Update app.py

app.py

@@ -3,6 +3,46 @@ import os
 from moviepy.editor import *
 import gradio as gr
 import re
+import nltk
+from nltk.stem import WordNetLemmatizer
+from nltk.tokenize import word_tokenize
+from nltk.corpus import wordnet
+
+nltk.download('punkt')
+nltk.download('wordnet')
+nltk.download('averaged_perceptron_tagger')
+
+def get_wordnet_pos(tag):
+    if tag.startswith('J'):
+        return wordnet.ADJ
+    elif tag.startswith('V'):
+        return wordnet.VERB
+    elif tag.startswith('N'):
+        return wordnet.NOUN
+    elif tag.startswith('R'):
+        return wordnet.ADV
+    else:
+        return wordnet.NOUN  # Default to noun if the POS tag is not found
+
+def get_lemma(word):
+    lemmatizer = WordNetLemmatizer()
+
+    tokens = word_tokenize(word)
+    tagged_words = nltk.pos_tag(tokens)
+    lemmas = []
+    for tagged_word in tagged_words:
+        word = tagged_word[0]
+        pos = tagged_word[1]
+        wordnet_pos = get_wordnet_pos(pos)
+        lemma = lemmatizer.lemmatize(word, pos=wordnet_pos)
+        lemmas.append(lemma)
+    return ' '.join(lemmas)
+
+def apply_lemma_to_string(sentence):
+    words = word_tokenize(sentence)
+    lemmas = [get_lemma(word) for word in words]
+    return ' '.join(lemmas)
+    
 
 def parse_string(string, dataset):
     parsed_list = []
@@ -59,6 +99,7 @@ print(VideosNames)
 def texttoSign(text):
       text=text+" "
       text=text.lower()
+      text=apply_lemma_to_string(text)
       text=re.sub('[^a-z]+', ' ', text)
       framescount=0
       listofwords=parse_string(text,VideosNames)