Update app.py

app.py

@@ -12,7 +12,7 @@ text_model = transformers.pipeline("text-generation")
 audio_model = transformers.Wav2Vec2ForCTC.from_pretrained("facebook/wav2vec2-base-960h")
 audio_tokenizer = transformers.Wav2Vec2Tokenizer.from_pretrained("facebook/wav2vec2-base-960h")
 image_model = transformers.pipeline("image-classification")
-video_model = transformers.VideoClassificationPipeline(model="mmf/facebook-mmf-vit-base-16", feature_extractor="mmf/facebook-mmf-vit-base-16")
+#video_model = transformers.VideoClassificationPipeline(model="mmf/facebook-mmf-vit-base-16", feature_extractor="mmf/facebook-mmf-vit-base-16")
 
 
 # Define functions for processing inputs and outputs