Update app.py

app.py

@@ -3,18 +3,12 @@ import torch
 from transformers import pipeline, AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig, TextStreamer, AutoModelForSpeechSeq2Seq
 
 # Whisper Model Optimization
-WHISPER_MODEL = "openai/whisper-large-v3"
+model = "openai/whisper-small"
 DEVICE = "cuda" if torch.cuda.is_available() else "cpu"
 
 processor = AutoProcessor.from_pretrained(MODEL_NAME)
 
-whisper_model = AutoModelForSpeechSeq2Seq.from_pretrained(
-    WHISPER_MODEL,
-    torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32,  # Use fp16 if GPU available
-    device_map="auto"
-) 
 
-whisper_tokenizer = AutoTokenizer.from_pretrained(WHISPER_MODEL)
 transcriber = pipeline(
     "automatic-speech-recognition",
     model=model,