Create app.py

app.py

@@ -0,0 +1,45 @@
+import gradio as gr
+from transformers import pipeline
+import tensorflow as tf
+import pandas as pd
+from tensorflow.keras.layers import TextVectorization
+
+# Load your data
+new_data = pd.read_csv('data_train.csv')  # Make sure to adjust the path if necessary
+
+x = new_data['comment_text']
+y = new_data[new_data.columns[2:]].values
+
+max_features = 100000
+vectorizer = TextVectorization(max_tokens=max_features,
+                               output_sequence_length=1500,
+                               output_mode='int')
+vectorizer.get_vocabulary()
+vectorizer.adapt(x.values)
+
+model = tf.keras.models.load_model('finalprojecttoxic.h5')
+
+translator_hindi = pipeline("translation", model="Helsinki-NLP/opus-mt-hi-en", tokenizer="Helsinki-NLP/opus-mt-hi-en")
+
+def translate_hindi(from_text):
+    result2 = translator_hindi(from_text)
+    return result2[0]['translation_text']
+
+def score_comment(comment):
+    vectorized_comment = vectorizer([comment])
+    results = model.predict(vectorized_comment)
+    
+    text = ''
+    for idx, col in enumerate(new_data.columns[2:]):
+        text += '{}: {}\n'.format(col, results[0][idx] > 0.5)
+        
+    return text
+
+def combined_models(input):
+    translated_text = translate_hindi(input)
+    toxic_score = score_comment(input)
+    
+    return translated_text, toxic_score
+
+interface = gr.Interface(fn=combined_models, inputs="text", outputs=["text", "text"], title="Toxic Comment Analyzer")
+interface.launch(share=True)