Update app.py

app.py

@@ -6,6 +6,9 @@ import torch
 from transformers import WhisperTokenizer, WhisperForConditionalGeneration, WhisperProcessor
 import soundfile as sf
 import ffmpeg
+import os
+from huggingface_hub import InferenceClient
+from gradio_client import Client, file
 import spaces
 
 warnings.filterwarnings("ignore")
@@ -28,7 +31,7 @@ def convert_audio_format(audio_path):
     return output_path
 
     
-@spaces.GPU 
+@spaces.GPU(duration=120, queue=False)
 def transcribe_audio(audio_file, batch_size=4):
     audio_path = convert_audio_format(audio_file)
     audio_input, sample_rate = sf.read(audio_path)
@@ -52,16 +55,26 @@ def transcribe_audio(audio_file, batch_size=4):
 
     return transcription.strip()
 
-# HTML | Banner image
+# HTML
 banner_html = """
 <div style="text-align: center;">
     <img src="https://huggingface.co/spaces/camparchimedes/ola_s-audioshop/raw/main/Olas%20AudioSwitch%20Shop.png" alt="Banner" width="87%" height="auto">
 </div>
 <div style="text-align: center; margin-top: 20px;">
-    <img src="https://huggingface.co/spaces/camparchimedes/ola_s-audioshop/raw/main/picture.jpg" alt="image" width="50%" height="auto">
+    <img src="https://huggingface.co/spaces/camparchimedes/ola_s-audioshop/raw/main/picture.jpg" alt="picture" width="50%" height="auto">
 </div>
 """
 
+images_path = os.path.dirname(__file__)
+IMAGES = [
+    [
+        {
+            "text": "What usual stuff happens in this image? :)",
+            "files": [f"{images_path}/500x_picture.png"],
+        }
+    ]
+]
+
 # Gradio interface
 iface = gr.Blocks()