Upload tokenizer

added_tokens.json

@@ -1,6 +1,6 @@
 {
-  "</s>": 103,
-  "<s>": 102,
-  "[PAD]": 101,
-  "[UNK]": 100
+  "</s>": 2,
+  "<pad>": 0,
+  "<s>": 1,
+  "<unk>": 3
 }

special_tokens_map.json

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

tokenizer_config.json

@@ -1,36 +1,36 @@
 {
   "added_tokens_decoder": {
-    "100": {
-      "content": "[UNK]",
+    "0": {
+      "content": "<pad>",
       "lstrip": true,
       "normalized": false,
       "rstrip": true,
       "single_word": false,
       "special": false
     },
-    "101": {
-      "content": "[PAD]",
+    "1": {
+      "content": "<s>",
       "lstrip": true,
       "normalized": false,
       "rstrip": true,
       "single_word": false,
       "special": false
     },
-    "102": {
-      "content": "<s>",
-      "lstrip": false,
+    "2": {
+      "content": "</s>",
+      "lstrip": true,
       "normalized": false,
-      "rstrip": false,
+      "rstrip": true,
       "single_word": false,
-      "special": true
+      "special": false
     },
-    "103": {
-      "content": "</s>",
-      "lstrip": false,
+    "3": {
+      "content": "<unk>",
+      "lstrip": true,
       "normalized": false,
-      "rstrip": false,
+      "rstrip": true,
       "single_word": false,
-      "special": true
+      "special": false
     }
   },
   "additional_special_tokens": [],
@@ -39,11 +39,11 @@
   "do_lower_case": false,
   "eos_token": "</s>",
   "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "[PAD]",
+  "pad_token": "<pad>",
   "replace_word_delimiter_char": " ",
   "target_lang": null,
   "tokenizer_class": "Wav2Vec2CTCTokenizer",
   "tokenizer_file": null,
-  "unk_token": "[UNK]",
+  "unk_token": "<unk>",
   "word_delimiter_token": "|"
 }

vocab.json

@@ -1,104 +1,88 @@
 {
-  " ": 0,
-  "&": 1,
-  "[PAD]": 101,
-  "[UNK]": 100,
-  "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,
-  "|": 28,
-  "ँ": 29,
-  "ं": 30,
-  "ः": 31,
-  "अ": 32,
-  "आ": 33,
-  "इ": 34,
-  "ई": 35,
-  "उ": 36,
-  "ऊ": 37,
-  "ऋ": 38,
-  "ए": 39,
-  "ऐ": 40,
-  "ऑ": 41,
-  "ओ": 42,
-  "औ": 43,
-  "क": 44,
-  "ख": 45,
-  "ग": 46,
-  "घ": 47,
-  "च": 48,
-  "छ": 49,
-  "ज": 50,
-  "झ": 51,
-  "ञ": 52,
-  "ट": 53,
-  "ठ": 54,
-  "ड": 55,
-  "ढ": 56,
-  "ण": 57,
-  "त": 58,
-  "थ": 59,
-  "द": 60,
-  "ध": 61,
-  "न": 62,
-  "प": 63,
-  "फ": 64,
-  "ब": 65,
-  "भ": 66,
-  "म": 67,
-  "य": 68,
-  "र": 69,
-  "ल": 70,
-  "व": 71,
-  "श": 72,
-  "ष": 73,
-  "स": 74,
-  "ह": 75,
-  "़": 76,
-  "ा": 77,
-  "ि": 78,
-  "ी": 79,
-  "ु": 80,
-  "ू": 81,
-  "ृ": 82,
-  "ॅ": 83,
-  "े": 84,
-  "ै": 85,
-  "ॉ": 86,
-  "ो": 87,
-  "ौ": 88,
-  "्": 89,
-  "क़": 90,
-  "ख़": 91,
-  "ग़": 92,
-  "ज़": 93,
-  "ड़": 94,
-  "ढ़": 95,
-  "फ़": 96,
-  "।": 97,
-  "–": 98,
-  "’": 99
+  "0": 5,
+  "1": 6,
+  "2": 7,
+  "3": 8,
+  "4": 9,
+  "5": 10,
+  "6": 11,
+  "7": 12,
+  "8": 13,
+  "9": 14,
+  "</s>": 2,
+  "<pad>": 0,
+  "<s>": 1,
+  "<unk>": 3,
+  "|": 4,
+  "ँ": 15,
+  "ं": 16,
+  "ः": 17,
+  "अ": 18,
+  "आ": 19,
+  "इ": 20,
+  "ई": 21,
+  "उ": 22,
+  "ऊ": 23,
+  "ऋ": 24,
+  "ए": 25,
+  "ऐ": 26,
+  "ऑ": 27,
+  "ओ": 28,
+  "औ": 29,
+  "क": 30,
+  "ख": 31,
+  "ग": 32,
+  "घ": 33,
+  "ङ": 34,
+  "च": 35,
+  "छ": 36,
+  "ज": 37,
+  "झ": 38,
+  "ञ": 39,
+  "ट": 40,
+  "ठ": 41,
+  "ड": 42,
+  "ढ": 43,
+  "ण": 44,
+  "त": 45,
+  "थ": 46,
+  "द": 47,
+  "ध": 48,
+  "न": 49,
+  "प": 50,
+  "फ": 51,
+  "ब": 52,
+  "भ": 53,
+  "म": 54,
+  "य": 55,
+  "र": 56,
+  "ल": 57,
+  "व": 58,
+  "श": 59,
+  "ष": 60,
+  "स": 61,
+  "ह": 62,
+  "़": 85,
+  "ा": 63,
+  "ि": 64,
+  "ी": 65,
+  "ु": 66,
+  "ू": 67,
+  "ृ": 68,
+  "ॅ": 69,
+  "े": 70,
+  "ै": 71,
+  "ॉ": 72,
+  "ो": 73,
+  "ौ": 74,
+  "्": 75,
+  "क़": 76,
+  "ख़": 77,
+  "ग़": 78,
+  "ज़": 79,
+  "ड़": 80,
+  "ढ़": 81,
+  "फ़": 82,
+  "य़": 83,
+  "।": 84
 }