Update README.md

README.md

@@ -103,7 +103,7 @@ import re
 test = Dataset.from_csv('test.csv')
 
 
-chars_to_ignore_regex = '[\\\\\\\\\\\\\\\\,\\\\\\\\\\\\\\\\?\\\\\\\\\\\\\\\\.\\\\\\\\\\\\\\\\!\\\\\\\\\\\\\\\\-\\\\\\\\\\\\\\\\;\\\\\\\\\\\\\\\\:\\\\\\\\\\\\\\\\"\\\\\\\\\\\\\\\\“\\\\\\\\\\\\\\\\%\\\\\\\\\\\\\\\\‘\\\\\\\\\\\\\\\\”\\\\\\\\\\\\\\\\�\\\\\\\\\\\\\\\\।]'
+chars_to_ignore_regex = '[\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\,\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\?\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\.\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\!\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\-\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\;\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\:\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\"\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\“\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\%\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\‘\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\”\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\�\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\।]'
 
 # Preprocessing the datasets.
 # We need to read the audio files as arrays
@@ -143,9 +143,14 @@ import torch
 import librosa
 import numpy as np
 import re
-from datasets import load_dataset
+from datasets import load_metric, load_dataset, Dataset
+from transformers import Wav2Vec2Processor, Wav2Vec2ForCTC
+
+wer = load_metric("wer")
+processor = Wav2Vec2Processor.from_pretrained('tanmaylaud/wav2vec2-large-xlsr-hindi-marathi')
+model = Wav2Vec2ForCTC.from_pretrained('tanmaylaud/wav2vec2-large-xlsr-hindi-marathi').to("cuda")
 
-chars_to_ignore_regex = '[\\\\\\\\\\\\\\\\,\\\\\\\\\\\\\\\\?\\\\\\\\\\\\\\\\.\\\\\\\\\\\\\\\\!\\\\\\\\\\\\\\\\-\\\\\\\\\\\\\\\\;\\\\\\\\\\\\\\\\:\\\\\\\\\\\\\\\\"\\\\\\\\\\\\\\\\“\\\\\\\\\\\\\\\\%\\\\\\\\\\\\\\\\‘\\\\\\\\\\\\\\\\”\\\\\\\\\\\\\\\\�\\\\\\\\\\\\\\\\।]'
+chars_to_ignore_regex = '[\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\,\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\?\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\.\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\!\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\-\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\;\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\:\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\"\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\“\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\%\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\‘\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\”\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\�\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\।]'
 
 # Preprocessing the datasets.
 # We need to read the audio files as arrays