Upload tokenizer

added_tokens.json

@@ -1,4 +1,4 @@
 {
-  "</s>": 86,
-  "<s>": 85
+  "</s>": 78,
+  "<s>": 77
 }

tokenizer_config.json

@@ -1,6 +1,6 @@
 {
   "added_tokens_decoder": {
-    "83": {
+    "75": {
       "content": "[UNK]",
       "lstrip": true,
       "normalized": false,
@@ -8,7 +8,7 @@
       "single_word": false,
       "special": false
     },
-    "84": {
+    "76": {
       "content": "[PAD]",
       "lstrip": true,
       "normalized": false,
@@ -16,7 +16,7 @@
       "single_word": false,
       "special": false
     },
-    "85": {
+    "77": {
       "content": "<s>",
       "lstrip": false,
       "normalized": false,
@@ -24,7 +24,7 @@
       "single_word": false,
       "special": true
     },
-    "86": {
+    "78": {
       "content": "</s>",
       "lstrip": false,
       "normalized": false,
@@ -39,7 +39,6 @@
   "eos_token": "</s>",
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "[PAD]",
-  "processor_class": "Wav2Vec2Processor",
   "replace_word_delimiter_char": " ",
   "target_lang": null,
   "tokenizer_class": "Wav2Vec2CTCTokenizer",

vocab.json

@@ -1,87 +1,79 @@
 {
-  "!": 76,
-  "\"": 77,
-  "'": 71,
-  ",": 7,
-  "-": 54,
-  ".": 67,
-  ":": 55,
-  ";": 40,
-  "?": 10,
-  "[PAD]": 84,
-  "[UNK]": 83,
-  "|": 12,
-  "ം": 65,
-  "ഃ": 4,
-  "അ": 75,
-  "ആ": 24,
-  "ഇ": 5,
-  "ഈ": 35,
-  "ഉ": 52,
-  "ഊ": 79,
-  "എ": 18,
-  "ഏ": 33,
-  "ഐ": 6,
-  "ഒ": 46,
-  "ഓ": 25,
-  "ഔ": 1,
-  "ക": 38,
-  "ഖ": 15,
-  "ഗ": 39,
-  "ഘ": 29,
-  "ങ": 36,
-  "ച": 58,
-  "ഛ": 62,
-  "ജ": 14,
-  "ഞ": 50,
-  "ട": 63,
-  "ഠ": 37,
-  "ഡ": 59,
-  "ഢ": 44,
-  "ണ": 69,
-  "ത": 70,
-  "ഥ": 68,
+  "'": 5,
+  "[PAD]": 76,
+  "[UNK]": 75,
+  "|": 52,
+  "ം": 35,
+  "ഃ": 29,
+  "അ": 49,
+  "ആ": 46,
+  "ഇ": 17,
+  "ഈ": 36,
+  "ഉ": 57,
+  "ഊ": 67,
+  "എ": 16,
+  "ഏ": 22,
+  "ഐ": 15,
+  "ഒ": 39,
+  "ഓ": 65,
+  "ഔ": 61,
+  "ക": 53,
+  "ഖ": 44,
+  "ഗ": 10,
+  "ഘ": 38,
+  "ങ": 27,
+  "ച": 14,
+  "ഛ": 47,
+  "ജ": 0,
+  "ഞ": 24,
+  "ട": 56,
+  "ഠ": 23,
+  "ഡ": 11,
+  "ഢ": 8,
+  "ണ": 51,
+  "ത": 55,
+  "ഥ": 59,
   "ദ": 66,
-  "ധ": 78,
-  "ന": 31,
-  "പ": 20,
-  "ഫ": 56,
-  "ബ": 47,
-  "ഭ": 45,
-  "മ": 3,
-  "യ": 81,
-  "ര": 23,
-  "റ": 82,
-  "ല": 74,
-  "ള": 21,
-  "ഴ": 57,
-  "വ": 60,
-  "ശ": 16,
-  "ഷ": 32,
-  "സ": 22,
-  "ഹ": 26,
-  "ാ": 80,
-  "ി": 64,
-  "ീ": 9,
-  "ു": 11,
-  "ൂ": 43,
-  "ൃ": 53,
-  "െ": 42,
-  "േ": 49,
-  "ൈ": 51,
-  "ൊ": 27,
-  "ോ": 0,
-  "ൌ": 48,
-  "്": 34,
-  "ൗ": 72,
-  "ൺ": 17,
-  "ൻ": 73,
-  "ർ": 19,
-  "ൽ": 41,
-  "ൾ": 13,
-  "ൿ": 2,
-  "‘": 28,
-  "’": 30,
-  "“": 61,
-  "”": 8
+  "ധ": 28,
+  "ന": 64,
+  "പ": 42,
+  "ഫ": 40,
+  "ബ": 25,
+  "ഭ": 50,
+  "മ": 43,
+  "യ": 18,
+  "ര": 19,
+  "റ": 21,
+  "ല": 62,
+  "ള": 63,
+  "ഴ": 3,
+  "വ": 48,
+  "ശ": 30,
+  "ഷ": 74,
+  "സ": 9,
+  "ഹ": 69,
+  "ാ": 26,
+  "ി": 12,
+  "ീ": 37,
+  "ു": 68,
+  "ൂ": 33,
+  "ൃ": 1,
+  "െ": 7,
+  "േ": 58,
+  "ൈ": 54,
+  "ൊ": 71,
+  "ോ": 2,
+  "ൌ": 4,
+  "്": 45,
+  "ൗ": 60,
+  "ൺ": 31,
+  "ൻ": 32,
+  "ർ": 72,
+  "ൽ": 13,
+  "ൾ": 73,
+  "ൿ": 70,
+  "‘": 6,
+  "’": 41,
+  "“": 20,
+  "”": 34
 }