Update app.py

app.py

@@ -2,9 +2,7 @@ import streamlit as st
 import whisper
 import torch
 import spacy
-import speech_recognition as sr
 from transformers import pipeline
-import tempfile
 
 # Load spaCy Model
 try:
@@ -32,37 +30,23 @@ whisper_model = load_whisper()
 
 # Streamlit UI
 st.title("🎙️ Voice-Controlled AI Text Editor")
-st.subheader("Supports Real-Time Speech-to-Text, Sentiment Analysis, Summarization & POS Tagging")
-
-# Store text history for undo/redo
-if "text_history" not in st.session_state:
-    st.session_state.text_history = [""]
-    st.session_state.history_index = 0
-
-def get_current_text():
-    return st.session_state.text_history[st.session_state.history_index]
-
-def update_text(new_text):
-    # Save history for undo/redo
-    st.session_state.text_history = st.session_state.text_history[:st.session_state.history_index + 1]
-    st.session_state.text_history.append(new_text)
-    st.session_state.history_index += 1
-
-# Speech Recognition
-def recognize_speech():
-    recognizer = sr.Recognizer()
-    with sr.Microphone() as source:
-        st.write("🎤 Listening... Speak now!")
-        recognizer.adjust_for_ambient_noise(source)
-        audio = recognizer.listen(source)
-
-    with tempfile.NamedTemporaryFile(delete=True, suffix=".wav") as temp_audio:
-        temp_audio.write(audio.get_wav_data())
-        temp_audio.flush()
-        result = whisper_model.transcribe(temp_audio.name)
-        return result["text"]
-
-# Command Processing
+st.subheader("Supports Speech-to-Text, Sentiment Analysis, Summarization & POS Tagging")
+
+# File Upload for Whisper
+uploaded_audio = st.file_uploader("🎵 Upload an audio file", type=["wav", "mp3", "m4a"])
+
+if uploaded_audio:
+    st.audio(uploaded_audio, format="audio/wav")
+    with open("temp_audio.wav", "wb") as f:
+        f.write(uploaded_audio.read())
+    
+    with st.spinner("Transcribing..."):
+        result = whisper_model.transcribe("temp_audio.wav")
+        text = result["text"]
+        st.success("Transcription Complete!")
+        st.text_area("Transcribed Text", text, height=200)
+
+# Function to process voice commands
 def process_command(command, text):
     command = command.lower()
     if "summarize" in command:
@@ -70,13 +54,7 @@ def process_command(command, text):
     elif "analyze sentiment" in command:
         return analyze_sentiment(text)
     elif "delete" in command:
-        return ""  # Clear text
-    elif "undo" in command and st.session_state.history_index > 0:
-        st.session_state.history_index -= 1
-        return get_current_text()
-    elif "redo" in command and st.session_state.history_index < len(st.session_state.text_history) - 1:
-        st.session_state.history_index += 1
-        return get_current_text()
+        return ""
     else:
         return text  # Return original text if no command is matched
 
@@ -87,38 +65,25 @@ def summarize_text(text):
     summary = summarizer(text[:1024], max_length=100, min_length=30, do_sample=False)
     return summary[0]['summary_text']
 
-# Sentiment Analysis Function (Happy, Sad, Positive, Negative, Neutral, Fact-based)
+# Sentiment Analysis Function
 def analyze_sentiment(text):
-    result = sentiment_analyzer(text[:512])[0]
-    if result["label"] == "POSITIVE":
-        if result["score"] > 0.85:
-            mood = "😊 Happy"
-        else:
-            mood = "🙂 Positive"
-    elif result["label"] == "NEGATIVE":
-        if result["score"] > 0.85:
-            mood = "😢 Sad"
-        else:
-            mood = "🙁 Negative"
-    else:
-        mood = "🧐 Neutral / Fact-based"
-
-    return f"Sentiment: {mood} (Confidence: {result['score']:.2f})"
+    result = sentiment_analyzer(text[:512])
+    return f"Sentiment: {result[0]['label']} (Confidence: {result[0]['score']:.2f})"
 
 # POS Tagging Function
 def pos_tagging(text):
     doc = nlp(text)
     return [f"{token.text} -> {token.pos_}" for token in doc]
 
-# Real-Time Voice Command
+# Voice Command for Summarization or Sentiment Analysis
 if st.button("🎙️ Speak Command"):
     with st.spinner("Listening..."):
-        command = recognize_speech()
+        result = whisper_model.transcribe("temp_audio.wav")
+        command = result["text"]
         st.write(f"Command Recognized: {command}")
 
         # Process the command
-        processed_text = process_command(command, get_current_text())
-        update_text(processed_text)
+        processed_text = process_command(command, text)
         st.text_area("Processed Text", processed_text, height=200)
 
 # Sidebar Options
@@ -126,34 +91,21 @@ with st.sidebar:
     st.header("⚡ Actions")
     
     if st.button("😊 Analyze Sentiment"):
-        sentiment = analyze_sentiment(get_current_text())
+        sentiment = analyze_sentiment(text)
         st.success(sentiment)
 
     if st.button("📝 Summarize Text"):
-        summary = summarize_text(get_current_text())
+        summary = summarize_text(text)
         st.success(summary)
 
     if st.button("🔍 Show POS Tags"):
-        pos_tags = pos_tagging(get_current_text())
+        pos_tags = pos_tagging(text)
         st.write("🔎 POS Tags:", pos_tags)
-
+    
     if st.button("❌ Clear Text"):
-        update_text("")
+        text = ""
         st.success("Text cleared.")
 
-    if st.button("↩️ Undo"):
-        if st.session_state.history_index > 0:
-            st.session_state.history_index -= 1
-            st.success("Undo successful!")
-
-    if st.button("↪️ Redo"):
-        if st.session_state.history_index < len(st.session_state.text_history) - 1:
-            st.session_state.history_index += 1
-            st.success("Redo successful!")
-
-# Display text area
-st.text_area("📝 Live Text Editor", get_current_text(), height=200)
-