Update app.py

app.py

@@ -1,6 +1,5 @@
 import streamlit as st
 from gradio_client import Client
-from st_audiorec import st_audiorec
 from gtts import gTTS
 import os
 
@@ -27,11 +26,15 @@ whisper_client = Client("https://sanchit-gandhi-whisper-large-v2.hf.space/")
 
 def transcribe(wav_path):
     return whisper_client.predict(
-        wav_path,    # str (filepath or URL to file) in 'inputs' Audio component
-        "transcribe",    # str in 'Task' Radio component
+        wav_path,
+        "transcribe",
         api_name="/predict"
     )
 
+# Initialize session state
+if "messages" not in st.session_state:
+    st.session_state.messages = []
+
 # Prediction function
 def predict(message, system_prompt='Your name is OpenGPT. You are developed by Achyuth. You need to mostly focus on giving information about future agriculture and advanced farming. Empower yourself farming future with cutting-edge technology and sustainable practices. You need to cultivate a greener and more productive. Your developer is studying in The Hyderabad Public School Kadapa.', temperature=0.7, max_new_tokens=4096, Topp=0.5, Repetitionpenalty=1.2):
     with st.status("Starting client"):
@@ -40,13 +43,13 @@ def predict(message, system_prompt='Your name is OpenGPT. You are developed by A
     with st.status("Requesting AgriTure v1"):
         st.write("Requesting API")
         response = client.predict(
-            message,    # str in 'Message' Textbox component
-            system_prompt,    # str in 'Optional system prompt' Textbox component
-            max_new_tokens,    # int | float (numeric value between 0 and 4096)
-            temperature,    # int | float (numeric value between 0.0 and 1.0)
+            message,
+            system_prompt,
+            max_new_tokens,
+            temperature,
             Topp,
             500,
-            Repetitionpenalty,    # int | float (numeric value between 1.0 and 2.0)
+            Repetitionpenalty,
             api_name="/chat"
         )
         st.write("Done")
@@ -54,22 +57,14 @@ def predict(message, system_prompt='Your name is OpenGPT. You are developed by A
 
 # Function to convert text to speech
 def text_to_speech(text, language='en', filename='output.mp3'):
-    # Create a gTTS object
     tts = gTTS(text=text, lang=language, slow=False)
-
-    # Save the audio file
     tts.save(filename)
-
-    # Play the audio file
-    os.system(f'start {filename}')  # This works on Windows. For other OS, you might need a different command.
+    os.system(f'start {filename}')
 
 # Streamlit UI
 st.title(TITLE)
 st.write(DESCRIPTION)
 
-if "messages" not in st.session_state:
-    st.session_state.messages = []
-
 # Display chat messages from history on app rerun
 for message in st.session_state.messages:
     with st.chat_message(message["role"], avatar=("🧑‍💻" if message["role"] == 'human' else '🦙')):
@@ -80,11 +75,9 @@ wav_audio_data = st_audiorec()
 
 if wav_audio_data is not None:
     with st.status("Transcribing audio..."):
-        # save audio
         with open("audio.wav", "wb") as f:
             f.write(wav_audio_data)
         prompt = transcribe("audio.wav")
-
         st.write("Transcribed Given Audio ✔")
 
     st.chat_message("human", avatar="🧑‍💻").markdown(prompt)
@@ -95,26 +88,21 @@ if wav_audio_data is not None:
 
     with st.chat_message("assistant", avatar='🦙'):
         st.markdown(response)
-    # Add assistant response to chat history
     st.session_state.messages.append({"role": "assistant", "content": response})
 
     # Convert response to audio
-    text_to_speech(response)  # Call text_to_speech after getting the response
+    text_to_speech(response)
 
 # React to user input
 if prompt := textinput:
-    # Display user message in chat message container
     st.chat_message("human", avatar="💬: ").markdown(prompt)
-    # Add user message to chat history
     st.session_state.messages.append({"role": "human", "content": prompt})
 
     response = predict(message=prompt)
-    
-    # Display assistant response in chat message container
+
     with st.chat_message("assistant", avatar='🦙'):
         st.markdown(response)
-    # Add assistant response to chat history
     st.session_state.messages.append({"role": "assistant", "content": response})
-    
+
     # Convert response to audio
-    text_to_speech(response)  # Call text_to_speech after getting the response
+    text_to_speech(response)