Upload tokenizer

README.md

@@ -9,8 +9,8 @@ model-index:
 - name: w2v2-bert-urdu
   results:
   - task:
-      name: Automatic Speech Recognition
       type: automatic-speech-recognition
+      name: Automatic Speech Recognition
     dataset:
       name: common_voice_17_0
       type: common_voice_17_0
@@ -18,9 +18,9 @@ model-index:
       split: test[:100]
       args: ur
     metrics:
-    - name: Wer
-      type: wer
+    - type: wer
       value: 0.3300546448087432
+      name: Wer
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You

added_tokens.json

@@ -1,4 +1,4 @@
 {
-  "</s>": 64,
-  "<s>": 63
+  "</s>": 48,
+  "<s>": 47
 }

special_tokens_map.json

@@ -1,30 +1,6 @@
 {
-  "bos_token": {
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "[PAD]",
-    "lstrip": true,
-    "normalized": false,
-    "rstrip": true,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "[UNK]",
-    "lstrip": true,
-    "normalized": false,
-    "rstrip": true,
-    "single_word": false
-  }
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "[PAD]",
+  "unk_token": "[UNK]"
 }

tokenizer_config.json

@@ -1,6 +1,6 @@
 {
   "added_tokens_decoder": {
-    "61": {
+    "45": {
       "content": "[UNK]",
       "lstrip": true,
       "normalized": false,
@@ -8,7 +8,7 @@
       "single_word": false,
       "special": false
     },
-    "62": {
+    "46": {
       "content": "[PAD]",
       "lstrip": true,
       "normalized": false,
@@ -16,7 +16,7 @@
       "single_word": false,
       "special": false
     },
-    "63": {
+    "47": {
       "content": "<s>",
       "lstrip": false,
       "normalized": false,
@@ -24,7 +24,7 @@
       "single_word": false,
       "special": true
     },
-    "64": {
+    "48": {
       "content": "</s>",
       "lstrip": false,
       "normalized": false,
@@ -39,7 +39,6 @@
   "eos_token": "</s>",
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "[PAD]",
-  "processor_class": "Wav2Vec2ProcessorWithLM",
   "replace_word_delimiter_char": " ",
   "target_lang": null,
   "tokenizer_class": "Wav2Vec2CTCTokenizer",

vocab.json

@@ -1,6 +1,6 @@
 {
-  "[PAD]": 62,
-  "[UNK]": 61,
+  "[PAD]": 46,
+  "[UNK]": 45,
   "|": 0,
   "أ": 1,
   "ؤ": 2,
@@ -26,40 +26,24 @@
   "غ": 22,
   "ف": 23,
   "ق": 24,
-  "ك": 25,
-  "ل": 26,
-  "م": 27,
-  "ن": 28,
-  "ه": 29,
-  "و": 30,
-  "ي": 31,
-  "ٹ": 32,
-  "پ": 33,
-  "چ": 34,
-  "ڈ": 35,
-  "ڑ": 36,
-  "ژ": 37,
-  "ک": 38,
-  "گ": 39,
-  "ں": 40,
-  "ھ": 41,
-  "ہ": 42,
-  "ۂ": 43,
-  "ۃ": 44,
-  "ی": 45,
-  "ے": 46,
-  "ۓ": 47,
-  "ﭨ": 48,
-  "ﮭ": 49,
-  "ﮯ": 50,
-  "ﯾ": 51,
-  "ﷲ": 52,
-  "ﷺ": 53,
-  "ﺅ": 54,
-  "ﺗ": 55,
-  "ﺘ": 56,
-  "ﺩ": 57,
-  "ﺲ": 58,
-  "ﻧ": 59,
-  "ﻮ": 60
+  "ل": 25,
+  "م": 26,
+  "ن": 27,
+  "و": 28,
+  "ٹ": 29,
+  "پ": 30,
+  "چ": 31,
+  "ڈ": 32,
+  "ڑ": 33,
+  "ژ": 34,
+  "ک": 35,
+  "گ": 36,
+  "ں": 37,
+  "ھ": 38,
+  "ہ": 39,
+  "ۂ": 40,
+  "ۃ": 41,
+  "ی": 42,
+  "ے": 43,
+  "ۓ": 44
 }