Update app.py to use Whisper large-v2 model for audio transcription

app.py

@@ -5,7 +5,7 @@ import torch
 from transformers import AutoModelForSpeechSeq2Seq, AutoProcessor, pipeline
 from datasets import load_dataset
 
-@spaces.GPU(duration=600)
+@spaces.GPU(duration=120)
 def transcribe_audio(audio):
     device = "cuda:0" if torch.cuda.is_available() else "cpu"
     torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32

requirements.txt

@@ -3,4 +3,5 @@ transformers
 torch
 torchvision
 torchaudio
-accelerate
+accelerate
+datasets