Update app.py

app.py

@@ -12,7 +12,10 @@ from dotenv import load_dotenv
 
 genai.configure(api_key=os.getenv("GOOGLE_API_KEY"))
 
-
+def transcribe_audio(audio_file):
+    model = whisper.load_model("large")
+    result = model.transcribe(audio_file, language="en", fp16=False)
+    return result["text"]
 def get_pdf_text(pdf_docs):
     text=""
     for pdf in pdf_docs:
@@ -78,20 +81,22 @@ def main():
     st.set_page_config("Chat PDF")
     st.header("QnA with Multiple PDF files💁")
 
-    user_question = st.text_input("Ask a Question from the PDF Files")
-
-    if user_question:
-        user_input(user_question)
-
     with st.sidebar:
         st.title("Menu:")
-        pdf_docs = st.file_uploader("Upload your PDF Files and Click on the Submit & Process Button", accept_multiple_files=True)
+        audio_query = st.file_uploader("Upload your Audio Query", type=['mp3', 'wav'])
+        pdf_docs = st.file_uploader("Upload your PDF Files", accept_multiple_files=True)
         if st.button("Submit & Process"):
-            with st.spinner("Processing..."):
-                raw_text = get_pdf_text(pdf_docs)
-                text_chunks = get_text_chunks(raw_text)
-                get_vector_store(text_chunks)
-                st.success("Done")
+            with st.spinner("Processing Audio and PDFs..."):
+                if audio_query is not None:
+                    user_question = transcribe_audio(audio_query)
+                    raw_text = get_pdf_text(pdf_docs)
+                    text_chunks = get_text_chunks(raw_text)
+                    get_vector_store(text_chunks)
+                    response = user_input(user_question)
+                    st.success("Done")
+                    st.write("Reply: ", response)
+                else:
+                    st.error("Please upload an audio file for the query.")