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

9f0f86b

•

1 Parent(s): 943132a

add tokenizer

Files changed (2) hide show

tokenizer_config.json +0 -1
vocab.json +43 -43

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

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