Update README.md

README.md

@@ -36,15 +36,12 @@ import torchaudio
 from datasets import load_dataset
 from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
 import pandas as pd
-
 # Evaluation notebook contains the procedure to download the data
-df = pd.read_csv("/content/te/test.tsv", sep="\\\\t")
+df = pd.read_csv("/content/te/test.tsv", sep="\t")
 df["path"] = "/content/te/clips/" + df["path"]
 test_dataset = Dataset.from_pandas(df)
-
 processor = Wav2Vec2Processor.from_pretrained("anuragshas/wav2vec2-large-xlsr-53-telugu")
 model = Wav2Vec2ForCTC.from_pretrained("anuragshas/wav2vec2-large-xlsr-53-telugu") 
-
 resampler = torchaudio.transforms.Resample(48_000, 16_000)
 # Preprocessing the datasets.
 # We need to read the aduio files as arrays
@@ -52,7 +49,6 @@ def speech_file_to_array_fn(batch):
     speech_array, sampling_rate = torchaudio.load(batch["path"])
     batch["speech"] = resampler(speech_array).squeeze().numpy()
     return batch
-    
 test_dataset = test_dataset.map(speech_file_to_array_fn)
 inputs = processor(test_dataset["speech"][:2], sampling_rate=16_000, return_tensors="pt", padding=True)
 with torch.no_grad():
@@ -70,25 +66,19 @@ from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
 import re
 from sklearn.model_selection import train_test_split
 import pandas as pd
-
 # Evaluation notebook contains the procedure to download the data
-df = pd.read_csv("/content/te/test.tsv", sep="\\\\t")
+df = pd.read_csv("/content/te/test.tsv", sep="\t")
 df["path"] = "/content/te/clips/" + df["path"]
 test_dataset = Dataset.from_pandas(df)
 wer = load_metric("wer")
-
 processor = Wav2Vec2Processor.from_pretrained("anuragshas/wav2vec2-large-xlsr-53-telugu")
 model = Wav2Vec2ForCTC.from_pretrained("anuragshas/wav2vec2-large-xlsr-53-telugu") 
 model.to("cuda")
-
-chars_to_ignore_regex = '[\\,\\?\\.\\!\\-\\_\\;\\:\\"\\“\\%\\‘\\”\\।\\’\'\\&]'
+chars_to_ignore_regex = '[\,\?\.\!\-\_\;\:\"\“\%\‘\”\।\’\'\&]'
 resampler = torchaudio.transforms.Resample(48_000, 16_000)
-
 def normalizer(text):
     # Use your custom normalizer
-    text = text.replace("\\\\\\
-","\\
-")
+    text = text.replace("\\n","\n")
     text = ' '.join(text.split())
     text = re.sub(r'''([a-z]+)''','',text,flags=re.IGNORECASE)
     text = re.sub(r'''%'''," శాతం ", text)
@@ -96,7 +86,6 @@ def normalizer(text):
     text = re.sub("ై","ై", text)
     text = text.strip()
     return text
-
 def speech_file_to_array_fn(batch):
     batch["sentence"] = normalizer(batch["sentence"])
     batch["sentence"] = re.sub(chars_to_ignore_regex, '', batch["sentence"]).lower()+ " "