": 21,
+  "t": 23,
+  "u": 16,
+  "v": 10,
+  "w": 11,
+  "x": 17,
+  "y": 3,
+  "z": 2,
+  "|": 5
+}