Upload tokenizer

added_tokens.json

@@ -1,4 +1,4 @@
 {
-  "</s>": 79,
-  "<s>": 78
+  "</s>": 71,
+  "<s>": 70
 }

tokenizer_config.json

@@ -1,6 +1,6 @@
 {
   "added_tokens_decoder": {
-    "76": {
+    "68": {
       "content": "[UNK]",
       "lstrip": true,
       "normalized": false,
@@ -8,7 +8,7 @@
       "single_word": false,
       "special": false
     },
-    "77": {
+    "69": {
       "content": "[PAD]",
       "lstrip": true,
       "normalized": false,
@@ -16,7 +16,7 @@
       "single_word": false,
       "special": false
     },
-    "78": {
+    "70": {
       "content": "<s>",
       "lstrip": false,
       "normalized": false,
@@ -24,7 +24,7 @@
       "single_word": false,
       "special": true
     },
-    "79": {
+    "71": {
       "content": "</s>",
       "lstrip": false,
       "normalized": false,
@@ -39,7 +39,6 @@
   "eos_token": "</s>",
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "[PAD]",
-  "processor_class": "Wav2Vec2BertProcessor",
   "replace_word_delimiter_char": " ",
   "target_lang": null,
   "tokenizer_class": "Wav2Vec2CTCTokenizer",

vocab.json

@@ -1,80 +1,72 @@
 {
-  "[PAD]": 77,
-  "[UNK]": 76,
-  "a": 1,
-  "b": 2,
-  "c": 3,
-  "e": 4,
-  "f": 5,
-  "k": 6,
-  "o": 7,
+  "[PAD]": 69,
+  "[UNK]": 68,
   "|": 0,
-  "ँ": 8,
-  "ं": 9,
-  "ः": 10,
-  "अ": 11,
-  "आ": 12,
-  "इ": 13,
-  "ई": 14,
-  "उ": 15,
-  "ऊ": 16,
-  "ऋ": 17,
-  "ए": 18,
-  "ऐ": 19,
-  "ओ": 20,
-  "औ": 21,
-  "क": 22,
-  "ख": 23,
-  "ग": 24,
-  "घ": 25,
-  "ङ": 26,
-  "च": 27,
-  "छ": 28,
-  "ज": 29,
-  "झ": 30,
-  "ञ": 31,
-  "ट": 32,
-  "ठ": 33,
-  "ड": 34,
-  "ढ": 35,
-  "ण": 36,
-  "त": 37,
-  "थ": 38,
-  "द": 39,
-  "ध": 40,
-  "न": 41,
-  "प": 42,
-  "फ": 43,
-  "ब": 44,
-  "भ": 45,
-  "म": 46,
-  "य": 47,
-  "र": 48,
-  "ऱ": 49,
-  "ल": 50,
-  "व": 51,
-  "श": 52,
-  "ष": 53,
-  "स": 54,
-  "ह": 55,
-  "़": 56,
-  "ा": 57,
-  "ि": 58,
-  "ी": 59,
-  "ु": 60,
-  "ू": 61,
-  "ृ": 62,
-  "े": 63,
-  "ै": 64,
-  "ॊ": 65,
-  "ो": 66,
-  "ौ": 67,
-  "्": 68,
-  "ॐ": 69,
-  "ॠ": 70,
-  "।": 71,
-  "॰": 72,
-  "‌": 73,
-  "‍": 74,
-  "‎": 75
+  "ँ": 1,
+  "ं": 2,
+  "ः": 3,
+  "अ": 4,
+  "आ": 5,
+  "इ": 6,
+  "ई": 7,
+  "उ": 8,
+  "ऊ": 9,
+  "ऋ": 10,
+  "ए": 11,
+  "ऐ": 12,
+  "ओ": 13,
+  "औ": 14,
+  "क": 15,
+  "ख": 16,
+  "ग": 17,
+  "घ": 18,
+  "ङ": 19,
+  "च": 20,
+  "छ": 21,
+  "ज": 22,
+  "झ": 23,
+  "ञ": 24,
+  "ट": 25,
+  "ठ": 26,
+  "ड": 27,
+  "ढ": 28,
+  "ण": 29,
+  "त": 30,
+  "थ": 31,
+  "द": 32,
+  "ध": 33,
+  "न": 34,
+  "प": 35,
+  "फ": 36,
+  "ब": 37,
+  "भ": 38,
+  "म": 39,
+  "य": 40,
+  "र": 41,
+  "ल": 42,
+  "व": 43,
+  "श": 44,
+  "ष": 45,
+  "स": 46,
+  "ह": 47,
+  "़": 48,
+  "ा": 49,
+  "ि": 50,
+  "ी": 51,
+  "ु": 52,
+  "ू": 53,
+  "ृ": 54,
+  "े": 55,
+  "ै": 56,
+  "ॊ": 57,
+  "ो": 58,
+  "ौ": 59,
+  "्": 60,
+  "ॐ": 61,
+  "ॠ": 62,
+  "।": 63,
+  "॰": 64,
+  "‌": 65,
+  "‍": 66,
+  "‎": 67
 }