Update app.py

app.py

@@ -28,13 +28,14 @@ def transcribe_audio(audio_file):
 # Create Gradio interface
 iface = gr.Interface(
     fn=transcribe_audio,
-    inputs=gr.Audio(source="upload", type="filepath"),
+    inputs=gr.Audio(type="filepath"),
     outputs="text",
     title="Audio Transcription App",
     description="Upload an audio file to get the transcription",
     theme="default",
     layout="vertical",
     live=False
+)
 
     
 from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq, AutoTokenizer, AutoModelForSeq2SeqLM
@@ -106,15 +107,15 @@ def transcribe_audio(audio_file, batch_size=4):
     
     return transcription.strip(), result
 
-    def summarize_text(text):
+def summarize_text(text):
     inputs = summarization_tokenizer([text], max_length=1024, return_tensors="pt", truncation=True)
     inputs = inputs.to(device)
     summary_ids = summarization_model.generate(inputs.input_ids, num_beams=4, max_length=150, early_stopping=True)
     summary = summarization_tokenizer.decode(summary_ids[0], skip_special_tokens=True)
     return summary
 
-    # HTML syntax for imagery
-banner_html = """
+# HTML syntax for imagery
+image_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>
@@ -127,7 +128,7 @@ banner_html = """
 iface = gr.Blocks()
 
 with iface:
-    gr.HTML(banner_html)
+    gr.HTML(image_html)
     gr.Markdown("# Switch Work Audio Transcription App\nUpload an audio file to get the transcription")
     audio_input = gr.Audio(type="filepath")
     batch_size_input = gr.Slider(minimum=1, maximum=16, step=1, default=4, label="Batch Size")
@@ -136,9 +137,9 @@ with iface:
     transcribe_button = gr.Button("Transcribe and Summarize")
 
     def transcribe_and_summarize(audio_file, batch_size):
-        transcription = transcribe_audio(audio_file, batch_size)
+        transcription, result = transcribe_audio(audio_file, batch_size)
         summary = summarize_text(transcription)
-        return transcription, summary
+        return result, summary
 
     transcribe_button.click(fn=transcribe_and_summarize, inputs=[audio_input, batch_size_input], outputs=[transcription_output, summary_output])
     
@@ -148,7 +149,7 @@ def save_to_pdf(transcription, summary):
     pdf.add_page()
     pdf.set_font("Arial", size=12)
     
-    # incøude transcription
+    # include transcription
     pdf.multi_cell(0, 10, "Transcription:\n" + transcription)
     
     # paragraph space
@@ -165,7 +166,3 @@ def save_to_pdf(transcription, summary):
     
 # run
 iface.launch(share=True, debug=True)
-
-
-
-