Update app.py

app.py

@@ -1,7 +1,6 @@
 import streamlit as st
 from transformers import pipeline
 import torchaudio
-from audio_recorder_streamlit import audio_recorder
 import torch
 from io import BytesIO
 import hashlib
@@ -20,6 +19,17 @@ def process_audio(audio_bytes):
         waveform = resampler(waveform)
     return {"raw": waveform.numpy().squeeze(), "sampling_rate": 16000}
 
+# Custom audio recorder component
+def audio_recorder_component():
+    return st.audio(
+        "microphone",
+        format="audio/wav",
+        start_recording=True,
+        pause_threshold=1.0,
+        sample_rate=16000,
+        key="audio_recorder"
+    )
+
 # App Interface
 st.title("Real-Time Voice Typing")
 st.write("Speak and your words will appear immediately")
@@ -27,10 +37,8 @@ st.write("Speak and your words will appear immediately")
 # Initialize session state
 if 'text_input' not in st.session_state:
     st.session_state.text_input = ""
-if 'current_audio' not in st.session_state:
-    st.session_state.current_audio = None
-if 'is_recording' not in st.session_state:
-    st.session_state.is_recording = False
+if 'last_audio' not in st.session_state:
+    st.session_state.last_audio = None
 
 # Text display
 text_input = st.text_area(
@@ -39,47 +47,30 @@ text_input = st.text_area(
     height=300
 )
 
-# Audio recorder with callback
-def handle_recording(audio_bytes):
-    if audio_bytes:
-        st.session_state.current_audio = audio_bytes
-        process_current_audio()
+# Audio recording
+audio_bytes = audio_recorder_component()
 
-def process_current_audio():
-    if st.session_state.current_audio:
-        try:
-            audio_input = process_audio(st.session_state.current_audio)
-            whisper = load_model()
-            transcribed_text = whisper(audio_input)["text"].strip()
+# Process audio when available
+if audio_bytes and audio_bytes != st.session_state.last_audio:
+    st.session_state.last_audio = audio_bytes
+    try:
+        audio_input = process_audio(audio_bytes)
+        whisper = load_model()
+        transcribed_text = whisper(audio_input)["text"].strip()
+        
+        if transcribed_text:
+            st.session_state.text_input += " " + transcribed_text
+            st.rerun()
             
-            if transcribed_text:
-                st.session_state.text_input += " " + transcribed_text
-                st.session_state.current_audio = None
-                st.rerun()
-                
-        except Exception as e:
-            st.error(f"Error: {str(e)}")
-
-# Audio recorder component
-audio_bytes = audio_recorder(
-    pause_threshold=1.0,  # Faster response
-    text="Click to speak",
-    recording_color="#e8b62c",
-    neutral_color="#6aa36f",
-    callback=handle_recording,
-    key="audio_recorder"
-)
-
-# Process any pending audio
-if st.session_state.current_audio:
-    process_current_audio()
+    except Exception as e:
+        st.error(f"Error: {str(e)}")
 
 # Control buttons
 col1, col2 = st.columns(2)
 with col1:
     if st.button("Clear Text"):
         st.session_state.text_input = ""
-        st.session_state.current_audio = None
+        st.session_state.last_audio = None
         st.rerun()
 with col2:
     st.download_button(