hadiqa123
/

xls-r_cv_ur

Automatic Speech Recognition

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

hadiqa123 commited on Mar 1, 2023

Commit

4d0045d

•

1 Parent(s): 69494b9

add tokenizer

Files changed (2) hide show

tokenizer_config.json +0 -1
vocab.json +40 -40

tokenizer_config.json CHANGED Viewed

@@ -2,7 +2,6 @@
   "bos_token": "<s>",
   "do_lower_case": false,
   "eos_token": "</s>",
-  "model_max_length": 1000000000000000019884624838656,
   "pad_token": "[PAD]",
   "replace_word_delimiter_char": " ",
   "tokenizer_class": "Wav2Vec2CTCTokenizer",

   "bos_token": "<s>",
   "do_lower_case": false,
   "eos_token": "</s>",
   "pad_token": "[PAD]",
   "replace_word_delimiter_char": " ",
   "tokenizer_class": "Wav2Vec2CTCTokenizer",

vocab.json CHANGED Viewed

@@ -1,47 +1,47 @@
 {
-  " ": 32,
   "PAD": 43,
   "[UNK]": 44,
-  "آ": 21,
-  "أ": 20,
-  "ؤ": 18,
-  "ئ": 38,
-  "ا": 9,
-  "ب": 27,
-  "ت": 34,
   "ث": 19,
-  "ج": 37,
-  "ح": 16,
-  "خ": 13,
-  "د": 41,
-  "ذ": 23,
-  "ر": 25,
-  "ز": 17,
-  "س": 3,
-  "ش": 30,
-  "ص": 33,
-  "ض": 42,
-  "ط": 36,
-  "ظ": 35,
-  "ع": 15,
-  "غ": 8,
-  "ف": 29,
-  "ق": 2,
-  "ل": 0,
-  "م": 24,
-  "ن": 28,
-  "و": 5,
-  "ً": 6,
-  "ٹ": 39,
   "پ": 7,
-  "چ": 10,
-  "ڈ": 1,
-  "ڑ": 14,
-  "ک": 40,
-  "گ": 26,
-  "ں": 12,
-  "ھ": 4,
   "ہ": 31,
-  "ی": 22,
-  "ے": 11
 }

 {
+  " ": 35,
   "PAD": 43,
   "[UNK]": 44,
+  "آ": 37,
+  "أ": 21,
+  "ؤ": 1,
+  "ئ": 39,
+  "ا": 29,
+  "ب": 2,
+  "ت": 5,
   "ث": 19,
+  "ج": 12,
+  "ح": 20,
+  "خ": 23,
+  "د": 4,
+  "ذ": 3,
+  "ر": 36,
+  "ز": 10,
+  "س": 8,
+  "ش": 24,
+  "ص": 13,
+  "ض": 34,
+  "ط": 18,
+  "ظ": 6,
+  "ع": 42,
+  "غ": 40,
+  "ف": 14,
+  "ق": 17,
+  "ل": 38,
+  "م": 11,
+  "ن": 32,
+  "و": 0,
+  "ً": 22,
+  "ٹ": 15,
   "پ": 7,
+  "چ": 28,
+  "ڈ": 9,
+  "ڑ": 26,
+  "ک": 16,
+  "گ": 41,
+  "ں": 33,
+  "ھ": 30,
   "ہ": 31,
+  "ی": 25,
+  "ے": 27
 }