Spaces:
Sleeping
Sleeping
| import streamlit as st | |
| import moviepy.editor as mp | |
| import speech_recognition as sr | |
| from pydub import AudioSegment | |
| import tempfile | |
| import os | |
| # 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." | |
| # Streamlit app layout | |
| st.title("Video to Audio to Text Transcription") | |
| st.write("Upload a video file, and it will be converted to audio and transcribed into text.") | |
| # 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) | |
| # Store transcription and audio file in session state | |
| st.session_state.transcription = transcription | |
| st.session_state.wav_audio_file = wav_audio_file | |
| # 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 | |
| with open(st.session_state.wav_audio_file, "rb") as audio_file_data: | |
| st.download_button( | |
| label="Download Audio", | |
| data=audio_file_data, | |
| file_name="converted_audio.wav", | |
| mime="audio/wav" | |
| ) |