Update main.py

main.py

@@ -38,25 +38,25 @@ def convert_size(bytes):
         return f"{bytes / 1024**2:.2f} MB"
 
 def transcribe(audio_path):
-    print(f"Transcribing audio from: {audio_path}", flush=True)
+    #print(f"        Transcribing audio from: {audio_path}", flush=True)
 
     # Load audio and pad/trim it to fit 30 seconds
-    print("        Loading and processing audio...", flush=True)
+    #print("        Loading and processing audio...", flush=True)
     audio = whisper.load_audio(audio_path)
     audio = whisper.pad_or_trim(audio)
 
     # Make log-Mel spectrogram and move to the same device as the model
-    print("        Creating log-Mel spectrogram...", flush=True)
+    #print("        Creating log-Mel spectrogram...", flush=True)
     mel = whisper.log_mel_spectrogram(audio).to(model.device)
 
     # Detect the spoken language
-    print("        Detecting language...", flush=True)
+    #print("        Detecting language...", flush=True)
     _, probs = model.detect_language(mel)
     language = max(probs, key=probs.get)
-    print(f"        Detected language: {language}", flush=True)
+    #print(f"        Detected language: {language}", flush=True)
 
     # Decode the audio
-    print("        Decoding audio...", flush=True)
+    #print("        Decoding audio...", flush=True)
     options = whisper.DecodingOptions(fp16=False)
     result = whisper.decode(model, mel, options)
     
@@ -106,7 +106,7 @@ def transcribe_audio():
     response_sent_time, _ = get_time()
 
     # Return the transcription, detected language, and timing information
-    print(f"        Transcription: {transcription}, Language: {language}\n", flush=True)
+    print(f"        Transcription: {transcription}, Language: {language}, Processing Time: {transcription_duration_seconds}\n", flush=True)
     return jsonify({
         "transcription": transcription,
         "language": language,