Update app.py

app.py

@@ -210,6 +210,9 @@ def load_default():
 
 def transfer_learning_forecasting():
     st.title("Transfer Learning Forecasting")
+    st.markdown("""
+    Instant time series forecasting and visualization by using various pre-trained deep neural network-based model trained on M4 data.
+    """)
 
     nhits_models, timesnet_models, lstm_models, tft_models = load_all_models()
     
@@ -301,7 +304,11 @@ def transfer_learning_forecasting():
 
 def dynamic_forecasting():
     st.title("Dynamic Forecasting")
-    st.subheader("Speed depends on CPU/GPU availability", divider="gray")
+    st.markdown("""
+    Train time series forecasting model from scratch and provide forecasts/visualization by using various deep neural network-based model trained on user data.
+    
+    Forecasting speed depends on CPU/GPU availabilty.
+    """)
     
     with st.sidebar.expander("Upload and Configure Dataset", expanded=True):
         uploaded_file = st.file_uploader("Upload your time series data (CSV)", type=["csv"])
@@ -347,6 +354,9 @@ def timegpt_fcst():
 
     
     st.title("TimeGPT Forecasting")
+    st.markdown("""
+    Instant time series forecasting and visualization by using the TimeGPT API provided by Nixtla.
+    """)
     with st.sidebar.expander("Upload and Configure Dataset", expanded=True):
         uploaded_file = st.file_uploader("Upload your time series data (CSV)", type=["csv"])
         if uploaded_file:
@@ -405,7 +415,10 @@ def timegpt_anom():
     )
 
     
-    st.title("TimeGPT Forecasting")
+    st.title("TimeGPT Anomaly Detection")
+        st.markdown("""
+    Instant time series anomaly detection and visualization by using the TimeGPT API provided by Nixtla.
+    """)
     with st.sidebar.expander("Upload and Configure Dataset", expanded=True):
         uploaded_file = st.file_uploader("Upload your time series data (CSV)", type=["csv"])
         if uploaded_file: