Upload tokenizer

README.md

@@ -1,8 +1,8 @@
 ---
 license: apache-2.0
-base_model: facebook/wav2vec2-large-xlsr-53
 tags:
 - generated_from_trainer
+base_model: facebook/wav2vec2-large-xlsr-53
 datasets:
 - common_voice_11_0
 model-index:

added_tokens.json

@@ -1,4 +1,4 @@
 {
-  "</s>": 76,
-  "<s>": 75
+  "</s>": 86,
+  "<s>": 85
 }

tokenizer_config.json

@@ -1,6 +1,6 @@
 {
   "added_tokens_decoder": {
-    "73": {
+    "83": {
       "content": "[UNK]",
       "lstrip": true,
       "normalized": false,
@@ -8,7 +8,7 @@
       "single_word": false,
       "special": false
     },
-    "74": {
+    "84": {
       "content": "[PAD]",
       "lstrip": true,
       "normalized": false,
@@ -16,7 +16,7 @@
       "single_word": false,
       "special": false
     },
-    "75": {
+    "85": {
       "content": "<s>",
       "lstrip": false,
       "normalized": false,
@@ -24,7 +24,7 @@
       "single_word": false,
       "special": true
     },
-    "76": {
+    "86": {
       "content": "</s>",
       "lstrip": false,
       "normalized": false,

vocab.json

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