Update README.md

README.md

@@ -112,7 +112,7 @@ model.to("cuda")
 
 #Note: Not ignoring "'"  on this one 
 #Note: Not ignoring "'"  on this one 
-chars_to_ignore_regex = '[\\,\\?\\.\\!\\-\\;\\:\\"\\“\\%\\‘\\”\\�\\#\\>\\<\\_\\’\\[\\]\\{\\}]'
+chars_to_ignore_regex = '[\\\\,\\\\?\\\\.\\\\!\\\\-\\\\;\\\\:\\\\"\\\\“\\\\%\\\\‘\\\\”\\\\�\\\\#\\\\>\\\\<\\\\_\\\\’\\\\[\\\\]\\\\{\\\\}]'
 
 #resampler = torchaudio.transforms.Resample(48_000, 16_000)
 #using custom load and transformer for audio  -> see audio_resampler
@@ -147,13 +147,13 @@ def audio_resampler(batch, new_sample_rate = 16000):
 def remove_special_characters(batch):
 
     ##this one comes from subtitles if additional timestamps not processed  -> 00:01:01   00:01:01,33
-    batch["sentence"] = re.sub('\\b\\d{2}:\\d{2}:\\d{2}(,+\\d{2})?\\b', ' ', batch["sentence"])
+    batch["sentence"] = re.sub('\\\\b\\\\d{2}:\\\\d{2}:\\\\d{2}(,+\\\\d{2})?\\\\b', ' ', batch["sentence"])
 
     ##remove all caps in text [AÇIKLAMA] etc, do it before..
-    batch["sentence"] = re.sub('\\[(\\b[A-Z]+\\])', '', batch["sentence"]) 
+    batch["sentence"] = re.sub('\\\\[(\\\\b[A-Z]+\\\\])', '', batch["sentence"]) 
 
     ##replace three dots (that are inside string with single)
-    batch["sentence"] = re.sub("([a-zA-Z]+)\\.\\.\\.", r"\\1.", batch["sentence"])
+    batch["sentence"] = re.sub("([a-zA-Z]+)\\\\.\\\\.\\\\.", r"\\\\1.", batch["sentence"])
 
     #standart ignore list
     batch["sentence"] = re.sub(chars_to_ignore_regex, '', batch["sentence"]).lower() + " "
@@ -188,6 +188,7 @@ result = test_dataset.map(evaluate, batched=True, batch_size=2)
 print("WER: {:2f}".format(100 * wer.compute(predictions=result["pred_strings"], references=result["sentence"])))
 
 ```
-**Test Result**: TBD %  
+**Test Result**: 50.41 %  
 ## Training
-The Common Voice `train` and `validation` datasets were used for training. Additional 5 Turkish movies with subtitles also used 
+The Common Voice `train` and `validation` datasets were used for training. Additional 5 Turkish movies with subtitles also used.
+Training still continues...