Update app.py

app.py

@@ -1,28 +1,14 @@
-# import gradio as gr
-
-# from transformers import pipeline
-# classifier = pipeline('text-classification', model='nlmaldonadog/clasificador-rotten-tomatoes-xlnet-base-cased')
-
-# def predict(text):
-#     prediction = classifier(text)
-#     return prediction[0]  
-
-# iface = gr.Interface(fn=predict, inputs=[gr.Textbox(placeholder='Escribe aquí...')], outputs="text")
-# iface.launch(share=True)
-from huggingface_hub import from_pretrained_fastai
 import gradio as gr
-from fastai.text.all import *
 
-# Cargar el primer modelo
-repo_id1 = "nlmaldonadog/AWD_LSTM_P7"
-learner1 = from_pretrained_fastai(repo_id1)
-labels1 = learner1.dls.vocab
+from transformers import pipeline
 
-def predict1(text):
-    pred,pred_idx,probs = learner1.predict(text)
-    return str({labels1[i]: float(probs[i]) for i in range(len(labels1))})
+classifier3 = pipeline('text-classification', model='nlmaldonadog/clasificador-rotten-tomatoes-bert-base-uncased')
+classifier4 = pipeline('text-classification', model='nlmaldonadog/clasificador-rotten-tomatoes-xlnet-base-cased')
 
-texto = gr.Textbox(placeholder='Escribe aquí...')
+def predict(text):
+    prediction3 = classifier3(text)
+    prediction4 = classifier4(text)
+    return DatasetDict({'bert-base-uncased': prediction3, 'xlnet-base-cased': prediction4})
 
-# Creamos las interfaces y las lanzamos. 
-gr.Interface(fn=predict1, inputs=[texto], outputs="text").launch(share=True)
+iface = gr.Interface(fn=predict, inputs=[gr.Textbox(placeholder='Escribe aquí...')], outputs="text")
+iface.launch(share=True)