Upload tokenizer

README.md

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

added_tokens.json

@@ -1,4 +1,4 @@
 {
-  "</s>": 80,
-  "<s>": 79
+  "</s>": 94,
+  "<s>": 93
 }

tokenizer_config.json

@@ -1,6 +1,6 @@
 {
   "added_tokens_decoder": {
-    "77": {
+    "91": {
       "content": "[UNK]",
       "lstrip": true,
       "normalized": false,
@@ -8,7 +8,7 @@
       "single_word": false,
       "special": false
     },
-    "78": {
+    "92": {
       "content": "[PAD]",
       "lstrip": true,
       "normalized": false,
@@ -16,7 +16,7 @@
       "single_word": false,
       "special": false
     },
-    "79": {
+    "93": {
       "content": "<s>",
       "lstrip": false,
       "normalized": false,
@@ -24,7 +24,7 @@
       "single_word": false,
       "special": true
     },
-    "80": {
+    "94": {
       "content": "</s>",
       "lstrip": false,
       "normalized": false,

vocab.json

@@ -1,7 +1,7 @@
 {
   " ": 0,
-  "[PAD]": 78,
-  "[UNK]": 77,
+  "[PAD]": 92,
+  "[UNK]": 91,
   "a": 1,
   "b": 2,
   "c": 3,
@@ -27,55 +27,69 @@
   "w": 23,
   "x": 24,
   "y": 25,
-  "|": 76,
-  "ঁ": 26,
-  "ং": 27,
-  "অ": 28,
-  "আ": 29,
-  "ই": 30,
-  "ঈ": 31,
-  "উ": 32,
-  "এ": 33,
-  "ও": 34,
-  "ক": 35,
-  "খ": 36,
-  "গ": 37,
-  "ঘ": 38,
-  "ঙ": 39,
-  "চ": 40,
-  "ছ": 41,
-  "জ": 42,
-  "ঞ": 43,
-  "ট": 44,
-  "ঠ": 45,
-  "ড": 46,
-  "ণ": 47,
-  "ত": 48,
-  "থ": 49,
-  "দ": 50,
-  "ধ": 51,
-  "ন": 52,
-  "প": 53,
-  "ফ": 54,
-  "ব": 55,
-  "ভ": 56,
-  "ম": 57,
-  "য": 58,
-  "র": 59,
-  "ল": 60,
-  "শ": 61,
-  "ষ": 62,
-  "স": 63,
-  "হ": 64,
-  "়": 65,
-  "া": 66,
-  "ি": 67,
-  "ী": 68,
-  "ু": 69,
-  "ৃ": 70,
-  "ে": 71,
-  "ো": 72,
-  "্": 73,
-  "ড়": 74,
-  "য়": 75
+  "z": 26,
+  "|": 90,
+  " ": 27,
+  "ঁ": 28,
+  "ং": 29,
+  "ঃ": 30,
+  "অ": 31,
+  "আ": 32,
+  "ই": 33,
+  "ঈ": 34,
+  "উ": 35,
+  "এ": 36,
+  "ঐ": 37,
+  "ও": 38,
+  "ঔ": 39,
+  "ক": 40,
+  "খ": 41,
+  "গ": 42,
+  "ঘ": 43,
+  "ঙ": 44,
+  "চ": 45,
+  "ছ": 46,
+  "জ": 47,
+  "ঝ": 48,
+  "ঞ": 49,
+  "ট": 50,
+  "ঠ": 51,
+  "ড": 52,
+  "ঢ": 53,
+  "ণ": 54,
+  "ত": 55,
+  "থ": 56,
+  "দ": 57,
+  "ধ": 58,
+  "ন": 59,
+  "প": 60,
+  "ফ": 61,
+  "ব": 62,
+  "ভ": 63,
+  "ম": 64,
+  "য": 65,
+  "র": 66,
+  "ল": 67,
+  "শ": 68,
+  "ষ": 69,
+  "স": 70,
+  "হ": 71,
+  "়": 72,
+  "া": 73,
+  "ি": 74,
+  "ী": 75,
+  "ু": 76,
+  "ূ": 77,
+  "ৃ": 78,
+  "ে": 79,
+  "ৈ": 80,
+  "ো": 81,
+  "ৌ": 82,
+  "্": 83,
+  "ৎ": 84,
+  "ড়": 85,
+  "য়": 86,
+  "০": 87,
+  "২": 88,
+  "৬": 89
 }