Update app.py

app.py

@@ -175,18 +175,29 @@ class VideoClassifier:
         video_name = mp4_file.split("/")[-1]
         wav_file = "results/audiotrack.wav"
         video_clip = VideoFileClip(mp4_file)
-        audioclip = video_clip.audio
-        wav_file = audioclip.write_audiofile(wav_file)
-        audioclip.close()
+        with tempfile.NamedTemporaryFile(suffix=".wav", delete=False) as temp_audio:
+            video_clip.audio.write_audiofile(temp_audio.name, codec='pcm_s16le', nbytes=2, fps=16000)
         video_clip.close()
-        audiotrack = "results/audiotrack.wav"
-        # client = OpenAI(api_key="sk-proj-KY1qI7zTpsUiJhMUHuNdT3BlbkFJLOjVnTUSpYJi87yUtSEI")
-        # audiotrack= open("audiotrack.wav", "rb")
-        transcription = self.client.audio.transcriptions.create(
-          model="whisper-1", 
-          file=audioclip
-        )
-        print(transcription.text)
+        
+        with open(temp_audio.name, 'rb') as audio_file:
+            transcription = client.audio.transcriptions.create(
+                model="whisper-1", 
+                file=audio_file
+            )
+            print(transcription.text)
+        os.remove(temp_audio.name)
+        # audioclip = video_clip.audio
+        # wav_file = audioclip.write_audiofile(wav_file)
+        # audioclip.close()
+        # video_clip.close()
+        # audiotrack = "results/audiotrack.wav"
+        # # client = OpenAI(api_key="sk-proj-KY1qI7zTpsUiJhMUHuNdT3BlbkFJLOjVnTUSpYJi87yUtSEI")
+        # # audiotrack= open("audiotrack.wav", "rb")
+        # transcription = self.client.audio.transcriptions.create(
+        #   model="whisper-1", 
+        #   file=audioclip
+        # )
+        # print(transcription.text)
         return transcription.text
         
     def generate_text(self, inputs, parameters=None):