Update README.md

README.md

@@ -43,26 +43,47 @@ how to use the model in colab:
         audio.export(wav_path, format="wav")
         return wav_path
     
-    # Transcribe an audio file and save as text
-    def transcribe(audio_path):
+    # Split long audio into chunks
+    def split_audio(audio_path, chunk_length_ms=30000):  # Default: 30 sec per chunk
+        audio = AudioSegment.from_wav(audio_path)
+        chunks = [audio[i:i+chunk_length_ms] for i in range(0, len(audio), chunk_length_ms)]
+        chunk_paths = []
+        
+        for i, chunk in enumerate(chunks):
+            chunk_path = f"chunk_{i}.wav"
+            chunk.export(chunk_path, format="wav")
+            chunk_paths.append(chunk_path)
+        
+        return chunk_paths
+    
+    # Transcribe a long audio file
+    def transcribe_long_audio(audio_path):
         wav_path = convert_to_wav(audio_path)
-        result = whisper_pipe(wav_path)
-        os.remove(wav_path)  # Cleanup temporary file
+        chunk_paths = split_audio(wav_path)
+        transcription = ""
+        
+        for chunk in chunk_paths:
+            result = whisper_pipe(chunk)
+            transcription += result["text"] + "\n"
+            os.remove(chunk)  # Remove processed chunk
+        
+        os.remove(wav_path)  # Cleanup original file
         
         # Save transcription to a text file
         text_path = "transcription.txt"
         with open(text_path, "w") as f:
-            f.write(result["text"])
+            f.write(transcription)
         
         return text_path
     
     # Upload and process audio in Colab
     uploaded = files.upload()
     audio_file = list(uploaded.keys())[0]
-    transcription_file = transcribe(audio_file)
+    transcription_file = transcribe_long_audio(audio_file)
     
     # Download the transcription file
     files.download(transcription_file)
 
 
 
+