Update app.py

app.py

@@ -21,7 +21,7 @@ torch_dtype = torch.float32
 model.to(device)
 
 
-def transcribe_audio(audio_file):
+def transcribe_audio(audio_file, batch_size=4):
     audio_input, sample_rate = sf.read(audio_file)
     chunk_size = 16000 * 28  # 28 seconds chunks, seems to work best
     chunks = [audio_input[i:i + chunk_size] for i in range(0, len(audio_input), chunk_size)]
@@ -44,10 +44,15 @@ def transcribe_audio(audio_file):
             )
         transcription += " ".join(processor.batch_decode(output, skip_special_tokens=True)) + " "
 
+    return transcription.strip()
+
 # HTML |banner image
 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;">
+    <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="Additional Image" width="50%" height="auto">
 </div>
 """