Upload processor

added_tokens.json

@@ -1,4 +1,4 @@
 {
-  "<pad>": 0,
-  "<unk>": 96
+  "[PAD]": 0,
+  "[UNK]": 1
 }

special_tokens_map.json

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

tokenizer_config.json

@@ -1,15 +1,15 @@
 {
   "added_tokens_decoder": {
     "0": {
-      "content": "<pad>",
+      "content": "[PAD]",
       "lstrip": true,
       "normalized": false,
       "rstrip": true,
       "single_word": false,
       "special": false
     },
-    "96": {
-      "content": "<unk>",
+    "1": {
+      "content": "[UNK]",
       "lstrip": true,
       "normalized": false,
       "rstrip": true,
@@ -18,17 +18,17 @@
     }
   },
   "additional_special_tokens": [],
-  "bos_token": "<pad>",
+  "bos_token": "[PAD]",
   "clean_up_tokenization_spaces": true,
   "do_lower_case": false,
-  "eos_token": "<pad>",
+  "eos_token": "[PAD]",
   "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "<pad>",
+  "pad_token": "[PAD]",
   "processor_class": "Wav2Vec2Processor",
   "replace_word_delimiter_char": " ",
   "target_lang": null,
   "tokenizer_class": "Wav2Vec2CTCTokenizer",
   "tokenizer_file": null,
-  "unk_token": "<unk>",
+  "unk_token": "[UNK]",
   "word_delimiter_token": "|"
 }

vocab.json

@@ -1,99 +1,92 @@
 {
-  "'": 95,
-  "<pad>": 0,
-  "<unk>": 96,
-  "a": 2,
-  "b": 3,
-  "c": 4,
-  "d": 5,
-  "e": 6,
-  "f": 7,
-  "g": 8,
-  "h": 9,
-  "i": 10,
-  "j": 11,
-  "k": 12,
-  "l": 13,
-  "m": 14,
-  "n": 15,
-  "o": 16,
-  "p": 17,
-  "q": 18,
-  "r": 19,
-  "s": 20,
-  "t": 21,
-  "u": 22,
-  "v": 23,
-  "w": 24,
-  "x": 25,
-  "y": 26,
-  "z": 27,
-  "|": 1,
-  "à": 28,
-  "á": 29,
-  "â": 30,
-  "ã": 31,
-  "è": 32,
-  "é": 33,
-  "ê": 34,
-  "ì": 35,
-  "í": 36,
-  "ò": 37,
-  "ó": 38,
-  "ô": 39,
-  "õ": 40,
-  "ù": 41,
-  "ú": 42,
-  "ý": 43,
-  "ă": 44,
-  "đ": 45,
-  "ĩ": 46,
-  "ũ": 47,
-  "ơ": 48,
-  "ư": 49,
-  "ạ": 50,
-  "ả": 51,
-  "ấ": 52,
-  "ầ": 53,
-  "ẩ": 54,
-  "ẫ": 55,
-  "ậ": 56,
-  "ắ": 57,
-  "ằ": 58,
-  "ẳ": 59,
-  "ẵ": 60,
-  "ặ": 61,
-  "ẹ": 62,
-  "ẻ": 63,
-  "ẽ": 64,
-  "ế": 65,
-  "ề": 66,
-  "ể": 67,
-  "ễ": 68,
-  "ệ": 69,
-  "ỉ": 70,
-  "ị": 71,
-  "ọ": 72,
-  "ỏ": 73,
-  "ố": 74,
-  "ồ": 75,
-  "ổ": 76,
-  "ỗ": 77,
-  "ộ": 78,
-  "ớ": 79,
-  "ờ": 80,
-  "ở": 81,
-  "ỡ": 82,
-  "ợ": 83,
-  "ụ": 84,
-  "ủ": 85,
-  "ứ": 86,
-  "ừ": 87,
-  "ử": 88,
-  "ữ": 89,
-  "ự": 90,
-  "ỳ": 91,
-  "ỵ": 92,
-  "ỷ": 93,
-  "ỹ": 94
+  "0": 3,
+  "1": 4,
+  "2": 5,
+  "3": 6,
+  "4": 7,
+  "5": 8,
+  "6": 9,
+  "7": 10,
+  "8": 11,
+  "9": 12,
+  "[PAD]": 0,
+  "[UNK]": 1,
+  "a": 13,
+  "b": 14,
+  "c": 15,
+  "d": 16,
+  "e": 17,
+  "f": 18,
+  "g": 19,
+  "h": 20,
+  "i": 21,
+  "j": 22,
+  "k": 23,
+  "l": 24,
+  "m": 25,
+  "n": 26,
+  "o": 27,
+  "p": 28,
+  "q": 29,
+  "r": 30,
+  "s": 31,
+  "t": 32,
+  "u": 33,
+  "v": 34,
+  "w": 35,
+  "x": 36,
+  "y": 37,
+  "z": 38,
+  "|": 2,
+  "à": 39,
+  "á": 40,
+  "â": 41,
+  "ã": 42,
+  "è": 43,
+  "é": 44,
+  "ê": 45,
+  "ì": 46,
+  "í": 47,
+  "ò": 48,
+  "ó": 49,
+  "ô": 50,
+  "õ": 51,
+  "ù": 52,
+  "ú": 53,
+  "ý": 54,
+  "ă": 55,
+  "đ": 56,
+  "ĩ": 57,
+  "ũ": 58,
+  "ơ": 59,
+  "ạ": 60,
+  "ả": 61,
+  "ấ": 62,
+  "ầ": 63,
+  "ẩ": 64,
+  "ẫ": 65,
+  "ậ": 66,
+  "ắ": 67,
+  "ằ": 68,
+  "ẳ": 69,
+  "ẵ": 70,
+  "ặ": 71,
+  "ẹ": 72,
+  "ẻ": 73,
+  "ẽ": 74,
+  "ế": 75,
+  "ề": 76,
+  "ể": 77,
+  "ễ": 78,
+  "ệ": 79,
+  "ỉ": 80,
+  "ị": 81,
+  "ọ": 82,
+  "ỏ": 83,
+  "ố": 84,
+  "ồ": 85,
+  "ổ": 86,
+  "ỗ": 87,
+  "ộ": 88,
+  "ớ": 89
 }