Update app.py

app.py

@@ -2,6 +2,8 @@ from flask import Flask, request, render_template, redirect, url_for
 import os
 import requests
 from moviepy.editor import VideoFileClip
+from pydub import AudioSegment
+from pydub.utils import make_chunks
 
 app = Flask(__name__)
 
@@ -33,8 +35,8 @@ def upload_video():
     try:
         # Extract audio from the video
         audio_path = extract_audio(video_path)
-        # Transcribe the audio
-        transcript = transcribe_audio(audio_path)
+        # Split and transcribe the audio
+        transcript = split_and_transcribe_audio(audio_path)
     except Exception as e:
         return f"Error: {e}"
 
@@ -50,20 +52,38 @@ def extract_audio(video_path):
         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}")
-
+def transcribe_audio_chunk(audio_chunk):
     try:
-        with open(audio_path, "rb") as audio_file:
-            headers = {"Authorization": f"Bearer {API_TOKEN}"}
-            response = requests.post(API_URL, headers=headers, files={"file": audio_file})
+        headers = {"Authorization": f"Bearer {API_TOKEN}"}
+        response = requests.post(API_URL, headers=headers, files={"file": audio_chunk})
 
         if response.status_code != 200:
             raise RuntimeError(f"Error during transcription: {response.text}")
 
         result = response.json()
-        return result.get("text", "No transcription available")
+        return result.get("text", "")
+    except Exception as e:
+        raise RuntimeError(f"Error during transcription: {e}")
+
+def split_and_transcribe_audio(audio_path):
+    if not os.path.exists(audio_path):
+        raise FileNotFoundError(f"Audio file not found at {audio_path}")
+
+    try:
+        audio = AudioSegment.from_wav(audio_path)
+        chunk_length_ms = 60000  # Split audio into 1-minute chunks
+        chunks = make_chunks(audio, chunk_length_ms)
+        
+        transcript = ""
+        for i, chunk in enumerate(chunks):
+            chunk_path = f"{audio_path[:-4]}_chunk{i}.wav"
+            chunk.export(chunk_path, format="wav")
+            
+            with open(chunk_path, "rb") as audio_chunk:
+                transcript += transcribe_audio_chunk(audio_chunk)
+                transcript += " "  # Add space between chunks' transcriptions
+
+        return transcript.strip()
     except Exception as e:
         raise RuntimeError(f"Error during transcription: {e}")