Update README.md

README.md

@@ -57,8 +57,8 @@ def load_dataset_sundanese():
     
     dfs = []
     
-    dfs.append(pd.read_csv(filenames[0], sep='\\t\\t', names=["path", "sentence"]))
-    dfs.append(pd.read_csv(filenames[1], sep='\\t\\t', names=["path", "sentence"]))
+    dfs.append(pd.read_csv(filenames[0], sep='\\\\t\\\\t', names=["path", "sentence"]))
+    dfs.append(pd.read_csv(filenames[1], sep='\\\\t\\\\t', names=["path", "sentence"]))
     
     for i, dir in enumerate(data_dirs):
         dfs[i]["path"] = dfs[i].apply(lambda row: str(data_dirs[i]) + "/" + row + ".wav", axis=1)
@@ -124,8 +124,8 @@ def load_dataset_sundanese():
     
     dfs = []
     
-    dfs.append(pd.read_csv(filenames[0], sep='\\t\\t', names=["path", "sentence"]))
-    dfs.append(pd.read_csv(filenames[1], sep='\\t\\t', names=["path", "sentence"]))
+    dfs.append(pd.read_csv(filenames[0], sep='\\\\t\\\\t', names=["path", "sentence"]))
+    dfs.append(pd.read_csv(filenames[1], sep='\\\\t\\\\t', names=["path", "sentence"]))
     
     for i, dir in enumerate(data_dirs):
         dfs[i]["path"] = dfs[i].apply(lambda row: str(data_dirs[i]) + "/" + row + ".wav", axis=1)
@@ -145,8 +145,7 @@ processor = Wav2Vec2Processor.from_pretrained("cahya/wav2vec2-large-xlsr-sundane
 model = Wav2Vec2ForCTC.from_pretrained("cahya/wav2vec2-large-xlsr-sundanese") 
 model.to("cuda")
 
-chars_to_ignore_regex = '[\\\\\\\\,\\\\\\\\?\\\\\\\\.\\\\\\\\!\\\\\\\\-\\\\\\\\;\\\\\\\\:\\\\\\\\"\\\\\\\\“\\\\\\\\%\\\\\\\\‘\\\\\\\\'\\\\\\\\”]'
-
+chars_to_ignore_regex = '[\,\?\.\!\-\;\:\"\“\%\‘\'\”_\�]'
 resampler = torchaudio.transforms.Resample(48_000, 16_000)
 
 # Preprocessing the datasets.