Upload tokenizer

added_tokens.json

@@ -1,4 +1,4 @@
 {
-  "</s>": 55,
-  "<s>": 54
+  "</s>": 56,
+  "<s>": 55
 }

tokenizer_config.json

@@ -1,6 +1,6 @@
 {
   "added_tokens_decoder": {
-    "52": {
+    "53": {
       "content": "[UNK]",
       "lstrip": true,
       "normalized": false,
@@ -8,7 +8,7 @@
       "single_word": false,
       "special": false
     },
-    "53": {
+    "54": {
       "content": "[PAD]",
       "lstrip": true,
       "normalized": false,
@@ -16,7 +16,7 @@
       "single_word": false,
       "special": false
     },
-    "54": {
+    "55": {
       "content": "<s>",
       "lstrip": false,
       "normalized": false,
@@ -24,7 +24,7 @@
       "single_word": false,
       "special": true
     },
-    "55": {
+    "56": {
       "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": "tam-32",
   "tokenizer_class": "Wav2Vec2CTCTokenizer",

vocab.json

@@ -1,58 +1,59 @@
 {
   "tam-32": {
     "&": 1,
-    "[PAD]": 53,
-    "[UNK]": 52,
+    "[PAD]": 54,
+    "[UNK]": 53,
     "_": 2,
     "|": 0,
-    "ஃ": 3,
-    "அ": 4,
-    "ஆ": 5,
-    "இ": 6,
-    "ஈ": 7,
-    "உ": 8,
-    "ஊ": 9,
-    "எ": 10,
-    "ஏ": 11,
-    "ஐ": 12,
-    "ஒ": 13,
-    "ஓ": 14,
-    "ஔ": 15,
-    "க": 16,
-    "ங": 17,
-    "ச": 18,
-    "ஜ": 19,
-    "ஞ": 20,
-    "ட": 21,
-    "ண": 22,
-    "த": 23,
-    "ந": 24,
-    "ன": 25,
-    "ப": 26,
-    "ம": 27,
-    "ய": 28,
-    "ர": 29,
-    "ற": 30,
-    "ல": 31,
-    "ள": 32,
-    "ழ": 33,
-    "வ": 34,
-    "ஷ": 35,
-    "ஸ": 36,
-    "ஹ": 37,
-    "ா": 38,
-    "ி": 39,
-    "ீ": 40,
-    "ு": 41,
-    "ூ": 42,
-    "ெ": 43,
-    "ே": 44,
-    "ை": 45,
-    "ொ": 46,
-    "ோ": 47,
-    "ௌ": 48,
-    "்": 49,
-    "ௗ": 50,
-    "ഥ": 51
+    "¾": 3,
+    "ஃ": 4,
+    "அ": 5,
+    "ஆ": 6,
+    "இ": 7,
+    "ஈ": 8,
+    "உ": 9,
+    "ஊ": 10,
+    "எ": 11,
+    "ஏ": 12,
+    "ஐ": 13,
+    "ஒ": 14,
+    "ஓ": 15,
+    "ஔ": 16,
+    "க": 17,
+    "ங": 18,
+    "ச": 19,
+    "ஜ": 20,
+    "ஞ": 21,
+    "ட": 22,
+    "ண": 23,
+    "த": 24,
+    "ந": 25,
+    "ன": 26,
+    "ப": 27,
+    "ம": 28,
+    "ய": 29,
+    "ர": 30,
+    "ற": 31,
+    "ல": 32,
+    "ள": 33,
+    "ழ": 34,
+    "வ": 35,
+    "ஷ": 36,
+    "ஸ": 37,
+    "ஹ": 38,
+    "ா": 39,
+    "ி": 40,
+    "ீ": 41,
+    "ு": 42,
+    "ூ": 43,
+    "ெ": 44,
+    "ே": 45,
+    "ை": 46,
+    "ொ": 47,
+    "ோ": 48,
+    "ௌ": 49,
+    "்": 50,
+    "ௗ": 51,
+    "ഥ": 52
   }
 }