video-text / app.py
Elalimy's picture
Update app.py
e407e34 verified
from flask import Flask, request, render_template, redirect, url_for
import os
from moviepy.editor import VideoFileClip
import whisper
app = Flask(__name__)
# Configure the maximum content length for uploads (500 MB)
app.config['MAX_CONTENT_LENGTH'] = 1024 * 1024 * 500 # 500 MB limit
# Load the Whisper model
model = whisper.load_model("base")
@app.route('/')
def index():
return render_template('index.html')
@app.route('/upload', methods=['POST'])
def upload_video():
if 'video' not in request.files:
return redirect(url_for('index'))
video_file = request.files['video']
if video_file.filename == '':
return redirect(url_for('index'))
# Save the video file
video_path = os.path.join('uploads', video_file.filename)
video_file.save(video_path)
try:
# Extract audio from the video
audio_path = extract_audio(video_path)
# Transcribe the audio
transcript = transcribe_audio(audio_path)
except Exception as e:
return f"Error: {e}"
return render_template('result.html', transcript=transcript)
def extract_audio(video_path):
audio_path = os.path.splitext(video_path)[0] + ".wav"
try:
# Use a temporary file to reduce the load on memory
with VideoFileClip(video_path) as video:
video.audio.write_audiofile(audio_path)
except Exception as e:
raise RuntimeError(f"Error extracting audio: {e}")
return audio_path
def transcribe_audio(audio_path):
if not os.path.exists(audio_path):
raise FileNotFoundError(f"Audio file not found at {audio_path}")
try:
result = model.transcribe(audio_path)
return result["text"]
except Exception as e:
raise RuntimeError(f"Error during transcription: {e}")
if __name__ == '__main__':
app.run(debug=False, host='0.0.0.0', port=7860)