Update app.py

app.py

@@ -13,6 +13,7 @@ model = WhisperForConditionalGeneration.from_pretrained(
     peft_config.base_model_name_or_path, load_in_8bit=False, device_map="cuda:0"
 )
 model = PeftModel.from_pretrained(model, peft_model_id)
+model.merge_and_unload()
 tokenizer = WhisperTokenizer.from_pretrained(peft_config.base_model_name_or_path, language=language, task=task)
 processor = WhisperProcessor.from_pretrained(peft_config.base_model_name_or_path, language=language, task=task)
 feature_extractor = processor.feature_extractor