Update app.py

app.py

@@ -2,23 +2,22 @@ import streamlit as st
 import librosa
 import numpy as np
 import matplotlib.pyplot as plt
+import seaborn as sns
 from pydub import AudioSegment
 from transformers import pipeline
 import os
-import openai_whisper as whisper
-import whisper  # OpenAI Whisper for transcription
 
 # Load pre-trained sentiment analysis model
 sentiment_analyzer = pipeline("sentiment-analysis")
 
 # Streamlit UI
-st.title("🎤 Audio Sentiment Analysis")
-st.write("Upload multiple MP3 files to analyze sentiment and tone.")
+st.title("🎤 Audio Sentiment & Feature Analysis")
+st.write("Upload an MP3 file to analyze its sentiment and audio features.")
 
-# Upload multiple audio files
-uploaded_files = st.file_uploader("Choose MP3 files", type=["mp3"], accept_multiple_files=True)
+# Upload audio file
+uploaded_file = st.file_uploader("Choose an MP3 file", type=["mp3"])
 
-# Function to process audio, get sentiment, and transcribe to text using Whisper
+# Function to process audio and get sentiment
 def analyze_audio(file_path):
     # Convert MP3 to WAV
     audio = AudioSegment.from_mp3(file_path)
@@ -32,63 +31,69 @@ def analyze_audio(file_path):
     mfccs = librosa.feature.mfcc(y=y, sr=sr, n_mfcc=13)
     mfccs_mean = np.mean(mfccs, axis=1)  # Take mean across time axis
 
-    # Perform speech-to-text transcription using Whisper
-    model = whisper.load_model("base")  # Load Whisper model
-    result = model.transcribe(wav_path)
-    transcription = result['text']
-    
-    # Perform sentiment analysis on the transcription
-    sentiment_result = sentiment_analyzer(transcription) if transcription else [{"label": "NEGATIVE", "score": 0.5}]
-    
+    # Dummy text for sentiment analysis (replace with actual text from speech-to-text if needed)
+    sentiment_result = sentiment_analyzer("This is a placeholder for sentiment analysis based on audio!")
+
     # Remove WAV file after processing
     os.remove(wav_path)
     
-    return sentiment_result[0], mfccs_mean, mfccs, y, sr, transcription
-
-# Process and plot if files are uploaded
-if uploaded_files:
-    # Create a directory to store temporary files
-    os.makedirs("temp", exist_ok=True)
-
-    # Prepare a single plot
-    fig, ax = plt.subplots(figsize=(10, 6))
+    return y, sr, sentiment_result[0], mfccs, mfccs_mean
 
-    for uploaded_file in uploaded_files:
-        # Save the uploaded file
-        file_path = f"temp/{uploaded_file.name}"
-        with open(file_path, "wb") as f:
-            f.write(uploaded_file.getbuffer())
+# Process and plot if a file is uploaded
+if uploaded_file:
+    file_path = f"temp/{uploaded_file.name}"
 
-        # Analyze sentiment, extract features, and get transcription
-        sentiment, mfccs_mean, mfccs, audio_data, sample_rate, transcription = analyze_audio(file_path)
-
-        # Display sentiment and transcription result
-        st.subheader(f"📊 Sentiment Analysis Result for {uploaded_file.name}")
-        st.write(f"**Transcription:** {transcription}")
-        st.write(f"**Sentiment:** {sentiment['label']}")
-        st.write(f"**Confidence:** {sentiment['score']:.2f}")
-
-        # Normalize sentiment score to range from 0 to 1
-        sentiment_score = sentiment['score'] if sentiment['label'] == 'POSITIVE' else 1 - sentiment['score']
+    # Ensure temp directory exists
+    os.makedirs("temp", exist_ok=True)
 
-        # Plotting both curves in a single plot
-        ax.plot(np.linspace(0, len(audio_data) / sample_rate, len(audio_data)), [sentiment_score] * len(audio_data), label="Agent's Tone", linestyle='-', color='b')
-        
-        # Ensure that MFCCs are being averaged across time correctly
-        # Take the mean along the time axis (axis=1) to get one value per MFCC coefficient
-        mfccs_mean = np.mean(mfccs, axis=1)
+    # Save the uploaded file
+    with open(file_path, "wb") as f:
+        f.write(uploaded_file.getbuffer())
+
+    # Analyze sentiment and extract features
+    y, sr, sentiment, mfccs, mfccs_mean = analyze_audio(file_path)
+
+    # Display sentiment result
+    st.subheader("📊 Sentiment Analysis Result")
+    st.write(f"**Sentiment:** {sentiment['label']}")
+    st.write(f"**Confidence:** {sentiment['score']:.2f}")
+
+    # Plot MFCC Bar Chart
+    st.subheader("🎵 MFCC Feature Plot")
+    fig, ax = plt.subplots()
+    ax.bar(range(len(mfccs_mean)), mfccs_mean)
+    ax.set_xlabel("MFCC Coefficients")
+    ax.set_ylabel("Mean Value")
+    ax.set_title("MFCC Feature Extraction")
+    st.pyplot(fig)
 
-        # Plot Patient's Tone Curve (MFCC mean value per coefficient)
-        ax.plot(np.linspace(0, len(mfccs_mean), len(mfccs_mean)), mfccs_mean, label="Patient's Tone Curve (MFCCs)", linestyle='--', color='r')
+    # **Plot Audio Waveform**
+    st.subheader("📈 Audio Waveform")
+    fig, ax = plt.subplots(figsize=(10, 3))
+    librosa.display.waveshow(y, sr=sr, ax=ax, alpha=0.5)
+    ax.set_xlabel("Time (s)")
+    ax.set_ylabel("Amplitude")
+    ax.set_title("Waveform of Audio")
+    st.pyplot(fig)
 
-    # Customize plot
-    ax.set_xlabel("Time (seconds) / MFCC Coefficients")
-    ax.set_ylabel("Score / Mean MFCC Value")
-    ax.set_title("Agent Tone & Patient Tone Curve")
-    ax.legend()
+    # **Plot MFCC Heatmap**
+    st.subheader("🔥 MFCC Heatmap")
+    fig, ax = plt.subplots(figsize=(10, 4))
+    sns.heatmap(mfccs, cmap="coolwarm", yticklabels=[f"MFCC {i}" for i in range(1, 14)])
+    ax.set_xlabel("Time Frames")
+    ax.set_ylabel("MFCC Coefficients")
+    ax.set_title("MFCC Feature Heatmap")
+    st.pyplot(fig)
 
-    # Show plot in Streamlit
+    # **Plot Spectrogram**
+    st.subheader("🎼 Spectrogram")
+    fig, ax = plt.subplots(figsize=(10, 4))
+    S = librosa.feature.melspectrogram(y=y, sr=sr)
+    S_dB = librosa.power_to_db(S, ref=np.max)
+    img = librosa.display.specshow(S_dB, sr=sr, x_axis="time", y_axis="mel", ax=ax)
+    fig.colorbar(img, ax=ax, format="%+2.0f dB")
+    ax.set_title("Mel Spectrogram")
     st.pyplot(fig)
 
-    # Clean up temp files
+    # Clean up temp file
     os.remove(file_path)