Update app.py

app.py

@@ -7,8 +7,8 @@ import torch
 
 pipe1 = pipeline("automatic-speech-recognition", model="openai/whisper-base")
 pipe2 = pipeline("summarization", model="facebook/bart-large-cnn")
-pipe3 = DiffusionPipeline.from_pretrained("stable-diffusion-v1-5/stable-diffusion-v1-5")
-pipe3.to("cuda" if torch.cuda.is_available() else "cpu")
+#pipe3 = DiffusionPipeline.from_pretrained("stable-diffusion-v1-5/stable-diffusion-v1-5")
+#pipe3.to("cuda" if torch.cuda.is_available() else "cpu")
 
 def audio_to_image(audio):
     
@@ -19,10 +19,15 @@ def audio_to_image(audio):
         summary = pipe2(transcription_text, max_length=50, min_length=10, do_sample=False)
         summary_text = summary[0]['summary_text']
        
-        prompt = summary_text
-        image = pipe3(prompt).images[0]
+        #prompt = summary_text
+        #image = pipe3(prompt).images[0]
         
-        return image
+        #return image
+        print("Transcription:", transcription_text)
+        print("Summary:", summary_text)
+        return transcription_text, summary_text
+
     
-demo = gr.Interface(fn=audio_to_image, inputs=gr.Audio(), outputs="image")
+#demo = gr.Interface(fn=audio_to_image, inputs=gr.Audio(), outputs="image")
+demo = gr.Interface(fn=audio_to_image, inputs=gr.Audio(), outputs=[gr.Textbox(label="Transcription"), gr.Textbox(label="Summary")])
 demo.launch(share=True)