add tokenizer

added_tokens.json

@@ -1,4 +1 @@
-{
-  "</s>": 31,
-  "<s>": 30
-}
+{"<s>": 30, "</s>": 31}

special_tokens_map.json

@@ -1,22 +1 @@
-{
-  "additional_special_tokens": [
-    {
-      "content": "<s>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false
-    },
-    {
-      "content": "</s>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false
-    }
-  ],
-  "bos_token": "<s>",
-  "eos_token": "</s>",
-  "pad_token": "[PAD]",
-  "unk_token": "[UNK]"
-}
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]", "additional_special_tokens": [{"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}]}

tokenizer_config.json

@@ -1,12 +1 @@
-{
-  "bos_token": "<s>",
-  "do_lower_case": false,
-  "eos_token": "</s>",
-  "name_or_path": "./",
-  "pad_token": "[PAD]",
-  "replace_word_delimiter_char": " ",
-  "special_tokens_map_file": null,
-  "tokenizer_class": "Wav2Vec2CTCTokenizer",
-  "unk_token": "[UNK]",
-  "word_delimiter_token": "|"
-}
+{"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "./", "tokenizer_class": "Wav2Vec2CTCTokenizer"}

vocab.json

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