Add requirements.txt

app.py

@@ -26,7 +26,7 @@ nlp.vocab.add_flag(lambda s: s.lower() in spacy.lang.en.stop_words.STOP_WORDS, s
 
 def preprocess_text(text):
     """Preprocess the input text using SpaCy and return word indices."""
-    doc = nlp(text)
+    doc = nlp.pipe(text, n_process=1)
     word_seq = []
     for token in doc:
         if token.pos_ != "PUNCT":
@@ -38,17 +38,17 @@ def preprocess_text(text):
 def classify_question(text):
     # Preprocess the text
     seq = preprocess_text(text)
-    padded_seq = tf.keras.preprocessing.sequence.pad_sequences([seq], maxlen=50)  # Adjust maxlen if needed
-
+    padded_seq = tf.keras.preprocessing.sequence.pad_sequences([seq], maxlen=55)  # Adjust maxlen if needed
+    BATCH_SIZE = 512
     # Get predictions from each model
-    pred1 = 0.15 * np.squeeze(model_1.predict(padded_seq, batch_size=1, verbose=0))
-    pred2 = 0.35 * np.squeeze(model_2.predict(padded_seq, batch_size=1, verbose=0))
-    pred3 = 0.15 * np.squeeze(model_3.predict(padded_seq, batch_size=1, verbose=0))
-    pred4 = 0.35 * np.squeeze(model_4.predict(padded_seq, batch_size=1, verbose=0))
+    pred1 = 0.15 * np.squeeze(model_1.predict(padded_seq, batch_size=BATCH_SIZE, verbose=2))
+    pred2 = 0.35 * np.squeeze(model_2.predict(padded_seq, batch_size=BATCH_SIZE, verbose=2))
+    pred3 = 0.15 * np.squeeze(model_3.predict(padded_seq, batch_size=BATCH_SIZE, verbose=2))
+    pred4 = 0.35 * np.squeeze(model_4.predict(padded_seq, batch_size=BATCH_SIZE, verbose=2))
 
     # Combine predictions
     avg_pred = pred1 + pred2 + pred3 + pred4
-    label = "Insincere" if avg_pred > 0.5 else "Sincere"
+    label = "Insincere" if avg_pred > 0.35 else "Sincere"
 
     # Create a list of probabilities for each model
     probs = {

requirements.txt

@@ -0,0 +1,6 @@
+tensorflow
+gradio
+spacy
+tqdm
+numpy
+pandas