Update app.py

app.py

@@ -5,7 +5,7 @@ from pydub import AudioSegment
 import tempfile
 import os
 import io
-from textblob import TextBlob
+from transformers import pipeline
 import numpy as np
 import wave
 import matplotlib.pyplot as plt
@@ -55,11 +55,17 @@ def transcribe_audio(audio_file):
     except sr.RequestError:
         return "Could not request results from Google Speech Recognition service."
 
-# Function for sentiment analysis using TextBlob
-def analyze_sentiment(text):
-    blob = TextBlob(text)
-    sentiment = blob.sentiment
-    return sentiment
+# Function to perform emotion detection using Hugging Face transformers
+def detect_emotion(text):
+    # Load emotion detection pipeline
+    emotion_pipeline = pipeline("text-classification", model="j-hartmann/emotion-english-distilroberta-base", return_all_scores=True)
+    
+    # Get the emotion predictions
+    result = emotion_pipeline(text)
+    
+    # Extract the emotion with the highest score
+    emotions = {emotion['label']: emotion['score'] for emotion in result[0]}
+    return emotions
 
 # Function to visualize audio waveform
 def plot_waveform(audio_file):
@@ -73,8 +79,8 @@ def plot_waveform(audio_file):
         st.pyplot(plt)
 
 # Streamlit app layout
-st.title("Video and Audio to Text Transcription with Sentiment and Visualization")
-st.write("Upload a video or audio file to convert it to transcription, analyze sentiment, and visualize the audio waveform.")
+st.title("Video and Audio to Text Transcription with Emotion Detection and Visualization")
+st.write("Upload a video or audio file to convert it to transcription, detect emotions, and visualize the audio waveform.")
 
 # Create tabs to separate video and audio uploads
 tab = st.selectbox("Select the type of file to upload", ["Video", "Audio"])
@@ -105,9 +111,9 @@ if tab == "Video":
                 # Show the transcription
                 st.text_area("Transcription", transcription, height=300)
 
-                # Sentiment analysis
-                sentiment = analyze_sentiment(transcription)
-                st.write(f"Sentiment: {sentiment}")
+                # Emotion detection
+                emotions = detect_emotion(transcription)
+                st.write(f"Detected Emotions: {emotions}")
                 
                 # Plot the audio waveform
                 st.subheader("Audio Waveform Visualization")
@@ -173,9 +179,9 @@ elif tab == "Audio":
                 # Show the transcription
                 st.text_area("Transcription", transcription, height=300)
 
-                # Sentiment analysis
-                sentiment = analyze_sentiment(transcription)
-                st.write(f"Sentiment: {sentiment}")
+                # Emotion detection
+                emotions = detect_emotion(transcription)
+                st.write(f"Detected Emotions: {emotions}")
                 
                 # Plot the audio waveform
                 st.subheader("Audio Waveform Visualization")
@@ -212,4 +218,4 @@ elif tab == "Audio":
                 data=st.session_state.wav_audio_file_audio,
                 file_name="converted_audio_audio.wav",
                 mime="audio/wav"
-            )
+            )