Add application file

app.py

@@ -21,6 +21,7 @@ from transformers import pipeline
 import gradio as gr
 import os
 import torch
+import accelerate
 from diffusers import StableDiffusionPipeline, EulerDiscreteScheduler
 
 
@@ -39,6 +40,7 @@ def transcribe_text_audio(mic=None, file=None):
         audio = file
     else:
         return "No se ha detectado ninguna entrada de audio"
+
     transcription = model(audio)["text"]
 
     image = image_model(transcription).images[0]
@@ -53,5 +55,10 @@ gr.Interface(
         gr.Audio(sources=["microphone"], type="filepath"),
         gr.Audio(sources=["upload"], type="filepath"),
     ],
-    outputs=["text", "image"],
+    outputs=[
+      gr.Textbox(label="Transcripción del Audio"),
+      gr.Image(label="Imagen Generada")
+    ],
+    title="[ESpañol] - Audio -> Texto -> Imagen",
+    description="Esta aplicación transcribe el audio a texto para convertirlo en una imagen descriptiva."
 ).launch()