Update app.py

app.py

@@ -2,12 +2,21 @@ from flask import Flask, request, render_template, redirect, url_for
 import os
 from moviepy.editor import VideoFileClip
 import whisper
+import hashlib
 
 app = Flask(__name__)
 
 # Configure the maximum content length for uploads (500 MB)
 app.config['MAX_CONTENT_LENGTH'] = 1024 * 1024 * 500  # 500 MB limit
 
+# Create directories for uploads and cache
+UPLOAD_FOLDER = 'uploads'
+AUDIO_FOLDER = 'audio_cache'
+TRANSCRIPT_FOLDER = 'transcript_cache'
+os.makedirs(UPLOAD_FOLDER, exist_ok=True)
+os.makedirs(AUDIO_FOLDER, exist_ok=True)
+os.makedirs(TRANSCRIPT_FOLDER, exist_ok=True)
+
 # Load the Whisper model
 model = whisper.load_model("base")
 
@@ -25,21 +34,38 @@ def upload_video():
         return redirect(url_for('index'))
 
     # Save the video file
-    video_path = os.path.join('uploads', video_file.filename)
+    video_path = os.path.join(UPLOAD_FOLDER, 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)
+        # Generate a unique hash for the video file to use as a cache key
+        video_hash = hashlib.md5(video_file.read()).hexdigest()
+
+        # Check if the audio and transcript are already cached
+        audio_path = os.path.join(AUDIO_FOLDER, f"{video_hash}.wav")
+        transcript_path = os.path.join(TRANSCRIPT_FOLDER, f"{video_hash}.txt")
+
+        if not os.path.exists(audio_path):
+            # Extract audio from the video if not cached
+            audio_path = extract_audio(video_path, audio_path)
+
+        if not os.path.exists(transcript_path):
+            # Transcribe the audio if not cached
+            transcript = transcribe_audio(audio_path)
+            # Cache the transcript
+            with open(transcript_path, 'w') as f:
+                f.write(transcript)
+        else:
+            # Load cached transcript
+            with open(transcript_path, 'r') as f:
+                transcript = f.read()
+
     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"
+def extract_audio(video_path, audio_path):
     try:
         # Use a temporary file to reduce the load on memory
         with VideoFileClip(video_path) as video:
@@ -59,4 +85,4 @@ def transcribe_audio(audio_path):
         raise RuntimeError(f"Error during transcription: {e}")
 
 if __name__ == '__main__':
-    app.run(debug=False, host='0.0.0.0', port=7860)
+    app.run(debug=False, host='0.0.0.0', port=7860)