Update app.py

app.py

@@ -1 +1,200 @@
-st.markdown("Hello World")
+import streamlit as st #
+import moviepy.editor as mp
+import speech_recognition as sr
+from pydub import AudioSegment
+import tempfile
+import os
+import io
+from transformers import pipeline
+import matplotlib.pyplot as plt
+
+# Function to convert video to audio
+def video_to_audio(video_file):
+    # Load the video using moviepy
+    video = mp.VideoFileClip(video_file)
+    
+    # Extract audio
+    audio = video.audio
+    temp_audio_path = tempfile.mktemp(suffix=".mp3")
+    
+    # Write the audio to a file
+    audio.write_audiofile(temp_audio_path)
+    return temp_audio_path
+
+# Function to convert MP3 audio to WAV
+def convert_mp3_to_wav(mp3_file):
+    # Load the MP3 file using pydub
+    audio = AudioSegment.from_mp3(mp3_file)
+    
+    # Create a temporary WAV file
+    temp_wav_path = tempfile.mktemp(suffix=".wav")
+    
+    # Export the audio to the temporary WAV file
+    audio.export(temp_wav_path, format="wav")
+    return temp_wav_path
+
+# Function to transcribe audio to text
+def transcribe_audio(audio_file):
+    # Initialize recognizer
+    recognizer = sr.Recognizer()
+    
+    # Load the audio file using speech_recognition
+    audio = sr.AudioFile(audio_file)
+    
+    with audio as source:
+        audio_data = recognizer.record(source)
+    
+    try:
+        # Transcribe the audio data to text using Google Web Speech API
+        text = recognizer.recognize_google(audio_data)
+        return text
+    except sr.UnknownValueError:
+        return "Audio could not be understood."
+    except sr.RequestError:
+        return "Could not request results from Google Speech Recognition service."
+
+# 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
+
+# Streamlit app layout
+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"])
+
+if tab == "Video":
+    # File uploader for video
+    uploaded_video = st.file_uploader("Upload Video", type=["mp4", "mov", "avi"])
+
+    if uploaded_video is not None:
+        # Save the uploaded video file temporarily
+        with tempfile.NamedTemporaryFile(delete=False) as tmp_video:
+            tmp_video.write(uploaded_video.read())
+            tmp_video_path = tmp_video.name
+
+        # Add an "Analyze Video" button
+        if st.button("Analyze Video"):
+            with st.spinner("Processing video... Please wait."):
+
+                # Convert video to audio
+                audio_file = video_to_audio(tmp_video_path)
+                
+                # Convert the extracted MP3 audio to WAV
+                wav_audio_file = convert_mp3_to_wav(audio_file)
+                
+                # Transcribe audio to text
+                transcription = transcribe_audio(wav_audio_file)
+
+                # Show the transcription
+                st.text_area("Transcription", transcription, height=300)
+
+                # Emotion detection
+                emotions = detect_emotion(transcription)
+                st.write(f"Detected Emotions: {emotions}")
+
+                # Store transcription and audio file in session state
+                st.session_state.transcription = transcription
+                
+                # Store the audio file as a BytesIO object in memory
+                with open(wav_audio_file, "rb") as f:
+                    audio_data = f.read()
+                    st.session_state.wav_audio_file = io.BytesIO(audio_data)
+
+                # Cleanup temporary files
+                os.remove(tmp_video_path)
+                os.remove(audio_file)
+
+    # Check if transcription and audio file are stored in session state
+    if 'transcription' in st.session_state and 'wav_audio_file' in st.session_state:
+        # Provide the audio file to the user for download
+        st.audio(st.session_state.wav_audio_file, format='audio/wav')
+        
+        # Add download buttons for the transcription and audio
+        # Downloadable transcription file
+        st.download_button(
+            label="Download Transcription",
+            data=st.session_state.transcription,
+            file_name="transcription.txt",
+            mime="text/plain"
+        )
+        
+        # Downloadable audio file
+        st.download_button(
+            label="Download Audio",
+            data=st.session_state.wav_audio_file,
+            file_name="converted_audio.wav",
+            mime="audio/wav"
+        )
+
+elif tab == "Audio":
+    # File uploader for audio
+    uploaded_audio = st.file_uploader("Upload Audio", type=["wav", "mp3"])
+
+    if uploaded_audio is not None:
+        # Save the uploaded audio file temporarily
+        with tempfile.NamedTemporaryFile(delete=False) as tmp_audio:
+            tmp_audio.write(uploaded_audio.read())
+            tmp_audio_path = tmp_audio.name
+
+        # Add an "Analyze Audio" button
+        if st.button("Analyze Audio"):
+            with st.spinner("Processing audio... Please wait."):
+
+                # Convert audio to WAV if it's in MP3 format
+                if uploaded_audio.type == "audio/mpeg":
+                    wav_audio_file = convert_mp3_to_wav(tmp_audio_path)
+                else:
+                    wav_audio_file = tmp_audio_path
+                
+                # Transcribe audio to text
+                transcription = transcribe_audio(wav_audio_file)
+
+                # Show the transcription
+                st.text_area("Transcription", transcription, height=300)
+
+                # Emotion detection
+                emotions = detect_emotion(transcription)
+                st.write(f"Detected Emotions: {emotions}")
+
+                # Store transcription in session state
+                st.session_state.transcription_audio = transcription
+                
+                # Store the audio file as a BytesIO object in memory
+                with open(wav_audio_file, "rb") as f:
+                    audio_data = f.read()
+                    st.session_state.wav_audio_file_audio = io.BytesIO(audio_data)
+
+                # Cleanup temporary audio file
+                os.remove(tmp_audio_path)
+
+        # Check if transcription and audio file are stored in session state
+        if 'transcription_audio' in st.session_state and 'wav_audio_file_audio' in st.session_state:
+            # Provide the audio file to the user for download
+            st.audio(st.session_state.wav_audio_file_audio, format='audio/wav')
+            
+            # Add download buttons for the transcription and audio
+            # Downloadable transcription file
+            st.download_button(
+                label="Download Transcription",
+                data=st.session_state.transcription_audio,
+                file_name="transcription_audio.txt",
+                mime="text/plain"
+            )
+            
+            # Downloadable audio file
+            st.download_button(
+                label="Download Audio",
+                data=st.session_state.wav_audio_file_audio,
+                file_name="converted_audio_audio.wav",
+                mime="audio/wav"
+            )