Update app.py

app.py

@@ -1,34 +1,17 @@
-import gradio as gr
-import tensorflow as tf
 from transformers import BertTokenizer, BertModel
+import gradio as grad
 
-name = "MiVaCod/mbart-neutralization"
-tokenizer = BertTokenizer.from_pretrained(name)
-model = BertModel.from_pretrained(name)
+model_name = "MiVaCod/rotten"
+text2text_tkn= BertTokenizer.from_pretrained(model_name)
+mdl = BertModel.from_pretrained(model_name)
 
-# Define a function to make predictions
-def predict(texts):
-    # Tokenize and preprocess the new text
-    new_encodings = tokenizer(texts, truncation=True, padding=True, max_length=70, return_tensors='tf')
-    new_predictions = model(new_encodings)
-    # Make predictions
-    new_predictions = model(new_encodings)
-    new_labels_pred = tf.argmax(new_predictions.logits, axis=1)
-    new_labels_pred = new_labels_pred.numpy()[0]
+def text2text_paraphrase(sentence1):
+     inp1 = sentence1
+     enc = text2text_tkn(inp1, return_tensors="pt")
+     tokens = mdl.generate(**enc)
+     response=text2text_tkn.batch_decode(tokens)
+     return response
 
-    labels_list = ["Negative 😠", "Positive 😍"]
-    emotion = labels_list[new_labels_pred]
-    return emotion
-
-# Create a Gradio interface
-iface = gr.Interface(
-    fn=predict,
-    inputs="text",
-    outputs=gr.outputs.Label(num_top_classes = 6),  # Corrected output type
-    examples=[["the rock is destined to be the 21st century's new conan and that he's going to make a splash even greater than arnold schwarzenegger , jean-claud van damme or steven segal."],
-              ],
-    title="Rotten tomatoes classification",
-    description="Predict the class associated with a text."
-)
-# Launch the interfac
-iface.launch()
+sent1=grad.Textbox(lines=1, label="Review", placeholder="Introduce la review de una película.")
+out=gr.outputs.Label(num_top_classes=1)
+grad.Interface(text2text_paraphrase, inputs=sent1, outputs=out).launch()