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