Update app.py

app.py

@@ -1,18 +1,41 @@
 import gradio as gr
-from huggingface_hub import hf_hub_download
-from datasets import load_dataset
-from whisper import load_model, transcribe
 import os
 import zipfile
 import tempfile
 import spaces
-
-# Download and load the Whisper model for Portuguese
-model_path = hf_hub_download(repo_id="distil-whisper/distil-large-v3-openai", filename="model.bin")
+import torch
+from transformers import AutoModelForSpeechSeq2Seq, AutoProcessor, pipeline
+from datasets import load_dataset
 
 
 @spaces.GPU
 def transcribe_audio(zip_file):
+    device = "cuda:0" if torch.cuda.is_available() else "cpu"
+    torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32
+    
+    model_id = "distil-whisper/distil-large-v3"
+    
+    model = AutoModelForSpeechSeq2Seq.from_pretrained(
+        model_id, torch_dtype=torch_dtype, low_cpu_mem_usage=True, use_safetensors=True
+    )
+    model.to(device)
+    
+    processor = AutoProcessor.from_pretrained(model_id)
+    
+    transcribe = pipeline(
+        "automatic-speech-recognition",
+        model=model,
+        tokenizer=processor.tokenizer,
+        feature_extractor=processor.feature_extractor,
+        max_new_tokens=128,
+        torch_dtype=torch_dtype,
+        device=device,
+    )
+    
+    dataset = load_dataset("distil-whisper/librispeech_long", "clean", split="validation")
+    
+
+
     model = load_model(model_path)
     
     # Create a temporary directory to extract the ZIP file