Update README.md

README.md

@@ -120,7 +120,8 @@ 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
@@ -151,23 +152,22 @@ def audio_resampler(batch, new_sample_rate = 16000):
 
     return batch
 
-
 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() + " "
-
     
     return batch
+
     
 # Preprocessing the datasets.
 # We need to read the aduio files as arrays