Update app.py

app.py

@@ -2,7 +2,6 @@ import gradio as gr
 from transformers import pipeline
 from PIL import Image, ImageOps
 import torch
-import timm
 
 
 #Definir 2 modelos uno de imagen a texto y otro de texto a audio que inyecta
@@ -19,25 +18,17 @@ text_to_audio_model = pipeline("text-to-speech")
 # Función para la interfaz de Gradio
 def image_to_audio(input_image):
     # Convertir la imagen a texto
-    model = timm.create_model("hf_hub:timm/mobilenetv3_large_100.ra_in1k", pretrained=True)
-    model = model.eval()
+     model=gr.Interface.load("models/timm/mobilenetv3_large_100.ra_in1k").launch()
+     text_output = image_to_text_model(model)[0]['label']
     # get model specific transforms (normalization, resize)
-    data_config = timm.data.resolve_model_data_config(model)
-    transforms = timm.data.create_transform(**data_config, is_training=False)
-    output = model(transforms(img).unsqueeze(0))  # unsqueeze single image into batch of 1
-    for o in output:
-
-        #text_output = image_to_text_model(input_image)[0]['label']
-        # Generar audio a partir del texto
-        audio_output = text_to_audio_model(o.shape)['audio']
-        print(o.shape)
+     audio_output = text_to_audio_model(model)['audio']
 
 
     
 # Interfaz Gradio
 iface = gr.Interface(
     fn=image_to_audio,
-    inputs= gr.Image(type="pil"),
+    inputs= gr.Image(type='PIL'),
     outputs="audio",
     live=True,
     interpretation="default",