Update app.py

app.py

@@ -3,7 +3,9 @@ import toml
 from omegaconf import OmegaConf
 from query import VectaraQuery
 import os
-from transformers import pipeline, AutoModelForCausalLM, AutoTokenizer
+from transformers import pipeline
+import scipy
+import numpy as np
 
 import streamlit as st
 from PIL import Image
@@ -105,17 +107,16 @@ def launch_bot():
     # If assistant has most recently reaponded create audio of response 
         if st.session_state.messages[-1]["role"] == "assistant":
         #text-to-speech
-            text_inputs = response
-            pipe = pipeline(model="suno/bark-small")
-            output = pipe()
+            synthesiser = pipeline("text-to-speech", "suno/bark-small")
 
-            audio = output[response]
-            sampling_rate = output["sampling_rate"]
+            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
-            audio_file = audio
+            audio_file = open('bark_out.wav', 'rb')
             audio_bytes = audio_file.read()
 
-            st.audio(audio_bytes, format='audio/ogg')
+            st.audio(audio_bytes, format='audio/wav')
 
             sample_rate = 44100  # 44100 samples per second
             seconds = 2  # Note duration of 2 seconds