URDU-ASR-LM

.gitattributes

@@ -29,3 +29,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zstandard filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+language_model/5gram_correct.arpa filter=lfs diff=lfs merge=lfs -text

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 53,
+  "<s>": 52
+}

alphabet.json

@@ -0,0 +1 @@
+{"labels": ["\u0631", "\u06a9", "\u062b", "\u0621", "\u0639", "\u0622", "\u06cc", "\u0642", "\u0641", "\u0679", "\u0630", "\u063a", "\u06d3", "\u06af", "\u0691", "\u0638", "\u0688", "\u0649", "\u06d2", "\u062a", "\u06c3", "\u0647", "\u064a", "\u06ba", "\u06be", "\u0628", "\u0636", "\u062f", "\u0633", "\u06c2", "\u067e", "\u062e", "\u0623", "\u0632", "\u06c1", "\u0624", "\u0646", "\u0645", "\u0626", "\u062d", "\u0686", "\u0644", "\u0634", "\u0635", " ", "\u0637", "\u0627", "\u0698", "\u0648", "\u062c", "\u2047", "", "<s>", "</s>"], "is_bpe": false}

language_model/5gram_correct.arpa

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e43e9614c504ebc5d38bf8e173fb8b1f08f19a0f49ffe32e799b876746fd5fdb
+size 76535773

language_model/attrs.json

@@ -0,0 +1 @@
+{"alpha": 0.5, "beta": 1.5, "unk_score_offset": -10.0, "score_boundary": true}

preprocessor_config.json

@@ -4,6 +4,7 @@
   "feature_size": 1,
   "padding_side": "right",
   "padding_value": 0.0,
+  "processor_class": "Wav2Vec2ProcessorWithLM",
   "return_attention_mask": true,
   "sampling_rate": 16000
 }

special_tokens_map.json

@@ -1,4 +1,20 @@
 {
+  "additional_special_tokens": [
+    {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
   "bos_token": "<s>",
   "eos_token": "</s>",
   "pad_token": "[PAD]",

tokenizer_config.json

@@ -2,8 +2,11 @@
   "bos_token": "<s>",
   "do_lower_case": false,
   "eos_token": "</s>",
+  "name_or_path": "Talha/URDU-ASR",
   "pad_token": "[PAD]",
+  "processor_class": "Wav2Vec2ProcessorWithLM",
   "replace_word_delimiter_char": " ",
+  "special_tokens_map_file": "/home/talha/.cache/huggingface/transformers/4fe513b575fc984e7d81818eca5e05a17aaa2c7ad8887d98c7fe479944f81219.fea372b8528a479b7415f13ca4e27a2f5f3782cbb3f15b4d19bb3cbe734e8137",
   "tokenizer_class": "Wav2Vec2CTCTokenizer",
   "unk_token": "[UNK]",
   "word_delimiter_token": "|"