Changes in transcribe_audio, made directly using mp4

app.py

@@ -75,30 +75,45 @@ def process_video():
             os.remove(temp_video_file.name)
 
 
+# def transcribe_audio(video_path):
+#     """
+#     Extract audio from video file and transcribe using Whisper AI.
+#     """
+#     try:
+#         # Extract audio using ffmpeg
+#         audio_path = video_path.replace(".mp4", ".wav")
+#         command = [
+#             "ffmpeg",
+#             "-i", video_path,
+#             "-q:a", "0",
+#             "-map", "a",
+#             audio_path
+#         ]
+#         subprocess.run(command, check=True)
+#         print(f"Audio extracted to: {audio_path}")
+
+#         # Transcribe audio using Whisper AI
+#         print("Transcribing audio...")
+#         result = whisper_model.transcribe(audio_path)
+
+#         # Clean up audio file after transcription
+#         if os.path.exists(audio_path):
+#             os.remove(audio_path)
+
+#         return result.get("text", "").strip()
+
+#     except Exception as e:
+#         print(f"Error in transcription: {e}")
+#         return None
+
 def transcribe_audio(video_path):
     """
-    Extract audio from video file and transcribe using Whisper AI.
+    Transcribe audio directly from a video file using Whisper AI.
     """
     try:
-        # Extract audio using ffmpeg
-        audio_path = video_path.replace(".mp4", ".wav")
-        command = [
-            "ffmpeg",
-            "-i", video_path,
-            "-q:a", "0",
-            "-map", "a",
-            audio_path
-        ]
-        subprocess.run(command, check=True)
-        print(f"Audio extracted to: {audio_path}")
-
-        # Transcribe audio using Whisper AI
-        print("Transcribing audio...")
-        result = whisper_model.transcribe(audio_path)
-
-        # Clean up audio file after transcription
-        if os.path.exists(audio_path):
-            os.remove(audio_path)
+        # Transcribe audio from video directly using Whisper AI
+        print(f"Transcribing video: {video_path}")
+        result = whisper_model.transcribe(video_path)
 
         return result.get("text", "").strip()
 
@@ -107,6 +122,7 @@ def transcribe_audio(video_path):
         return None
 
 
+
 def query_gemini_api(transcription):
     """
     Send transcription text to Gemini API and fetch structured recipe information.