Update app.py

app.py

@@ -131,7 +131,28 @@ class VideoAnalytics:
         except Exception as e:
             logging.error(f"Error processing audio: {e}")
             return ""
+            
+    def split_audio(self,input_file):
+        # Load the audio file
+        audio = AudioSegment.from_file(input_file)
+
+        # Define segment length in milliseconds (5 minutes = 300,000 milliseconds)
+        segment_length = 60000
+
+        # Split the audio into segments
+        segments = []
+        for i, start_time in enumerate(range(0, len(audio), segment_length)):
+            # Calculate end time for current segment
+            end_time = start_time + segment_length if start_time + segment_length < len(audio) else len(audio)
+            
+            # Extract segment
+            segment = audio[start_time:end_time]
+            
+            # Append segment to list
+            segments.append(segment)
 
+        return segments
+        
     def transcribe_video(self, vid: str) -> str:
       """
       Transcribe the audio of the video.
@@ -151,9 +172,11 @@ class VideoAnalytics:
 
           # Replace 'input.mp3' and 'output.wav' with your file paths
           audio_filename = self.mp3_to_wav("output_audio.mp3", 'output.wav')
-          
+          segments = self.split_audio(audio_filename)
+          splitted_audio_filename = segments[0].export("segment_for_1_min.wav",format="wav")
+
           # for detect lang
-          signal = self.language_id.load_audio(audio_filename)
+          signal = self.language_id.load_audio(splitted_audio_filename.name)
           prediction =  self.language_id.classify_batch(signal)
           lang = [prediction[3][0].split(":")][0][0]
           text  = self.get_large_audio_transcription_on_silence(audio_filename,lang)