Upload tokenizer

added_tokens.json

@@ -1,4 +1,4 @@
 {
-  "</s>": 73,
-  "<s>": 72
+  "</s>": 66,
+  "<s>": 65
 }

tokenizer_config.json

@@ -1,6 +1,6 @@
 {
   "added_tokens_decoder": {
-    "70": {
+    "63": {
       "content": "[UNK]",
       "lstrip": true,
       "normalized": false,
@@ -8,7 +8,7 @@
       "single_word": false,
       "special": false
     },
-    "71": {
+    "64": {
       "content": "[PAD]",
       "lstrip": true,
       "normalized": false,
@@ -16,7 +16,7 @@
       "single_word": false,
       "special": false
     },
-    "72": {
+    "65": {
       "content": "<s>",
       "lstrip": false,
       "normalized": false,
@@ -24,7 +24,7 @@
       "single_word": false,
       "special": true
     },
-    "73": {
+    "66": {
       "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",
   "tokenizer_class": "Wav2Vec2CTCTokenizer",

vocab.json

@@ -76,76 +76,69 @@
   },
   "tam": {
     "&": 1,
-    "[PAD]": 71,
-    "[UNK]": 70,
+    "[PAD]": 64,
+    "[UNK]": 63,
     "_": 2,
     "`": 3,
     "|": 0,
     "·": 4,
     "½": 5,
-    "¾": 6,
-    "á": 7,
-    "é": 8,
-    "ô": 9,
-    "š": 10,
-    "ஃ": 11,
-    "அ": 12,
-    "ஆ": 13,
-    "இ": 14,
-    "ஈ": 15,
-    "உ": 16,
-    "ஊ": 17,
-    "எ": 18,
-    "ஏ": 19,
-    "ஐ": 20,
-    "ஒ": 21,
-    "ஓ": 22,
-    "ஔ": 23,
-    "க": 24,
-    "ங": 25,
-    "ச": 26,
-    "ஜ": 27,
-    "ஞ": 28,
-    "ட": 29,
-    "ண": 30,
-    "த": 31,
-    "ந": 32,
-    "ன": 33,
-    "ப": 34,
-    "ம": 35,
-    "ய": 36,
-    "ர": 37,
-    "ற": 38,
-    "ல": 39,
-    "ள": 40,
-    "ழ": 41,
-    "வ": 42,
-    "ஷ": 43,
-    "ஸ": 44,
-    "ஹ": 45,
-    "ா": 46,
-    "ி": 47,
-    "ீ": 48,
-    "ு": 49,
-    "ூ": 50,
-    "ெ": 51,
-    "ே": 52,
-    "ை": 53,
-    "ொ": 54,
-    "ோ": 55,
-    "ௌ": 56,
-    "்": 57,
-    "ௗ": 58,
-    "ഥ": 59,
-    "–": 60,
-    "—": 61,
-    "’": 62,
-    "‚": 63,
-    "•": 64,
-    "…": 65,
-    "′": 66,
-    "″": 67,
-    "●": 68,
-    "◯": 69
+    "á": 6,
+    "é": 7,
+    "ô": 8,
+    "š": 9,
+    "ஃ": 10,
+    "அ": 11,
+    "ஆ": 12,
+    "இ": 13,
+    "ஈ": 14,
+    "உ": 15,
+    "ஊ": 16,
+    "எ": 17,
+    "ஏ": 18,
+    "ஐ": 19,
+    "ஒ": 20,
+    "ஓ": 21,
+    "ஔ": 22,
+    "க": 23,
+    "ங": 24,
+    "ச": 25,
+    "ஜ": 26,
+    "ஞ": 27,
+    "ட": 28,
+    "ண": 29,
+    "த": 30,
+    "ந": 31,
+    "ன": 32,
+    "ப": 33,
+    "ம": 34,
+    "ய": 35,
+    "ர": 36,
+    "ற": 37,
+    "ல": 38,
+    "ள": 39,
+    "ழ": 40,
+    "வ": 41,
+    "ஷ": 42,
+    "ஸ": 43,
+    "ஹ": 44,
+    "ா": 45,
+    "ி": 46,
+    "ீ": 47,
+    "ு": 48,
+    "ூ": 49,
+    "ெ": 50,
+    "ே": 51,
+    "ை": 52,
+    "ொ": 53,
+    "ோ": 54,
+    "ௌ": 55,
+    "்": 56,
+    "ௗ": 57,
+    "ഥ": 58,
+    "’": 59,
+    "•": 60,
+    "●": 61,
+    "◯": 62
   }
 }