Create app.py

app.py

@@ -0,0 +1,24 @@
+import gradio as gr
+import numpy as np
+from transformers import pipeline
+from diffusers import DiffusionPipeline
+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")
+
+def audio_to_image(audio):
+    transcription = pipe1(audio)["text"]
+    
+    summary = pipe2(transcription, max_length=30, min_length=10, do_sample=False)
+    summary_text = summary[0]['summary_text']
+   
+    prompt = summary_text
+    image = pipe3(prompt).images[0]
+    
+    return image
+
+demo = gr.Interface(fn=audio_to_image, inputs=gr.Audio(source="upload"), outputs="image")
+demo.launch(share=True)