Upload tokenizer

added_tokens.json

@@ -1,6 +1,6 @@
 {
-  "</s>": 91,
-  "<s>": 90,
-  "[PAD]": 89,
-  "[UNK]": 88
+  "</s>": 2,
+  "<pad>": 1,
+  "<s>": 0,
+  "<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": {
-    "88": {
-      "content": "[UNK]",
+    "0": {
+      "content": "<s>",
       "lstrip": true,
       "normalized": false,
       "rstrip": true,
       "single_word": false,
       "special": false
     },
-    "89": {
-      "content": "[PAD]",
+    "1": {
+      "content": "<pad>",
       "lstrip": true,
       "normalized": false,
       "rstrip": true,
       "single_word": false,
       "special": false
     },
-    "90": {
-      "content": "<s>",
-      "lstrip": false,
+    "2": {
+      "content": "</s>",
+      "lstrip": true,
       "normalized": false,
-      "rstrip": false,
+      "rstrip": true,
       "single_word": false,
-      "special": true
+      "special": false
     },
-    "91": {
-      "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

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