File size: 1,712 Bytes
791a72e |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 |
import os
import pyaudio
import streamlit as st
from langchain.memory import ConversationBufferMemory
from utils import record_audio_chunk, transcribe_audio, get_response_llm, play_text_to_speech, load_whisper
chunk_file = 'temp_audio_chunk.wav'
model = load_whisper()
def main():
st.markdown('<h1 style="color: darkblue;">AI Voice Assistant️</h1>', unsafe_allow_html=True)
memory = ConversationBufferMemory(memory_key="chat_history")
if st.button("Start Recording"):
while True:
# Audio Stream Initialization
audio = pyaudio.PyAudio()
stream = audio.open(format=pyaudio.paInt16, channels=1, rate=16000, input=True, frames_per_buffer=1024)
# Record and save audio chunk
record_audio_chunk(audio, stream)
text = transcribe_audio(model, chunk_file)
if text is not None:
st.markdown(
f'<div style="background-color: #f0f0f0; padding: 10px; border-radius: 5px;">Customer 👤: {text}</div>',
unsafe_allow_html=True)
os.remove(chunk_file)
response_llm = get_response_llm(user_question=text, memory=memory)
st.markdown(
f'<div style="background-color: #f0f0f0; padding: 10px; border-radius: 5px;">AI Assistant 🤖: {response_llm}</div>',
unsafe_allow_html=True)
play_text_to_speech(text=response_llm)
else:
stream.stop_stream()
stream.close()
audio.terminate()
break # Exit the while loop
print("End Conversation")
if __name__ == "__main__":
main() |