Upload tokenizer

README.md

@@ -1,8 +1,8 @@
 ---
 license: mit
-base_model: facebook/w2v-bert-2.0
 tags:
 - generated_from_trainer
+base_model: facebook/w2v-bert-2.0
 model-index:
 - name: w2v-bert-odia_v1
   results: []

added_tokens.json

@@ -1,4 +1,4 @@
 {
-  "</s>": 90,
-  "<s>": 89
+  "</s>": 69,
+  "<s>": 68
 }

tokenizer_config.json

@@ -1,6 +1,6 @@
 {
   "added_tokens_decoder": {
-    "87": {
+    "66": {
       "content": "[UNK]",
       "lstrip": true,
       "normalized": false,
@@ -8,7 +8,7 @@
       "single_word": false,
       "special": false
     },
-    "88": {
+    "67": {
       "content": "[PAD]",
       "lstrip": true,
       "normalized": false,
@@ -16,7 +16,7 @@
       "single_word": false,
       "special": false
     },
-    "89": {
+    "68": {
       "content": "<s>",
       "lstrip": false,
       "normalized": false,
@@ -24,7 +24,7 @@
       "single_word": false,
       "special": true
     },
-    "90": {
+    "69": {
       "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

@@ -1,91 +1,70 @@
 {
-  "0": 1,
-  "1": 2,
-  "2": 3,
-  "3": 4,
-  "5": 5,
-  "7": 6,
-  "8": 7,
-  "9": 8,
-  "[PAD]": 88,
-  "[UNK]": 87,
+  "[PAD]": 67,
+  "[UNK]": 66,
   "|": 0,
-  "।": 9,
-  "ଁ": 10,
-  "ଂ": 11,
-  "ଃ": 12,
-  "ଅ": 13,
-  "ଆ": 14,
-  "ଇ": 15,
-  "ଈ": 16,
-  "ଉ": 17,
-  "ଊ": 18,
-  "ଋ": 19,
-  "ଏ": 20,
-  "ଐ": 21,
-  "ଓ": 22,
-  "ଔ": 23,
-  "କ": 24,
-  "ଖ": 25,
-  "ଗ": 26,
-  "ଘ": 27,
-  "ଙ": 28,
-  "ଚ": 29,
-  "ଛ": 30,
-  "ଜ": 31,
-  "ଝ": 32,
-  "ଞ": 33,
-  "ଟ": 34,
-  "ଠ": 35,
-  "ଡ": 36,
-  "ଢ": 37,
-  "ଣ": 38,
-  "ତ": 39,
-  "ଥ": 40,
-  "ଦ": 41,
-  "ଧ": 42,
-  "ନ": 43,
-  "ପ": 44,
-  "ଫ": 45,
-  "ବ": 46,
-  "ଭ": 47,
-  "ମ": 48,
-  "ଯ": 49,
-  "ର": 50,
-  "ଲ": 51,
-  "ଳ": 52,
-  "ଵ": 53,
-  "ଶ": 54,
-  "ଷ": 55,
-  "ସ": 56,
-  "ହ": 57,
-  "଼": 58,
-  "ା": 59,
-  "ି": 60,
-  "ୀ": 61,
-  "ୁ": 62,
-  "ୂ": 63,
-  "ୃ": 64,
-  "େ": 65,
-  "ୈ": 66,
-  "ୋ": 67,
-  "ୌ": 68,
-  "୍": 69,
-  "ଡ଼": 70,
-  "ଢ଼": 71,
-  "ୟ": 72,
-  "୦": 73,
-  "୧": 74,
-  "୨": 75,
-  "୩": 76,
-  "୪": 77,
-  "୫": 78,
-  "୬": 79,
-  "୭": 80,
-  "୮": 81,
-  "୯": 82,
-  "ୱ": 83,
-  "‌": 84,
-  "–": 85,
-  "’": 86
+  "।": 1,
+  "ଁ": 2,
+  "ଂ": 3,
+  "ଃ": 4,
+  "ଅ": 5,
+  "ଆ": 6,
+  "ଇ": 7,
+  "ଈ": 8,
+  "ଉ": 9,
+  "ଊ": 10,
+  "ଋ": 11,
+  "ଏ": 12,
+  "ଐ": 13,
+  "ଓ": 14,
+  "ଔ": 15,
+  "କ": 16,
+  "ଖ": 17,
+  "ଗ": 18,
+  "ଘ": 19,
+  "ଙ": 20,
+  "ଚ": 21,
+  "ଛ": 22,
+  "ଜ": 23,
+  "ଝ": 24,
+  "ଞ": 25,
+  "ଟ": 26,
+  "ଠ": 27,
+  "ଡ": 28,
+  "ଢ": 29,
+  "ଣ": 30,
+  "ତ": 31,
+  "ଥ": 32,
+  "ଦ": 33,
+  "ଧ": 34,
+  "ନ": 35,
+  "ପ": 36,
+  "ଫ": 37,
+  "ବ": 38,
+  "ଭ": 39,
+  "ମ": 40,
+  "ଯ": 41,
+  "ର": 42,
+  "ଲ": 43,
+  "ଳ": 44,
+  "ଵ": 45,
+  "ଶ": 46,
+  "ଷ": 47,
+  "ସ": 48,
+  "ହ": 49,
+  "଼": 50,
+  "ା": 51,
+  "ି": 52,
+  "ୀ": 53,
+  "ୁ": 54,
+  "ୂ": 55,
+  "ୃ": 56,
+  "େ": 57,
+  "ୈ": 58,
+  "ୋ": 59,
+  "ୌ": 60,
+  "୍": 61,
+  "ଡ଼": 62,
+  "ଢ଼": 63,
+  "ୟ": 64,
+  "ୱ": 65
 }