Added temp file

app.py

@@ -5,6 +5,7 @@ from query import VectaraQuery
 import os
 from transformers import pipeline
 import numpy as np
+import tempfile
 
 import streamlit as st
 from PIL import Image
@@ -28,6 +29,9 @@ As a Natural Farming Fertilizers Assistant, you will assist the user with any fa
 User prompt:
 """
 
+#temporary file system created: used to text-to-speech
+fp = tempfile.TemporaryFile()
+
 def launch_bot():
     def generate_response(question):
         response = vq.submit_query(question)
@@ -106,31 +110,41 @@ def launch_bot():
             audio_result = st.button("Convert to Audio 🔊") 
             if audio_result:
                 with st.chat_message("text-to-speech"):
-                    with st.spinner("Thinking..."):
                 #text-to-speech
-                        print("Calling in Text-to-speech via suno/bark-small")
-                        synthesiser = pipeline("text-to-speech", "suno/bark-small")
-            
-                        speech = synthesiser(response, forward_params={"do_sample": True})
-            
-                        scipy.io.wavfile.write("bark_out.wav", rate=speech["sampling_rate"], data=speech["audio"])
-                    # ST interface for audio
-                        print("Now we try to display the audio file in the app")
-                        audio_file = open('bark_out.wav', 'rb')
-                        audio_bytes = audio_file.read()
+                    print("Calling in Text-to-speech via suno/bark-small")
+                    
+                    synthesiser = pipeline("text-to-speech", "suno/bark-small")
             
-                        audio_convert = st.audio(audio_bytes, format='audio/wav')
-                        st.session_state.messages.append(audio_convert)
-                        
-                #        sample_rate = 44100  # 44100 samples per second
-                #        seconds = 2  # Note duration of 2 seconds
-                #        frequency_la = 440  # Our played note will be 440 Hz
-                # Generate array with seconds*sample_rate steps, ranging between 0 and seconds
-                #        t = np.linspace(0, seconds, seconds * sample_rate, False)
-                # Generate a 440 Hz sine wave
-                #        note_la = np.sin(frequency_la * t * 2 * np.pi)
-            
-                #        st.audio(note_la, sample_rate=sample_rate)
+                    speech = synthesiser(response, forward_params={"do_sample": True})
+
+                    # write to temp file: the scipy wav write bark_out.wav
+                    fp.write(scipy.io.wavfile.write("bark_out.wav", rate=speech["sampling_rate"], data=speech["audio"]))
+                    
+                # ST interface for audio
+                    print("Now we try to display the audio file in the app")
+                    
+                    # Temp file access
+                    fp.seek(0)
+                    audio_file = fp.read('bark_out.wav', 'rb')
+                    
+                    audio_bytes = audio_file.read()
+        
+                    audio_convert = st.audio(audio_bytes, format='audio/wav')
+                    st.session_state.messages.append(audio_convert)
+                    sample_rate = 44100  # 44100 samples per second
+                    seconds = 2  # Note duration of 2 seconds
+                    
+                    frequency_la = 440  # Our played note will be 440 Hz
+                    
+                    # Generate array with seconds*sample_rate steps, ranging between 0 and seconds
+                    t = np.linspace(0, seconds, seconds * sample_rate, False)
+                    
+                    # Generate a 440 Hz sine wave
+                    note_la = np.sin(frequency_la * t * 2 * np.pi)
+                    st.audio(note_la, sample_rate=sample_rate)
+
+                    # Close and delete temp file
+                    fp.close()
                 
 if __name__ == "__main__":
     launch_bot()