Update src/streamlit_app.py

src/streamlit_app.py

@@ -1,40 +1,57 @@
-import altair as alt
-import numpy as np
-import pandas as pd
 import streamlit as st
-
-"""
-# Welcome to Streamlit!
-
-Edit `/streamlit_app.py` to customize this app to your heart's desire :heart:.
-If you have any questions, checkout our [documentation](https://docs.streamlit.io) and [community
-forums](https://discuss.streamlit.io).
-
-In the meantime, below is an example of what you can do with just a few lines of code:
-"""
-
-num_points = st.slider("Number of points in spiral", 1, 10000, 1100)
-num_turns = st.slider("Number of turns in spiral", 1, 300, 31)
-
-indices = np.linspace(0, 1, num_points)
-theta = 2 * np.pi * num_turns * indices
-radius = indices
-
-x = radius * np.cos(theta)
-y = radius * np.sin(theta)
-
-df = pd.DataFrame({
-    "x": x,
-    "y": y,
-    "idx": indices,
-    "rand": np.random.randn(num_points),
-})
-
-st.altair_chart(alt.Chart(df, height=700, width=700)
-    .mark_point(filled=True)
-    .encode(
-        x=alt.X("x", axis=None),
-        y=alt.Y("y", axis=None),
-        color=alt.Color("idx", legend=None, scale=alt.Scale()),
-        size=alt.Size("rand", legend=None, scale=alt.Scale(range=[1, 150])),
-    ))
+from transformers import pipeline
+import whisper
+from gtts import gTTS
+import os
+
+# Load Whisper model for speech-to-text
+@st.cache_resource
+def load_whisper():
+    return whisper.load_model("base")
+
+asr_model = load_whisper()
+
+# Load a small instruction-tuned model (for Hugging Face free GPU)
+@st.cache_resource
+def load_llm():
+    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
+def speak(text, filename="response.mp3"):
+    tts = gTTS(text)
+    tts.save(filename)
+    audio_file = open(filename, "rb")
+    audio_bytes = audio_file.read()
+    st.audio(audio_bytes, format="audio/mp3")
+    os.remove(filename)
+
+# UI
+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"])
+
+if input_type == "Type":
+    user_input = st.text_input("Ask something fun or educational:")
+else:
+    audio = st.file_uploader("Upload a voice file (wav/mp3)", type=["wav", "mp3"])
+    if audio:
+        with open("temp_audio.wav", "wb") as f:
+            f.write(audio.read())
+        result = asr_model.transcribe("temp_audio.wav")
+        user_input = result["text"]
+        st.success(f"You said: {user_input}")
+        os.remove("temp_audio.wav")
+
+if st.button("Ask the Buddy") and user_input:
+    prompt = f"You are a fun and friendly teacher for a 5-year-old. Question: {user_input} Answer:"
+    result = llm(prompt)[0]["generated_text"]
+    answer = result.split("Answer:")[-1].strip()
+    st.markdown(f"**AI Buddy says:** {answer}")
+    speak(answer)