Create app.py

app.py

@@ -0,0 +1,56 @@
+import gradio as gr
+import numpy as np
+import string
+import nltk
+from nltk.tokenize import word_tokenize
+from nltk.corpus import stopwords
+from nltk.stem import WordNetLemmatizer
+import tensorflow as tf
+from tensorflow import keras
+from keras import layers
+from tensorflow.keras.preprocessing.text import Tokenizer
+from tensorflow.keras.preprocessing.sequence import pad_sequences
+import joblib
+
+nltk.download('stopwords')
+nltk.download('omw-1.4')
+nltk.download('wordnet')
+nltk.download('punkt')
+
+tokenizer, model = joblib.load("lstm_model.pkl")
+
+def preprocess(text, tokenizer):
+    lemmatizer = WordNetLemmatizer()
+    vocab = set()
+    stop_words = set(stopwords.words('english'))
+    tokens = word_tokenize(text)
+    tokens = [word for word in tokens if word.lower() not in stop_words and word not in string.punctuation]
+    tokens = [lemmatizer.lemmatize(word.lower()) for word in tokens]
+    vocab.update(tokens)
+    preprocessed_text = ' '.join(tokens)
+    X = tokenizer.texts_to_sequences(preprocessed_text)
+    max_len = max(len(y) for y in X)
+    X = pad_sequences(X, maxlen=max_len)
+    return X
+
+def predict(text):
+    X = preprocess(text, tokenizer)
+    pred = model.predict(X)
+    probabilities = np.mean(pred, axis=0)
+    final_class = np.argmax(probabilities)
+    if final_class == 0:
+        prediction = "The string is classified as hate speech."
+    else:
+        prediction = "The string is classified as normal speech."
+    return {"prediction": prediction, "probability": probabilities.tolist()}
+
+iface = gr.Interface(
+    fn=predict,
+    inputs=gr.inputs.Textbox(lines=2, placeholder="Enter text here..."),
+    outputs=[gr.outputs.Textbox(label="Prediction"), gr.outputs.Textbox(label="Probabilities")],
+    title="Hate Speech Classifier",
+    description="A classifier to detect hate speech in a given text.",
+)
+
+if __name__ == "__main__":
+    iface.launch()