import re
text = "This is a sample text. It contains multiple sentences!"
tokens = re.findall(r'\w+', text.lower())

stopwords = set(['a', 'the', 'is', 'and', 'of'])
filtered_tokens = [word for word in tokens if word not in stopwords]

from nltk.stem import PorterStemmer
stemmer = PorterStemmer()
stems = [stemmer.stem(word) for word in filtered_tokens]

def create_ngrams(tokens, n=2):
    return [' '.join(tokens[i:i+n]) for i in range(len(tokens)-n+1)]

vocab = {word: idx for idx, word in enumerate(set(stems))}