Upload tokenizer

README.md

@@ -1,10 +1,10 @@
 ---
-license: apache-2.0
 base_model: facebook/wav2vec2-xls-r-300m
-tags:
-- generated_from_trainer
+license: apache-2.0
 metrics:
 - wer
+tags:
+- generated_from_trainer
 model-index:
 - name: wav2vec2-large-xls-r-300m-hindi_marathi-colab
   results: []

added_tokens.json

@@ -1,4 +1,4 @@
 {
-  "</s>": 155,
-  "<s>": 154
+  "</s>": 152,
+  "<s>": 151
 }

tokenizer_config.json

@@ -1,6 +1,6 @@
 {
   "added_tokens_decoder": {
-    "152": {
+    "149": {
       "content": "[UNK]",
       "lstrip": true,
       "normalized": false,
@@ -8,7 +8,7 @@
       "single_word": false,
       "special": false
     },
-    "153": {
+    "150": {
       "content": "[PAD]",
       "lstrip": true,
       "normalized": false,
@@ -16,7 +16,7 @@
       "single_word": false,
       "special": false
     },
-    "154": {
+    "151": {
       "content": "<s>",
       "lstrip": false,
       "normalized": false,
@@ -24,7 +24,7 @@
       "single_word": false,
       "special": true
     },
-    "155": {
+    "152": {
       "content": "</s>",
       "lstrip": false,
       "normalized": false,

vocab.json

@@ -34,8 +34,8 @@
   "X": 32,
   "Y": 33,
   "Z": 34,
-  "[PAD]": 153,
-  "[UNK]": 152,
+  "[PAD]": 150,
+  "[UNK]": 149,
   "a": 35,
   "b": 36,
   "c": 37,
@@ -137,20 +137,17 @@
   "॓": 133,
   "॔": 134,
   "क़": 135,
-  "ख़": 136,
-  "ग़": 137,
-  "ज़": 138,
-  "ड़": 139,
-  "ढ़": 140,
-  "फ़": 141,
-  "य़": 142,
-  "ॢ": 143,
-  "।": 144,
-  "॥": 145,
-  "ॲ": 146,
-  "–": 147,
-  "‘": 148,
-  "’": 149,
-  "“": 150,
-  "”": 151
+  "ग़": 136,
+  "ज़": 137,
+  "ड़": 138,
+  "ढ़": 139,
+  "फ़": 140,
+  "य़": 141,
+  "।": 142,
+  "॥": 143,
+  "ॲ": 144,
+  "‘": 145,
+  "’": 146,
+  "“": 147,
+  "”": 148
 }