Update README.md

README.md

@@ -23,7 +23,7 @@ model-index:
     metrics:
        - name: Test WER
          type: wer
-         value: 44.51
+         value: 66.45
 ---
 
 # Wav2Vec2-Large-XLSR-53-Moroccan
@@ -90,7 +90,8 @@ processor = Wav2Vec2Processor.from_pretrained("othrif/wav2vec2-large-xlsr-morocc
 model = Wav2Vec2ForCTC.from_pretrained("othrif/wav2vec2-large-xlsr-moroccan")
 model.to("cuda")
 
-chars_to_ignore_regex = '[0\,\?\.\!\-\;\:\"\“\%\‘\”\�\n\@\ـ\؟\*\ \#\'\ \…\\u2003]'
+chars_to_ignore_regex = '[0\\,\\?\\.\\!\\-\\;\\:\\"\\“\\%\\‘\\”\\�\
+\\@\\ـ\\؟\\*\\ \\#\\'\\ \\…\\\\u2003]'
 #resampler = torchaudio.transforms.Resample(48_000, 16_000)
 
 # Preprocessing the datasets.
@@ -100,7 +101,8 @@ def speech_file_to_array_fn(batch):
     batch["text"] = re.sub('[a-zA-z]', '', batch["text"]).lower() + " "
         batch["text"] = re.sub('[ًٌٍَُِ~]', '', batch["text"]).lower() + " "
 
-        # batch["text"] = re.sub('\\n','', batch["text"])
+        # batch["text"] = re.sub('\\\
+','', batch["text"])
         batch["text"] = re.sub("[إأٱآا]", "ا", batch["text"])
         batch["text"] = re.sub("ڸ", "ل", batch["text"])
         noise = re.compile(""" ّ    | # Tashdid
@@ -138,7 +140,7 @@ result = test_dataset.map(evaluate, batched=True, batch_size=8)
 print("WER: {:2f}".format(100 * wer.compute(predictions=result["pred_strings"], references=result["text"])))
 ```
 
-**Test Result**: 44.51
+**Test Result**: 66.45
 
 
 ## Training