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