Update app.py

app.py

@@ -3,6 +3,11 @@ from huggingface_hub import InferenceClient
 import random
 import whisper
 from pydub import AudioSegment
+import torch
+import torchvision.transforms as transforms
+import torchvision.models as models
+from PIL import Image
+
 # Load models
 client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
 whisper_model = whisper.load_model("base")