Update app.py

app.py

@@ -7,6 +7,7 @@ import torch
 import faiss
 import numpy as np
 from gtts import gTTS
+from pydub import AudioSegment
 
 # Function to convert audio file to text
 def audio_to_text(audio_file):
@@ -21,6 +22,13 @@ def audio_to_text(audio_file):
     except sr.RequestError:
         return "Sorry, there was a problem with the request"
 
+# Function to convert audio to WAV format
+def convert_to_wav(audio_file_path):
+    audio = AudioSegment.from_file(audio_file_path)
+    wav_path = "temp_audio.wav"
+    audio.export(wav_path, format="wav")
+    return wav_path
+
 # Function to extract text from a PDF file
 def extract_text_from_pdf(pdf_file):
     text = ""
@@ -52,7 +60,7 @@ dimension = 768  # Size of BERT embeddings
 index = faiss.IndexFlatL2(dimension)
 
 # Folder path containing PDFs
-pdf_folder_path = "pdfsforRAG"
+pdf_folder_path = "pdfs"
 
 # Read all PDF files from the specified folder
 pdf_paths = [os.path.join(pdf_folder_path, f) for f in os.listdir(pdf_folder_path) if f.endswith('.pdf')]
@@ -76,11 +84,14 @@ if audio_file:
     st.write("Processing...")
 
     # Save the uploaded audio file
-    with open("temp_audio.wav", "wb") as f:
+    with open("temp_audio.mp3", "wb") as f:
         f.write(audio_file.getbuffer())
 
+    # Convert audio to WAV format if needed
+    wav_path = convert_to_wav("temp_audio.mp3")
+
     # Convert audio to text
-    text = audio_to_text("temp_audio.wav")
+    text = audio_to_text(wav_path)
     st.write("Voice command:", text)
 
     # Find relevant advice