Update src/streamlit_app.py

src/streamlit_app.py

@@ -1,28 +1,29 @@
 import streamlit as st
 from transformers import pipeline
-import whisper
 from gtts import gTTS
 import os
 
-# Load Whisper model for speech-to-text
-@st.cache_resource
+# Load Whisper model (tiny for lower memory use)
+@st.cache_data(show_spinner="Loading Whisper model...")
 def load_whisper():
-    return whisper.load_model("base")
+    import whisper
+    return whisper.load_model("tiny")
 
 asr_model = load_whisper()
 
-# Load a small instruction-tuned model (for Hugging Face free GPU)
-@st.cache_resource
+# Load a small instruction-tuned model for child-safe answers
+@st.cache_resource(show_spinner="Loading language model...")
 def load_llm():
-    return pipeline("text-generation", 
-                    model="tiiuae/falcon-7b-instruct", 
+    return pipeline("text-generation",
+                    model="tiiuae/falcon-7b-instruct",
                     tokenizer="tiiuae/falcon-7b-instruct",
                     max_new_tokens=100,
                     do_sample=True,
                     temperature=0.7)
+
 llm = load_llm()
 
-# Convert text to speech using gTTS
+# Convert AI response to speech
 def speak(text, filename="response.mp3"):
     tts = gTTS(text)
     tts.save(filename)
@@ -35,15 +36,19 @@ def speak(text, filename="response.mp3"):
 st.set_page_config(page_title="AI Learning Buddy", page_icon="🧸")
 st.title("🧸 AI Learning Buddy for Kids (4–7)")
 
-input_type = st.radio("Choose how to ask your question:", ["Type", "Speak"])
+st.markdown("Ask a question by typing or uploading your voice.")
+
+input_type = st.radio("Choose input method:", ["Text", "Voice"])
+
+user_input = ""
 
-if input_type == "Type":
-    user_input = st.text_input("Ask something fun or educational:")
+if input_type == "Text":
+    user_input = st.text_input("Type your question here:")
 else:
-    audio = st.file_uploader("Upload a voice file (wav/mp3)", type=["wav", "mp3"])
-    if audio:
+    audio_file = st.file_uploader("Upload a voice file (wav/mp3)", type=["wav", "mp3"])
+    if audio_file:
         with open("temp_audio.wav", "wb") as f:
-            f.write(audio.read())
+            f.write(audio_file.read())
         result = asr_model.transcribe("temp_audio.wav")
         user_input = result["text"]
         st.success(f"You said: {user_input}")
@@ -54,4 +59,4 @@ if st.button("Ask the Buddy") and user_input:
     result = llm(prompt)[0]["generated_text"]
     answer = result.split("Answer:")[-1].strip()
     st.markdown(f"**AI Buddy says:** {answer}")
-    speak(answer)
+    speak(answer)