Update app.py

app.py

@@ -7,6 +7,7 @@ subprocess.run(["pip", "install", "transformers"])
 subprocess.run(["pip", "install", "torch", "torchvision", "torchaudio", "-f", "https://download.pytorch.org/whl/torch_stable.html"])
 import gradio as gr
 import numpy as np
+import torch
 from transformers import WhisperProcessor, WhisperForConditionalGeneration
 
 # Load model and processor
@@ -23,7 +24,8 @@ def preprocess_audio(audio_data, sampling_rate=16_000):
 # Function to perform ASR on audio data
 def transcribe_audio(audio_data):
     input_features = preprocess_audio(audio_data)
-    predicted_ids = model.generate(input_features["input_values"])
+    input_values = torch.tensor(input_features["input_values"]).unsqueeze(0)  # Add batch dimension
+    predicted_ids = model.generate(input_values)
     transcription = processor.batch_decode(predicted_ids, skip_special_tokens=True)
     return transcription[0]